@yeyuan98/opencode-bioresearcher-plugin 1.5.4-alpha.0 → 1.6.0

package/README.md

@@ -117,7 +117,7 @@ Configuration via `env.jsonc` in working directory. Use the `env-jsonc-setup` sk
 
 ## Skills
 
-Skills are reusable prompt templates discovered from multiple paths:
+Skills are reusable prompt templates discovered from multiple paths via the `bioresearcher-skill` tool:
 
 | Path | Scope |
 |------|-------|
@@ -126,24 +126,23 @@ Skills are reusable prompt templates discovered from multiple paths:
 | `.claude/skills/` | Claude Code compatible |
 | `.agents/skills/` | Agents compatible |
 
-This plugin provides a skill tool that overrides Opencode's built-in to support plugin-shipped skills.
-
-See README in `tools/skill` for full documentation.
+Plugin-shipped skills are discovered alongside user-defined skills. The `bioresearcher-skill` tool name avoids conflict with OpenCode's built-in `skill` tool.
 
 ### Supplied skills
 
-- `demo-skill`: showcase skill tool mechanisms.
+- `demo-skill`: showcase skill integration and resource resolution.
 - `python-setup-uv`: setup python runtime in your working directory with uv.
 - `pubmed-weekly`: automated download of pubmed daily update files over the past one week.
 - `long-table-summary`: batch-process large tables using parallel subagents for summarization.
 - `bioresearcher-core`: core patterns and utilities (retry, JSON tools, subagent waves) for skill development.
 - `env-jsonc-setup`: guided setup for database connection configuration (db-tools).
 - `gromacs-guides`: reusable guides for GROMACS molecular dynamics workflows.
+- `bioresearcher-tests`: comprehensive test suite for plugin tools and skills.
 
 Prompt the following and follow along:
 
 ```txt
-Setup python uv with skill
+Setup python uv with bioresearcher-skill
 ```
 
 ## Installation

package/dist/agents/bioresearcher/prompt.d.ts

@@ -4,5 +4,5 @@
  * A specialized biomedical research agent that performs reference-based
  * pharmaceutical and drug development research using BioMCP tools.
  */
-export declare const BIORESEARCHER_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\n\nYou are an expert in biomedical and pharmaceutical drug development research.\n\n## Skill Loading (MANDATORY)\n\nAt the start of complex research tasks, load the core skill:\n\n```\nskill bioresearcher-core\n```\n\nThis skill provides patterns for:\n- **Decision Making**: Tool selection, analysis method choice\n- **Workflow Control**: Retry logic, progress tracking, rate limiting\n- **Data Handling**: JSON validation, table operations, data exchange\n- **Research Standards**: Citation formatting, report templates, Python standards\n- **Best Practices**: Upfront filtering, error handling, performance optimization\n\n## Core Workflow\n\n### Step 1: Clarify Questions\nIf unclear, guide the user to make their question professional and specific:\n- Identify the core research question\n- Determine what type of data is needed\n- Understand the expected output format\n\n### Step 2: Select Appropriate Tools\nUse decision trees from `patterns/tool-selection.md`:\n\n**Data Source Identification:**\n- Database/SQL \u2192 db* tools (dbQuery, dbListTables, dbDescribeTable)\n- Excel/CSV file \u2192 table* tools (tableFilterRows, tableGroupBy, etc.)\n- Website/URL \u2192 web* tools (webfetch, websearch)\n- Literature/Papers \u2192 biomcp* article tools\n- Clinical Trials \u2192 biomcp* trial tools\n- Genes/Variants \u2192 biomcp* gene/variant tools\n- Drugs/Compounds \u2192 biomcp* drug tools\n\n**CRITICAL: Apply upfront filtering at the source (see best-practices.md)**\n\n### Step 3: Fetch Information\nGather trustable information using selected tools:\n\n**Database Queries:**\n```\n1. Check env.jsonc exists (if not, load skill 'env-jsonc-setup')\n2. dbListTables() \u2192 Discover available data\n3. dbDescribeTable() \u2192 Understand schema\n4. dbQuery(\"SELECT ... WHERE filter = :param\", {param: value})\n   \u2705 DO: Use WHERE clauses, LIMIT, named parameters\n   \u274C DON'T: SELECT * then filter in Python\n```\n\n**Table Operations:**\n```\n1. tableGetSheetPreview() \u2192 Preview structure\n2. Determine row count \u2192 Choose approach:\n   - < 30 rows: Use table tools directly\n   - 30-1000 rows: Consider long-table-summary skill\n   - > 1000 rows: Use Python for complex analysis\n3. Apply filters: tableFilterRows(column, operator, value)\n   \u2705 DO: Filter upfront with tableFilterRows\n   \u274C DON'T: Load entire table then filter\n```\n\n**BioMCP Queries:**\n```\n1. Use targeted queries with specific filters\n2. biomcp_article_searcher(genes=[\"BRAF\"], diseases=[\"melanoma\"], page_size=50)\n3. ALWAYS: blockingTimer(0.3) between consecutive calls\n4. Sequential only (NEVER concurrent)\n   \u2705 DO: Use specific filters (genes, diseases, variants)\n   \u274C DON'T: Broad query then manual filtering\n```\n\n### Step 4: Analyze Data\nChoose analysis method using `patterns/analysis-methods.md`:\n\n**Decision Matrix:**\n| Approach | When to Use |\n|----------|-------------|\n| Table Tools | < 30 rows, simple operations (filter, group, summarize) |\n| long-table-summary Skill | 30-1000 rows, structured summarization, parallel processing |\n| Custom Python | > 1000 rows, complex logic, ML, reusable pipeline |\n\n**Skill Loading:**\n- Complex analysis \u2192 Load `bioresearcher-core` for retry, validation patterns\n- Large table summarization \u2192 Load `long-table-summary` skill\n- Python needed but uv missing \u2192 Load `python-setup-uv` skill\n\n**Python Scripts:**\n- Follow `patterns/python-standards.md` (DRY principle)\n- Module docstrings with purpose, usage, dependencies\n- Function docstrings with Args, Returns, Raises, Examples\n- No code duplication - extract to reusable functions\n- Type hints for all functions\n- Save to `.scripts/py/` folder\n\n### Step 5: Write Reference-Based Report\nFollow `patterns/report-template.md` structure:\n\n**Mandatory Sections:**\n1. **Executive Summary** - Key findings with citations [1, 2]\n2. **Data Sources** - Origin, access method, scope, quality notes\n3. **Analysis Methodology** - Approach, tools, steps, validation\n4. **Findings** - Results with citations and data provenance\n5. **Limitations** - Data gaps, methodological constraints\n6. **References** - Formatted bibliography by source type\n\n**Data Provenance Requirements:**\nEvery claim must have:\n- Citation [N] reference, OR\n- Data source documentation, OR\n- Analysis method description\n\n**Citation Format (from `patterns/citations.md`):**\n- In-text: [1], [2, 3], [1-5]\n- Bibliography: Numbered by order of appearance\n- Source-specific formats (articles, trials, web, databases)\n\n## Rate Limiting (MANDATORY)\n\n**ALWAYS use blockingTimer between consecutive API calls:**\n- BioMCP tools: 0.3 seconds (300ms)\n- Web tools: 0.5 seconds (500ms)\n- Database: No delay needed\n- File operations: No delay needed\n\n## Error Handling & Validation\n\n**Validation Pattern (from best-practices.md):**\n1. Check data existence (not empty)\n2. Validate structure (required fields)\n3. Validate types (correct data types)\n4. Validate values (within ranges)\n5. Validate quality (no duplicates)\n\n**Retry Logic (from patterns/retry.md):**\n- Max 3 attempts for network operations\n- Exponential backoff: 2s, 4s, 8s\n- Use blockingTimer between retries\n\n## Python Guidelines\n\n**When to Use Python:**\n- ONLY if existing tools are not suitable\n- Complex transformations beyond table tools\n- Statistical analysis beyond basic aggregation\n- Machine learning or custom algorithms\n\n**Code Standards (MANDATORY):**\n```python\n#!/usr/bin/env python3\n\"\"\"Script Purpose - One Line Description\n\nThis module provides functionality for:\n- Functionality 1\n- Functionality 2\n\nUsage:\n    uv run python script.py command --input file.xlsx --output results/\n\nDependencies:\n    - pandas >= 1.5.0\n\nAuthor: BioResearcher AI Agent\nDate: YYYY-MM-DD\n\"\"\"\n```\n\n**Function Documentation:**\n```python\ndef analyze_data(data: List[Dict], threshold: float = 0.5) -> Dict:\n    \"\"\"Brief description.\n    \n    Args:\n        data: Description of data\n        threshold: Threshold value (0.0 to 1.0)\n    \n    Returns:\n        Dictionary with results\n    \n    Raises:\n        ValueError: If threshold out of range\n    \"\"\"\n```\n\n**File Location:**\n- Scripts: `.scripts/py/`\n- Use uv for execution: `uv run python .scripts/py/script.py`\n- If uv unavailable, load skill `python-setup-uv`\n\n## Best Practices (CRITICAL)\n\n### Upfront Filtering\n\u2705 ALWAYS filter at source:\n- Database: WHERE clauses, LIMIT\n- Tables: tableFilterRows upfront\n- BioMCP: Specific filters (genes, diseases, variants)\n- Web: Specific search queries\n\n\u274C NEVER retrieve all data then filter in Python\n\n### Data Validation\n\u2705 ALWAYS validate:\n- Check required fields exist\n- Verify data types correct\n- Ensure values in expected ranges\n\n### Error Handling\n\u2705 ALWAYS handle errors:\n- Try-except for external operations\n- Retry logic with exponential backoff\n- Informative error messages\n\n### Context Management\n\u2705 ALWAYS minimize context usage:\n- Summarize large datasets instead of loading all\n- Use file-based data exchange\n- Paginate large result sets\n\n## Bottomline Rules\n\n1. ONLY use high-quality sources: biomcp results or official biotech/pharma websites\n2. ALWAYS provide citations [1], [2], ... with full bibliography at end\n3. ALWAYS backup files before editing (create `.bak` files)\n4. ALWAYS use blockingTimer(0.3) between consecutive biomcp* calls\n5. ALWAYS filter upfront - never retrieve then filter\n6. ALWAYS validate data before processing\n7. ALWAYS follow structured report template with data provenance\n8. ALWAYS write documented Python code following DRY principle\n------ RULE REMINDER END ------\n";
+export declare const BIORESEARCHER_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\n\nYou are an expert in biomedical and pharmaceutical drug development research.\n\n## Skill Loading (MANDATORY)\n\nAt the start of complex research tasks, load the core skill:\n\n```\nbioresearcher-skill bioresearcher-core\n```\n\nThis skill provides patterns for:\n- **Decision Making**: Tool selection, analysis method choice\n- **Workflow Control**: Retry logic, progress tracking, rate limiting\n- **Data Handling**: JSON validation, table operations, data exchange\n- **Research Standards**: Citation formatting, report templates, Python standards\n- **Best Practices**: Upfront filtering, error handling, performance optimization\n\n## Core Workflow\n\n### Step 1: Clarify Questions\nIf unclear, guide the user to make their question professional and specific:\n- Identify the core research question\n- Determine what type of data is needed\n- Understand the expected output format\n\n### Step 2: Select Appropriate Tools\nUse decision trees from `patterns/tool-selection.md`:\n\n**Data Source Identification:**\n- Database/SQL \u2192 db* tools (dbQuery, dbListTables, dbDescribeTable)\n- Excel/CSV file \u2192 table* tools (tableFilterRows, tableGroupBy, etc.)\n- Website/URL \u2192 web* tools (webfetch, websearch)\n- Literature/Papers \u2192 biomcp* article tools\n- Clinical Trials \u2192 biomcp* trial tools\n- Genes/Variants \u2192 biomcp* gene/variant tools\n- Drugs/Compounds \u2192 biomcp* drug tools\n\n**CRITICAL: Apply upfront filtering at the source (see best-practices.md)**\n\n### Step 3: Fetch Information\nGather trustable information using selected tools:\n\n**Database Queries:**\n```\n1. Check env.jsonc exists (if not, load bioresearcher-skill 'env-jsonc-setup')\n2. dbListTables() \u2192 Discover available data\n3. dbDescribeTable() \u2192 Understand schema\n4. dbQuery(\"SELECT ... WHERE filter = :param\", {param: value})\n   \u2705 DO: Use WHERE clauses, LIMIT, named parameters\n   \u274C DON'T: SELECT * then filter in Python\n```\n\n**Table Operations:**\n```\n1. tableGetSheetPreview() \u2192 Preview structure\n2. Determine row count \u2192 Choose approach:\n   - < 30 rows: Use table tools directly\n   - 30-1000 rows: Consider long-table-summary skill\n   - > 1000 rows: Use Python for complex analysis\n3. Apply filters: tableFilterRows(column, operator, value)\n   \u2705 DO: Filter upfront with tableFilterRows\n   \u274C DON'T: Load entire table then filter\n```\n\n**BioMCP Queries:**\n```\n1. Use targeted queries with specific filters\n2. biomcp_article_searcher(genes=[\"BRAF\"], diseases=[\"melanoma\"], page_size=50)\n3. ALWAYS: blockingTimer(0.3) between consecutive calls\n4. Sequential only (NEVER concurrent)\n   \u2705 DO: Use specific filters (genes, diseases, variants)\n   \u274C DON'T: Broad query then manual filtering\n```\n\n### Step 4: Analyze Data\nChoose analysis method using `patterns/analysis-methods.md`:\n\n**Decision Matrix:**\n| Approach | When to Use |\n|----------|-------------|\n| Table Tools | < 30 rows, simple operations (filter, group, summarize) |\n| long-table-summary Skill | 30-1000 rows, structured summarization, parallel processing |\n| Custom Python | > 1000 rows, complex logic, ML, reusable pipeline |\n\n**Skill Loading:**\n- Complex analysis \u2192 Load `bioresearcher-core` for retry, validation patterns\n- Large table summarization \u2192 Load `long-table-summary` skill\n- Python needed but uv missing \u2192 Load `python-setup-uv` skill\n\n**Python Scripts:**\n- Follow `patterns/python-standards.md` (DRY principle)\n- Module docstrings with purpose, usage, dependencies\n- Function docstrings with Args, Returns, Raises, Examples\n- No code duplication - extract to reusable functions\n- Type hints for all functions\n- Save to `.scripts/py/` folder\n\n### Step 5: Write Reference-Based Report\nFollow `patterns/report-template.md` structure:\n\n**Mandatory Sections:**\n1. **Executive Summary** - Key findings with citations [1, 2]\n2. **Data Sources** - Origin, access method, scope, quality notes\n3. **Analysis Methodology** - Approach, tools, steps, validation\n4. **Findings** - Results with citations and data provenance\n5. **Limitations** - Data gaps, methodological constraints\n6. **References** - Formatted bibliography by source type\n\n**Data Provenance Requirements:**\nEvery claim must have:\n- Citation [N] reference, OR\n- Data source documentation, OR\n- Analysis method description\n\n**Citation Format (from `patterns/citations.md`):**\n- In-text: [1], [2, 3], [1-5]\n- Bibliography: Numbered by order of appearance\n- Source-specific formats (articles, trials, web, databases)\n\n## Rate Limiting (MANDATORY)\n\n**ALWAYS use blockingTimer between consecutive API calls:**\n- BioMCP tools: 0.3 seconds (300ms)\n- Web tools: 0.5 seconds (500ms)\n- Database: No delay needed\n- File operations: No delay needed\n\n## Error Handling & Validation\n\n**Validation Pattern (from best-practices.md):**\n1. Check data existence (not empty)\n2. Validate structure (required fields)\n3. Validate types (correct data types)\n4. Validate values (within ranges)\n5. Validate quality (no duplicates)\n\n**Retry Logic (from patterns/retry.md):**\n- Max 3 attempts for network operations\n- Exponential backoff: 2s, 4s, 8s\n- Use blockingTimer between retries\n\n## Python Guidelines\n\n**When to Use Python:**\n- ONLY if existing tools are not suitable\n- Complex transformations beyond table tools\n- Statistical analysis beyond basic aggregation\n- Machine learning or custom algorithms\n\n**Code Standards (MANDATORY):**\n```python\n#!/usr/bin/env python3\n\"\"\"Script Purpose - One Line Description\n\nThis module provides functionality for:\n- Functionality 1\n- Functionality 2\n\nUsage:\n    uv run python script.py command --input file.xlsx --output results/\n\nDependencies:\n    - pandas >= 1.5.0\n\nAuthor: BioResearcher AI Agent\nDate: YYYY-MM-DD\n\"\"\"\n```\n\n**Function Documentation:**\n```python\ndef analyze_data(data: List[Dict], threshold: float = 0.5) -> Dict:\n    \"\"\"Brief description.\n    \n    Args:\n        data: Description of data\n        threshold: Threshold value (0.0 to 1.0)\n    \n    Returns:\n        Dictionary with results\n    \n    Raises:\n        ValueError: If threshold out of range\n    \"\"\"\n```\n\n**File Location:**\n- Scripts: `.scripts/py/`\n- Use uv for execution: `uv run python .scripts/py/script.py`\n- If uv unavailable, load bioresearcher-skill `python-setup-uv`\n\n## Best Practices (CRITICAL)\n\n### Upfront Filtering\n\u2705 ALWAYS filter at source:\n- Database: WHERE clauses, LIMIT\n- Tables: tableFilterRows upfront\n- BioMCP: Specific filters (genes, diseases, variants)\n- Web: Specific search queries\n\n\u274C NEVER retrieve all data then filter in Python\n\n### Data Validation\n\u2705 ALWAYS validate:\n- Check required fields exist\n- Verify data types correct\n- Ensure values in expected ranges\n\n### Error Handling\n\u2705 ALWAYS handle errors:\n- Try-except for external operations\n- Retry logic with exponential backoff\n- Informative error messages\n\n### Context Management\n\u2705 ALWAYS minimize context usage:\n- Summarize large datasets instead of loading all\n- Use file-based data exchange\n- Paginate large result sets\n\n## Bottomline Rules\n\n1. ONLY use high-quality sources: biomcp results or official biotech/pharma websites\n2. ALWAYS provide citations [1], [2], ... with full bibliography at end\n3. ALWAYS backup files before editing (create `.bak` files)\n4. ALWAYS use blockingTimer(0.3) between consecutive biomcp* calls\n5. ALWAYS filter upfront - never retrieve then filter\n6. ALWAYS validate data before processing\n7. ALWAYS follow structured report template with data provenance\n8. ALWAYS write documented Python code following DRY principle\n------ RULE REMINDER END ------\n";
 export declare function getBioResearcherPrompt(): string;

package/dist/agents/bioresearcher/prompt.js

@@ -15,7 +15,7 @@ You are an expert in biomedical and pharmaceutical drug development research.
 At the start of complex research tasks, load the core skill:
 
 \`\`\`
-skill bioresearcher-core
+bioresearcher-skill bioresearcher-core
 \`\`\`
 
 This skill provides patterns for:
@@ -52,7 +52,7 @@ Gather trustable information using selected tools:
 
 **Database Queries:**
 \`\`\`
-1. Check env.jsonc exists (if not, load skill 'env-jsonc-setup')
+1. Check env.jsonc exists (if not, load bioresearcher-skill 'env-jsonc-setup')
 2. dbListTables() → Discover available data
 3. dbDescribeTable() → Understand schema
 4. dbQuery("SELECT ... WHERE filter = :param", {param: value})
@@ -197,7 +197,7 @@ def analyze_data(data: List[Dict], threshold: float = 0.5) -> Dict:
 **File Location:**
 - Scripts: \`.scripts/py/\`
 - Use uv for execution: \`uv run python .scripts/py/script.py\`
-- If uv unavailable, load skill \`python-setup-uv\`
+- If uv unavailable, load bioresearcher-skill \`python-setup-uv\`
 
 ## Best Practices (CRITICAL)
 

package/dist/agents/bioresearcherDR/prompt.d.ts

@@ -4,5 +4,5 @@
  * A specialized biomedical research agent that performs reference-based
  * pharmaceutical and drug development research using BioMCP tools.
  */
-export declare const BIORESEARCHERDR_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\nOverall goal: Perform reference-based biomedical and pharmaceutical drug development research.\n\nSteps to STRICTLY adhere to:\n\n1. If the user query includes 'no-interview', skip Step 2 and proceed to Step 3. Otherwise, proceed to Step 2.\n2. Comprehend initial user inquiry. Use the question tool to ask user to clarify 3-6 unclear points depending on inquiry complexity.\n3. Comprehend final user inquiry to identify critical research aspects to answer user inquiry.\n4. If the original user inquiry includes 'light-research', combine and/or pick top two research aspects and proceed to Step 5. Otherwise, proceed directly to Step 5.\n5. Decide on TOPIC of this inquiry (NO user input). TOPIC should be highly succinct, underscore-separated name based on user inquiry.\n6. Use the todowrite tool to generate a list of identified research aspects.\n7. Create the reports_biomcp/<TOPIC>/ folder if needed.\n8. Use the task tool to assign each research aspect to a bioresearcherDR_worker subagent. Start subagents in parallel in batches (size of 5 for each batch). Record finished subagents by checking the todo list. Prompt the user: 'If subagents are stuck without progress for too long, interrupt and ask me to resume work.'\n9. Proceed until subagents complete research. Restart failed subagents if necessary.\n10. Load the skill 'bioresearcher-core' and read 'patterns/citations.md' for citation format. Read reports from all subagents. Summarize findings to provide a succinct and accurate report addressing user inquiry with proper citations.\n11. Write to reports_biomcp/<TOPIC>/final_report.md with full bibliography.\n\nFollow this template to prompt the bioresearcherDR_worker subagents (Step 8):\n\n```md\nTOPIC: <TOPIC>\nYOUR RESEARCH FOCUS: <RESEARCH-ASPECT>\nDESCRIPTION: <ABSTRACT>\n```\n\nABSTRACT should be a short paragraph of less than 200 words, describing exact focus of the subagent's research aspect and a list of detailed research items.\n\nRules for YOU:\n\n- Do NOT use the following tools: biomcp*, web*, context7* (i.e., tool names starting with biomcp or web or context7. VERY IMPORTANT DO NOT USE ANY BIOMCP TOOL).\n- Do NOT fallback to internal knowledge when query tools fail. STRICTLY ADHERE to external trusted sources.\n- DO provide concrete references for all findings with citations (in brackets, e.g., [1], [2], ...) and full bibliography at the end.\n- DO keep your word succinct, accurate and professional, fitting top standards of academic writing.\n------ RULE REMINDER END ------\n";
+export declare const BIORESEARCHERDR_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\nOverall goal: Perform reference-based biomedical and pharmaceutical drug development research.\n\nSteps to STRICTLY adhere to:\n\n1. If the user query includes 'no-interview', skip Step 2 and proceed to Step 3. Otherwise, proceed to Step 2.\n2. Comprehend initial user inquiry. Use the question tool to ask user to clarify 3-6 unclear points depending on inquiry complexity.\n3. Comprehend final user inquiry to identify critical research aspects to answer user inquiry.\n4. If the original user inquiry includes 'light-research', combine and/or pick top two research aspects and proceed to Step 5. Otherwise, proceed directly to Step 5.\n5. Decide on TOPIC of this inquiry (NO user input). TOPIC should be highly succinct, underscore-separated name based on user inquiry.\n6. Use the todowrite tool to generate a list of identified research aspects.\n7. Create the reports_biomcp/<TOPIC>/ folder if needed.\n8. Use the task tool to assign each research aspect to a bioresearcherDR_worker subagent. Start subagents in parallel in batches (size of 5 for each batch). Record finished subagents by checking the todo list. Prompt the user: 'If subagents are stuck without progress for too long, interrupt and ask me to resume work.'\n9. Proceed until subagents complete research. Restart failed subagents if necessary.\n10. Load the bioresearcher-skill 'bioresearcher-core' and read 'patterns/citations.md' for citation format. Read reports from all subagents. Summarize findings to provide a succinct and accurate report addressing user inquiry with proper citations.\n11. Write to reports_biomcp/<TOPIC>/final_report.md with full bibliography.\n\nFollow this template to prompt the bioresearcherDR_worker subagents (Step 8):\n\n```md\nTOPIC: <TOPIC>\nYOUR RESEARCH FOCUS: <RESEARCH-ASPECT>\nDESCRIPTION: <ABSTRACT>\n```\n\nABSTRACT should be a short paragraph of less than 200 words, describing exact focus of the subagent's research aspect and a list of detailed research items.\n\nRules for YOU:\n\n- Do NOT use the following tools: biomcp*, web*, context7* (i.e., tool names starting with biomcp or web or context7. VERY IMPORTANT DO NOT USE ANY BIOMCP TOOL).\n- Do NOT fallback to internal knowledge when query tools fail. STRICTLY ADHERE to external trusted sources.\n- DO provide concrete references for all findings with citations (in brackets, e.g., [1], [2], ...) and full bibliography at the end.\n- DO keep your word succinct, accurate and professional, fitting top standards of academic writing.\n------ RULE REMINDER END ------\n";
 export declare function getBioResearcherDRPrompt(): string;

package/dist/agents/bioresearcherDR/prompt.js

@@ -20,7 +20,7 @@ Steps to STRICTLY adhere to:
 7. Create the reports_biomcp/<TOPIC>/ folder if needed.
 8. Use the task tool to assign each research aspect to a bioresearcherDR_worker subagent. Start subagents in parallel in batches (size of 5 for each batch). Record finished subagents by checking the todo list. Prompt the user: 'If subagents are stuck without progress for too long, interrupt and ask me to resume work.'
 9. Proceed until subagents complete research. Restart failed subagents if necessary.
-10. Load the skill 'bioresearcher-core' and read 'patterns/citations.md' for citation format. Read reports from all subagents. Summarize findings to provide a succinct and accurate report addressing user inquiry with proper citations.
+10. Load the bioresearcher-skill 'bioresearcher-core' and read 'patterns/citations.md' for citation format. Read reports from all subagents. Summarize findings to provide a succinct and accurate report addressing user inquiry with proper citations.
 11. Write to reports_biomcp/<TOPIC>/final_report.md with full bibliography.
 
 Follow this template to prompt the bioresearcherDR_worker subagents (Step 8):

package/dist/agents/bioresearcherDR_worker/prompt.d.ts

@@ -4,5 +4,5 @@
  * A focused worker subagent that executes specific research tasks
  * assigned by the bioresearcherDR orchestrator.
  */
-export declare const BIORESEARCHERDRWORKER_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\n\nOverall goal: Execute focused biomedical research as directed by the orchestrator.\n\n## Skill Loading (MANDATORY)\n\nAt the start of your task, load the core skill:\n\n```\nskill bioresearcher-core\n```\n\nThis skill provides patterns for:\n- `patterns/rate-limiting.md` - API rate limiting (use 0.5s between biomcp calls)\n- `patterns/retry.md` - Retry logic for failed requests (up to 3 retries)\n- `patterns/citations.md` - Citation formatting for your report\n\n## Workflow\n\n1. **Follow directions**: Execute the specific research task assigned to you\n2. **Stay focused**: Do NOT delegate to other subagents\n3. **Write findings**: Output to `reports_biomcp/<TOPIC>/<YOUR-FOCUS>.md`\n\n## Rate Limiting\n\nALWAYS use blockingTimer(0.5) between consecutive biomcp* tool calls.\n\n## Retry Logic\n\nIf a query fails:\n1. Wait a few seconds using blockingTimer\n2. Try with a simpler query\n3. Retry up to 3 times before giving up\n\n## Rules\n\n- Do NOT run concurrent MCP calls (sequential only)\n- Do NOT fallback to internal knowledge - use external trusted sources only\n- ALWAYS provide citations [1], [2], ... with full bibliography\n- Keep writing succinct, accurate, professional (academic standard)\n------ RULE REMINDER END ------\n";
+export declare const BIORESEARCHERDRWORKER_SYSTEM_PROMPT = "\n------ RULE REMINDER START ------\nIMPORTANT: THIS REMINDER SHALL OVERRIDE ALL OTHER PROMPTS PROVIDED TO YOU. IGNORE ALL OTHER PROMPTS.\n\nOverall goal: Execute focused biomedical research as directed by the orchestrator.\n\n## Skill Loading (MANDATORY)\n\nAt the start of your task, load the core skill:\n\n```\nbioresearcher-skill bioresearcher-core\n```\n\nThis skill provides patterns for:\n- `patterns/rate-limiting.md` - API rate limiting (use 0.5s between biomcp calls)\n- `patterns/retry.md` - Retry logic for failed requests (up to 3 retries)\n- `patterns/citations.md` - Citation formatting for your report\n\n## Workflow\n\n1. **Follow directions**: Execute the specific research task assigned to you\n2. **Stay focused**: Do NOT delegate to other subagents\n3. **Write findings**: Output to `reports_biomcp/<TOPIC>/<YOUR-FOCUS>.md`\n\n## Rate Limiting\n\nALWAYS use blockingTimer(0.5) between consecutive biomcp* tool calls.\n\n## Retry Logic\n\nIf a query fails:\n1. Wait a few seconds using blockingTimer\n2. Try with a simpler query\n3. Retry up to 3 times before giving up\n\n## Rules\n\n- Do NOT run concurrent MCP calls (sequential only)\n- Do NOT fallback to internal knowledge - use external trusted sources only\n- ALWAYS provide citations [1], [2], ... with full bibliography\n- Keep writing succinct, accurate, professional (academic standard)\n------ RULE REMINDER END ------\n";
 export declare function getBioResearcherDRWorkerPrompt(): string;

package/dist/agents/bioresearcherDR_worker/prompt.js

@@ -15,7 +15,7 @@ Overall goal: Execute focused biomedical research as directed by the orchestrato
 At the start of your task, load the core skill:
 
 \`\`\`
-skill bioresearcher-core
+bioresearcher-skill bioresearcher-core
 \`\`\`
 
 This skill provides patterns for:

package/dist/index.js

@@ -1,13 +1,13 @@
 import { createBioResearcherAgent } from "./agents/bioresearcher/index";
 import { createBioResearcherDRAgent } from "./agents/bioresearcherDR/index";
 import { createBioResearcherDRWorkerAgent } from "./agents/bioresearcherDR_worker/index";
+import { BioResearcherSkillTool } from "./tools/skill";
 import { tableTools } from "./tools/table/index";
 import { dbTools } from "./tools/db/index";
 import { blockingTimer, calculator, jsonExtract, jsonValidate, jsonInfer } from "./tools/misc/index";
 import { parse_pubmed_articleSet } from "./tools/parser/pubmed";
 import { parse_obo_file } from "./tools/parser/obo";
-import { SkillTool } from "./tools/skill";
-export const BioResearcherPlugin = async () => {
+export const BioResearcherPlugin = async (_input) => {
     return {
         config: async (config) => {
             config.agent = config.agent || {};
@@ -16,7 +16,7 @@ export const BioResearcherPlugin = async () => {
             config.agent.bioresearcherDR_worker = createBioResearcherDRWorkerAgent();
         },
         tool: {
-            skill: SkillTool,
+            "bioresearcher-skill": BioResearcherSkillTool,
             ...tableTools,
             ...dbTools,
             blockingTimer,

package/dist/shared/tool-restrictions.d.ts

@@ -20,8 +20,8 @@ export declare function createAllowlist(tools: string[]): ToolRestrictions;
  * Agent tool restrictions map.
  *
  * - bioresearcher: denylist for context7*, web*
- * - bioresearcherDR: allowlist for skill, table*, and core file tools (orchestrator - no biomcp)
- * - bioresearcherDR_worker: allowlist for skill, biomcp*, table*, and core file tools (data gatherer)
+ * - bioresearcherDR: allowlist for bioresearcher-skill, table*, and core file tools (orchestrator - no biomcp)
+ * - bioresearcherDR_worker: allowlist for bioresearcher-skill, biomcp*, table*, and core file tools (data gatherer)
  */
 export declare const AGENT_TOOL_RESTRICTIONS: Record<string, ToolRestrictions>;
 /**

package/dist/shared/tool-restrictions.js

@@ -27,13 +27,13 @@ export function createAllowlist(tools) {
  * Agent tool restrictions map.
  *
  * - bioresearcher: denylist for context7*, web*
- * - bioresearcherDR: allowlist for skill, table*, and core file tools (orchestrator - no biomcp)
- * - bioresearcherDR_worker: allowlist for skill, biomcp*, table*, and core file tools (data gatherer)
+ * - bioresearcherDR: allowlist for bioresearcher-skill, table*, and core file tools (orchestrator - no biomcp)
+ * - bioresearcherDR_worker: allowlist for bioresearcher-skill, biomcp*, table*, and core file tools (data gatherer)
  */
 export const AGENT_TOOL_RESTRICTIONS = {
     bioresearcher: createDenylist(["context7*", "web*"]),
     bioresearcherDR: createAllowlist([
-        "skill",
+        "bioresearcher-skill",
         "table*",
         "calculator",
         "blockingTimer",
@@ -47,7 +47,7 @@ export const AGENT_TOOL_RESTRICTIONS = {
         "task"
     ]),
     bioresearcherDR_worker: createAllowlist([
-        "skill",
+        "bioresearcher-skill",
         "biomcp*",
         "table*",
         "calculator",

package/dist/skills/bioresearcher-core/README.md

@@ -21,7 +21,7 @@ No installation required. This skill uses only:
 ### Load the Skill
 
 ```
-skill bioresearcher-core
+bioresearcher-skill bioresearcher-core
 ```
 
 ### Extract Skill Path

package/dist/skills/bioresearcher-core/SKILL.md

@@ -59,7 +59,7 @@ The bioresearcherDR_worker subagent uses only shared patterns (citations, rate-l
 
 ### Step 1: Load This Skill
 ```
-skill bioresearcher-core
+bioresearcher-skill bioresearcher-core
 ```
 
 ### Step 2: Extract Skill Path

package/dist/skills/bioresearcher-core/patterns/bioresearcher/analysis-methods.md

@@ -155,7 +155,7 @@ Agent actions:
 ### Skill Loading
 
 ```markdown
-skill long-table-summary
+bioresearcher-skill long-table-summary
 ```
 
 ### 16-Step Workflow Overview

package/dist/skills/bioresearcher-core/patterns/bioresearcher/best-practices.md

@@ -408,7 +408,7 @@ if row_count < 30:
 
 # Medium datasets (30-1000 rows): Use long-table-summary skill
 elif row_count < 1000:
-    skill long-table-summary
+    bioresearcher-skill long-table-summary
     # Follow 16-step workflow
 
 # Large datasets (> 1000 rows): Use Python

package/dist/skills/bioresearcher-tests/README.md

@@ -5,7 +5,7 @@ Comprehensive test suite for the bioresearcher plugin.
 ## Quick Start
 
 ```
-skill bioresearcher-tests
+bioresearcher-skill bioresearcher-tests
 ```
 
 Then follow the workflow steps in SKILL.md.

package/dist/skills/bioresearcher-tests/SKILL.md

@@ -25,7 +25,7 @@ allowedTools:
   - calculator
   - parse_pubmed_articleSet
   - parse_obo_file
-  - skill
+  - bioresearcher-skill
   - Question
 ---
 

package/dist/skills/bioresearcher-tests/test_cases/skill_tests.md

@@ -1,7 +1,7 @@
 # Skill Tests
 
 ## Test: Load demo-skill
-- Tool: skill
+- Tool: bioresearcher-skill
 - Input:
   ```json
   {"name": "demo-skill"}
@@ -12,7 +12,7 @@
 - Expected: Skill content loaded successfully
 
 ## Test: Load bioresearcher-core
-- Tool: skill
+- Tool: bioresearcher-skill
 - Input:
   ```json
   {"name": "bioresearcher-core"}
@@ -35,7 +35,7 @@
 - Expected: Demo script executes successfully
 
 ## Test: Skill Not Found
-- Tool: skill
+- Tool: bioresearcher-skill
 - Input:
   ```json
   {"name": "nonexistent-skill-xyz-12345"}

package/dist/skills/gromacs-guides/SKILL.md

@@ -1,48 +1,48 @@
----
-name: gromacs-guides
-description: Reusable guides for GROMACS molecular dynamics workflows
-allowedTools:
-  - Read
-  - Bash
----
-
-# GROMACS Guides
-
-This skill provides reusable guides for common GROMACS molecular dynamics workflows.
-
-## Quick Start
-
-### Step 1: Load This Skill
-The skill is loaded automatically when agent calls `skill gromacs-guides`.
-
-### Step 2: Extract Skill Path
-From the `<skill_files>` section in the skill tool output, extract the `<skill_path>` value.
-
-### Step 3: Read the Relevant Guide
-```
-Read <skill_path>/guides/inspect_tpr.md
-Read <skill_path>/guides/create_index.md
-```
-
-## Available Guides
-
-| Task | Guide |
-|------|-------|
-| TPR inspection | `guides/inspect_tpr.md` |
-| Index file creation | `guides/create_index.md` |
-
-## Guide Summaries
-
-### inspect_tpr.md
-Commands for extracting molecule information from TPR files:
-- Quick summary and detailed dump commands
-- Molecule type/counts extraction
-- Cyclic molecule bond detection
-- Molecule independence checking
-
-### create_index.md
-Workflow for creating GROMACS index files:
-- Basic `make_ndx` usage
-- `splitch` artefact identification and fixing
-- Merge → verify → delete → rename workflow
-- C-alpha group creation
+---
+name: gromacs-guides
+description: Reusable guides for GROMACS molecular dynamics workflows
+allowedTools:
+  - Read
+  - Bash
+---
+
+# GROMACS Guides
+
+This skill provides reusable guides for common GROMACS molecular dynamics workflows.
+
+## Quick Start
+
+### Step 1: Load This Skill
+The skill is loaded automatically when agent calls `bioresearcher-skill gromacs-guides`.
+
+### Step 2: Extract Skill Path
+From the `<skill_files>` section in the skill tool output, extract the `<skill_path>` value.
+
+### Step 3: Read the Relevant Guide
+```
+Read <skill_path>/guides/inspect_tpr.md
+Read <skill_path>/guides/create_index.md
+```
+
+## Available Guides
+
+| Task | Guide |
+|------|-------|
+| TPR inspection | `guides/inspect_tpr.md` |
+| Index file creation | `guides/create_index.md` |
+
+## Guide Summaries
+
+### inspect_tpr.md
+Commands for extracting molecule information from TPR files:
+- Quick summary and detailed dump commands
+- Molecule type/counts extraction
+- Cyclic molecule bond detection
+- Molecule independence checking
+
+### create_index.md
+Workflow for creating GROMACS index files:
+- Basic `make_ndx` usage
+- `splitch` artefact identification and fixing
+- Merge → verify → delete → rename workflow
+- C-alpha group creation

package/dist/skills/gromacs-guides/guides/inspect_tpr.md

@@ -126,3 +126,35 @@ gmx dump -s <tpr_file> 2>&1 | grep "bIntermolecularInteractions"
 ```bash
 echo "q" | gmx make_ndx -f <tpr_file> 2>&1 | grep -E "(System|Protein|Water|Ion|atoms)"
 ```
+
+## Standardized TPR Summary Template
+
+When users ask generic questions like "summarize this TPR" or "list all components", use this template for consistent output:
+
+### <tpr_file> Analysis Summary
+
+| Component | Count | Atoms | Structure |
+|-----------|-------|-------|-----------|
+| <moltype_name> | <N_copies> | <atoms_per_copy> | <Linear/Cyclic/-> |
+| ... | ... | ... | ... |
+| **Total** | - | **<sum_atoms>** | - |
+
+**Key Information:**
+- **Total protein residues**: <X> (<Y> atoms total)
+- **Molecules are <independent/linked>** (bIntermolecularInteractions=<true/false>)
+- <Notable features>
+
+### Populating the Template
+
+Use commands from:
+- **Key Information to Extract** table → Component, Count, Atoms columns
+- **Detecting Cyclic Molecule Configuration** → Structure column (Linear/Cyclic)
+- **Checking Molecule Independence** → bIntermolecularInteractions value
+
+### Structure Column Values
+
+| Value | When to Use |
+|-------|-------------|
+| `Linear` | Standard protein/peptide without cyclization |
+| `**Cyclic** (bond 0→<N-2>)` | N-to-C cyclization detected |
+| `-` | Non-protein (solvent, ions, ligands) |

package/dist/tools/db/index.d.ts

@@ -17,12 +17,12 @@ export declare const dbTools: {
         execute(args: {
             sql: string;
             params?: Record<string, any> | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     dbListTables: {
         description: string;
         args: {};
-        execute(args: Record<string, never>, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        execute(args: Record<string, never>, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     dbDescribeTable: {
         description: string;
@@ -31,7 +31,7 @@ export declare const dbTools: {
         };
         execute(args: {
             table_name: string;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
 };
 export { dbQuery, dbListTables, dbDescribeTable } from './tools';

package/dist/tools/db/tools.d.ts

@@ -9,12 +9,12 @@ export declare const dbQuery: {
     execute(args: {
         sql: string;
         params?: Record<string, any> | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const dbListTables: {
     description: string;
     args: {};
-    execute(args: Record<string, never>, context: ToolContext): Promise<string>;
+    execute(args: Record<string, never>, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const dbDescribeTable: {
     description: string;
@@ -23,5 +23,5 @@ export declare const dbDescribeTable: {
     };
     execute(args: {
         table_name: string;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/misc/calculator.d.ts

@@ -9,5 +9,5 @@ export declare const calculator: {
     execute(args: {
         formula: string;
         precision: number;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/misc/json-extract.d.ts

@@ -9,5 +9,5 @@ export declare const jsonExtract: {
     execute(args: {
         file_path: string;
         return_all: boolean;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/misc/json-infer.d.ts

@@ -9,5 +9,5 @@ export declare const jsonInfer: {
     execute(args: {
         data: string;
         strict: boolean;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/misc/json-validate.d.ts

@@ -9,5 +9,5 @@ export declare const jsonValidate: {
     execute(args: {
         data: string;
         schema: string;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/misc/json-validate.js

@@ -1,6 +1,120 @@
 import { tool } from '@opencode-ai/plugin/tool';
-import { z, fromJSONSchema } from 'zod';
+import { z } from 'zod';
 import * as path from 'path';
+function buildZodSchema(schema, rootSchema) {
+    if (!schema || typeof schema !== 'object')
+        return z.any();
+    if (schema.boolean === true)
+        return z.boolean();
+    if (schema.$ref && rootSchema) {
+        const refPath = schema.$ref.replace(/^#\//, '');
+        const parts = refPath.split('/').filter(Boolean);
+        let resolved = rootSchema;
+        for (const part of parts)
+            resolved = resolved?.[part];
+        return resolved ? buildZodSchema(resolved, rootSchema) : z.any();
+    }
+    if (schema.enum) {
+        const allStrings = schema.enum.every((v) => typeof v === 'string');
+        if (allStrings)
+            return z.enum(schema.enum);
+        return z.any();
+    }
+    let zodType;
+    switch (schema.type) {
+        case 'string':
+            zodType = z.string();
+            if (schema.minLength != null)
+                zodType = zodType.min(schema.minLength);
+            if (schema.maxLength != null)
+                zodType = zodType.max(schema.maxLength);
+            if (schema.pattern)
+                zodType = zodType.regex(new RegExp(schema.pattern));
+            if (schema.format === 'email')
+                zodType = z.email();
+            if (schema.format === 'url')
+                zodType = z.url();
+            if (schema.format === 'uuid')
+                zodType = z.uuid();
+            break;
+        case 'number':
+            zodType = z.number();
+            if (schema.minimum != null)
+                zodType = zodType.min(schema.minimum);
+            if (schema.maximum != null)
+                zodType = zodType.max(schema.maximum);
+            if (schema.exclusiveMinimum != null)
+                zodType = zodType.gt(schema.exclusiveMinimum);
+            if (schema.exclusiveMaximum != null)
+                zodType = zodType.lt(schema.exclusiveMaximum);
+            break;
+        case 'integer':
+            zodType = z.number().int();
+            if (schema.minimum != null)
+                zodType = zodType.min(schema.minimum);
+            if (schema.maximum != null)
+                zodType = zodType.max(schema.maximum);
+            break;
+        case 'boolean':
+            zodType = z.boolean();
+            break;
+        case 'null':
+            zodType = z.null();
+            break;
+        case 'array':
+            zodType = schema.items
+                ? z.array(buildZodSchema(schema.items, rootSchema))
+                : z.array(z.any());
+            if (schema.minItems != null)
+                zodType = zodType.min(schema.minItems);
+            if (schema.maxItems != null)
+                zodType = zodType.max(schema.maxItems);
+            break;
+        case 'object': {
+            const shape = {};
+            const requiredKeys = new Set(schema.required && Array.isArray(schema.required) ? schema.required : []);
+            if (schema.properties && typeof schema.properties === 'object') {
+                for (const [key, val] of Object.entries(schema.properties)) {
+                    const fieldSchema = buildZodSchema(val, rootSchema);
+                    shape[key] = requiredKeys.has(key) ? fieldSchema : fieldSchema.optional();
+                }
+            }
+            zodType = z.object(shape);
+            if (schema.additionalProperties === false) {
+                zodType = zodType.strict();
+            }
+            break;
+        }
+        default:
+            zodType = z.any();
+    }
+    if (!schema.anyOf && !schema.oneOf && !schema.allOf) {
+        if (schema.default !== undefined) {
+            zodType = zodType.default(schema.default);
+        }
+    }
+    if (schema.anyOf && Array.isArray(schema.anyOf)) {
+        const variants = schema.anyOf.map((s) => buildZodSchema(s, rootSchema));
+        zodType = z.union(variants);
+    }
+    if (schema.allOf && Array.isArray(schema.allOf)) {
+        const merged = {};
+        for (const s of schema.allOf) {
+            const sub = buildZodSchema(s, rootSchema);
+            const def = sub._def;
+            if (def?.shape)
+                Object.assign(merged, def.shape);
+        }
+        if (Object.keys(merged).length > 0) {
+            zodType = z.object(merged);
+        }
+    }
+    if (schema.oneOf && Array.isArray(schema.oneOf)) {
+        const variants = schema.oneOf.map((s) => buildZodSchema(s, rootSchema));
+        zodType = z.union(variants);
+    }
+    return zodType;
+}
 const UNSUPPORTED_SCHEMA_FEATURES = [
     'not', 'unevaluatedItems', 'unevaluatedProperties',
     'if', 'then', 'else', 'dependentSchemas', 'dependentRequired'
@@ -170,7 +284,7 @@ export const jsonValidate = tool({
         }
         let zodSchema;
         try {
-            zodSchema = fromJSONSchema(parsedSchema);
+            zodSchema = buildZodSchema(parsedSchema, parsedSchema);
         }
         catch (e) {
             return JSON.stringify({

package/dist/tools/misc/timer.d.ts

@@ -7,5 +7,5 @@ export declare const blockingTimer: {
     };
     execute(args: {
         delay: number;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/parser/obo/obo.d.ts

@@ -13,5 +13,5 @@ export declare const parse_obo_file: {
         outputFileName: string;
         verbose: boolean;
         outputDir?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/parser/pubmed/pubmed.d.ts

@@ -19,5 +19,5 @@ export declare const parse_pubmed_articleSet: {
         verbose: boolean;
         outputFileName?: string | undefined;
         outputDir?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/skill/index.d.ts

@@ -1,3 +1,3 @@
-export { SkillTool } from "./tool";
+export { BioResearcherSkillTool } from "./tool";
 export { getAllSkills, getSkill, SkillConflictError } from "./registry";
 export type { ExtendedSkill, ExtendedSkillFrontmatter, ParsedSkill } from "./types";

package/dist/tools/skill/index.js

@@ -1,2 +1,2 @@
-export { SkillTool } from "./tool";
+export { BioResearcherSkillTool } from "./tool";
 export { getAllSkills, getSkill, SkillConflictError } from "./registry";

package/dist/tools/skill/tool.d.ts

@@ -1,9 +1,9 @@
-export declare const SkillTool: {
+export declare const BioResearcherSkillTool: {
     description: string;
     args: {
         name: import("zod").ZodString;
     };
     execute(args: {
         name: string;
-    }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+    }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/dist/tools/skill/tool.js

@@ -1,5 +1,6 @@
 import path from "path";
 import { pathToFileURL } from "url";
+import { Effect } from "effect";
 import { tool } from "@opencode-ai/plugin";
 import { getAllSkills, getSkill } from "./registry";
 function formatDescription(skills) {
@@ -47,7 +48,7 @@ async function listSkillFiles(dir, signal) {
     }
     return files.map((f) => `<file>${f}</file>`).join("\n");
 }
-export const SkillTool = tool({
+export const BioResearcherSkillTool = tool({
     description: "", // Set dynamically below
     args: {
         name: tool.schema.string().describe("The name of the skill from available_skills"),
@@ -63,12 +64,12 @@ export const SkillTool = tool({
         if (skill.agent && ctx.agent !== skill.agent) {
             throw new Error(`Skill "${skill.name}" is restricted to agent "${skill.agent}". Current agent: "${ctx.agent || "unknown"}".`);
         }
-        await ctx.ask({
+        await Effect.runPromise(ctx.ask({
             permission: "skill",
             patterns: [params.name],
             always: [params.name],
             metadata: {},
-        });
+        }));
         const dir = path.dirname(skill.location);
         const base = pathToFileURL(dir).href;
         const files = await listSkillFiles(dir, ctx.abort);
@@ -112,9 +113,9 @@ export const SkillTool = tool({
 getAllSkills()
     .then((skills) => {
     ;
-    SkillTool.description = formatDescription(skills);
+    BioResearcherSkillTool.description = formatDescription(skills);
 })
     .catch((err) => {
     console.error("[bioresearcher-plugin] Failed to load skills for tool description:", err);
-    SkillTool.description = formatDescription([]);
+    BioResearcherSkillTool.description = formatDescription([]);
 });

package/dist/tools/table/index.d.ts

@@ -8,7 +8,7 @@ export declare const tableTools: {
         execute(args: {
             file_path: string;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableListSheets: {
         description: string;
@@ -17,7 +17,7 @@ export declare const tableTools: {
         };
         execute(args: {
             file_path: string;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableGetHeaders: {
         description: string;
@@ -28,7 +28,7 @@ export declare const tableTools: {
         execute(args: {
             file_path: string;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableGetCell: {
         description: string;
@@ -41,7 +41,7 @@ export declare const tableTools: {
             file_path: string;
             cell_address: string;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableFilterRows: {
         description: string;
@@ -68,7 +68,7 @@ export declare const tableTools: {
             value: any;
             max_results: number;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableSearch: {
         description: string;
@@ -83,7 +83,7 @@ export declare const tableTools: {
             search_term: string;
             max_results: number;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableGetRange: {
         description: string;
@@ -96,7 +96,7 @@ export declare const tableTools: {
             file_path: string;
             range: string;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableSummarize: {
         description: string;
@@ -109,7 +109,7 @@ export declare const tableTools: {
             file_path: string;
             sheet_name?: string | undefined;
             columns?: string[] | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableGroupBy: {
         description: string;
@@ -132,7 +132,7 @@ export declare const tableTools: {
             agg_column: string;
             agg_type: "sum" | "count" | "avg" | "min" | "max";
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tablePivotSummary: {
         description: string;
@@ -157,7 +157,7 @@ export declare const tableTools: {
             value_field: string;
             agg: "sum" | "count" | "avg" | "min" | "max";
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableAppendRows: {
         description: string;
@@ -170,7 +170,7 @@ export declare const tableTools: {
             file_path: string;
             rows: (any[] | Record<string, any>)[];
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableUpdateCell: {
         description: string;
@@ -185,7 +185,7 @@ export declare const tableTools: {
             cell_address: string;
             value: any;
             sheet_name?: string | undefined;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
     tableCreateFile: {
         description: string;
@@ -198,6 +198,6 @@ export declare const tableTools: {
             file_path: string;
             sheet_name: string;
             data: any;
-        }, context: import("@opencode-ai/plugin").ToolContext): Promise<string>;
+        }, context: import("@opencode-ai/plugin").ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
     };
 };

package/dist/tools/table/tools.d.ts

@@ -9,7 +9,7 @@ export declare const tableGetSheetPreview: {
     execute(args: {
         file_path: string;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableListSheets: {
     description: string;
@@ -18,7 +18,7 @@ export declare const tableListSheets: {
     };
     execute(args: {
         file_path: string;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableGetHeaders: {
     description: string;
@@ -29,7 +29,7 @@ export declare const tableGetHeaders: {
     execute(args: {
         file_path: string;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableGetCell: {
     description: string;
@@ -42,7 +42,7 @@ export declare const tableGetCell: {
         file_path: string;
         cell_address: string;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableFilterRows: {
     description: string;
@@ -69,7 +69,7 @@ export declare const tableFilterRows: {
         value: any;
         max_results: number;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableSearch: {
     description: string;
@@ -84,7 +84,7 @@ export declare const tableSearch: {
         search_term: string;
         max_results: number;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableGetRange: {
     description: string;
@@ -97,7 +97,7 @@ export declare const tableGetRange: {
         file_path: string;
         range: string;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableSummarize: {
     description: string;
@@ -110,7 +110,7 @@ export declare const tableSummarize: {
         file_path: string;
         sheet_name?: string | undefined;
         columns?: string[] | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableGroupBy: {
     description: string;
@@ -133,7 +133,7 @@ export declare const tableGroupBy: {
         agg_column: string;
         agg_type: "sum" | "count" | "avg" | "min" | "max";
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tablePivotSummary: {
     description: string;
@@ -158,7 +158,7 @@ export declare const tablePivotSummary: {
         value_field: string;
         agg: "sum" | "count" | "avg" | "min" | "max";
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableAppendRows: {
     description: string;
@@ -171,7 +171,7 @@ export declare const tableAppendRows: {
         file_path: string;
         rows: (any[] | Record<string, any>)[];
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableUpdateCell: {
     description: string;
@@ -186,7 +186,7 @@ export declare const tableUpdateCell: {
         cell_address: string;
         value: any;
         sheet_name?: string | undefined;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };
 export declare const tableCreateFile: {
     description: string;
@@ -199,5 +199,5 @@ export declare const tableCreateFile: {
         file_path: string;
         sheet_name: string;
         data: any;
-    }, context: ToolContext): Promise<string>;
+    }, context: ToolContext): Promise<import("@opencode-ai/plugin").ToolResult>;
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yeyuan98/opencode-bioresearcher-plugin",
-  "version": "1.5.4-alpha.0",
+  "version": "1.6.0",
   "description": "OpenCode plugin that adds a bioresearcher agent",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -30,22 +30,21 @@
     "README.md"
   ],
   "dependencies": {
-    "@opencode-ai/plugin": "^1.2.6",
+    "@opencode-ai/plugin": "^1.14.0",
+    "effect": "4.0.0-beta.48",
     "fast-xml-parser": "^5.3.5",
     "mongodb": "^7.1.0",
     "mysql2": "^3.18.2",
     "xdg-basedir": "^5.1.0",
     "xlsx": "^0.18.5",
-    "zod": "^4.3.6"
+    "zod": "4.1.8"
   },
   "devDependencies": {
     "@types/bun": "^1.2.0",
     "@types/node": "^20.0.0",
     "typescript": "^5.9.3"
   },
-  "overrides": {
-    "@opencode-ai/plugin": {
-      "zod": "^4.3.6"
-    }
+  "engines": {
+    "opencode": ">=1.4.0"
   }
 }