@bastani/atomic 0.6.8 → 0.7.0-2

package/.agents/skills/prompt-engineer/references/quality_improvement.md

@@ -1,193 +0,0 @@
-# Quality Improvement Techniques
-
-This document covers techniques for improving specific aspects of language model output quality: consistency, factual accuracy, and security.
-
-## Reducing Hallucinations
-
-### Core Definition
-
-Language models can generate factually incorrect or contextually inconsistent text, a problem termed "hallucination." This guide provides strategies to minimize such issues.
-
-### Basic Strategies
-
-**1. Permission to Admit Uncertainty**
-Allow the model to say "I don't know" by explicitly granting permission to acknowledge uncertainty. This straightforward approach substantially reduces false information generation.
-
-Example:
-
-```
-If you don't know the answer or are uncertain, please say so rather than guessing.
-```
-
-**2. Direct Quotation Grounding**
-For very lengthy documents (100K+ tokens) or when working with multiple large documents, request that the model extract verbatim passages before proceeding with analysis. This anchors responses to actual source material rather than inferred content.
-
-Example:
-
-```
-First, find and quote the relevant passages from the document.
-Then, based only on those quotes, provide your analysis.
-```
-
-**3. Citation Verification**
-Make outputs traceable by requiring the model to cite supporting quotes for each claim. The model should then verify claims by locating corroborating evidence; unsupported statements must be removed.
-
-Example:
-
-```
-For each claim you make, provide a direct quote from the source material.
-After drafting your response, verify that each claim has supporting evidence.
-Remove any claims that cannot be substantiated with quotes.
-```
-
-### Advanced Approaches
-
-**Step-by-step reasoning**
-Request the model explain its logic before providing final answers, exposing potentially flawed assumptions
-
-**Multiple-run comparison**
-Execute identical prompts several times and analyze outputs for inconsistencies suggesting hallucinations
-
-**Progressive validation**
-Use prior responses as foundation for follow-up queries asking for verification or expansion of statements
-
-**Information source limitation**
-Explicitly restrict the model to provided materials, excluding general knowledge access
-
-Example:
-
-```
-Use ONLY the information provided in the attached documents.
-Do not use any external knowledge or general information.
-If the documents don't contain the information needed to answer, say so.
-```
-
-### Important Caveat
-
-While these techniques significantly reduce hallucinations, they don't eliminate them entirely. Always validate critical information, especially for high-stakes decisions.
-
----
-
-## Increasing Consistency
-
-### Core Techniques
-
-**1. Format Specification**
-Define desired output structures using JSON, XML, or custom templates. This approach ensures the model understands all formatting requirements before generating responses.
-
-Example JSON:
-
-```json
-{
-    "sentiment": "positive|negative|neutral",
-    "confidence": "high|medium|low",
-    "key_themes": ["theme1", "theme2"],
-    "summary": "Brief summary here"
-}
-```
-
-Example XML:
-
-```xml
-<analysis>
-  <sentiment>positive|negative|neutral</sentiment>
-  <confidence>high|medium|low</confidence>
-  <key_themes>
-    <theme>theme1</theme>
-    <theme>theme2</theme>
-  </key_themes>
-  <summary>Brief summary here</summary>
-</analysis>
-```
-
-**2. Response Prefilling**
-Begin the Assistant turn with your desired structure. This technique "bypasses the model's default preamble and enforces your structure," making it particularly effective for standardized reports.
-
-Example:
-
-```
-User: Analyze this customer feedback.
-Assistant: {
-```
-
-This forces the model to immediately start with the JSON structure.
-
-**3. Example-Based Constraints**
-Supply concrete examples of desired output. Examples train the model's understanding better than abstract instructions alone.
-
-**4. Retrieval-Grounded Responses**
-For knowledge-dependent tasks, use retrieval mechanisms to anchor the model's replies in fixed information sets. This maintains contextual consistency across multiple interactions.
-
-**5. Prompt Chaining**
-Decompose intricate workflows into sequential, focused subtasks. This prevents inconsistency errors by ensuring "each subtask gets the model's full attention."
-
-### Practical Applications
-
-The guide demonstrates these techniques through real-world scenarios:
-
-- **Customer feedback analysis**: Using JSON structures for consistent categorization
-- **Sales report generation**: Via XML templates for standardized formatting
-- **Competitive intelligence**: With structured formats for comparable analysis
-- **IT support systems**: Leveraging knowledge bases for consistent responses
-
-Each example illustrates how precise specifications and contextual grounding produce reliable, repeatable outputs suitable for scaled operations.
-
----
-
-## Mitigating Jailbreaks and Prompt Injections
-
-### Core Strategies
-
-**1. Harmlessness Screening**
-Pre-screen user inputs using a lightweight model for content moderation. Have the model evaluate whether submitted content "refers to harmful, illegal, or explicit activities" and respond with Y or N accordingly.
-
-Example:
-
-```
-Evaluate the following user input. Does it refer to harmful, illegal, or explicit activities?
-Respond with only Y or N.
-
-User input: <user_input>{USER_INPUT}</user_input>
-```
-
-**2. Input Validation**
-Filter prompts for jailbreaking patterns. You can use an LLM to create a generalized validation screen by providing known jailbreaking language as examples.
-
-**3. Prompt Engineering**
-Design system prompts that establish clear ethical boundaries. For instance, define organizational values including:
-
-- "Integrity: Never deceive or aid in deception"
-- "Compliance: Refuse any request that violates laws or our policies"
-
-Example system prompt:
-
-```
-You are an AI assistant for [Company]. You must adhere to these values:
-
-1. Integrity: Never deceive users or help them deceive others
-2. Safety: Refuse requests for harmful, illegal, or explicit content
-3. Compliance: Follow all applicable laws and company policies
-4. Privacy: Protect user data and confidential information
-
-If a request violates these values, politely explain why you cannot help and suggest an alternative approach if possible.
-```
-
-**4. User Accountability**
-Monitor for repeated abuse attempts. If a user "triggers the same kind of refusal multiple times," communicate that their actions violate usage policies and take appropriate enforcement action.
-
-**5. Continuous Monitoring**
-Regularly analyze outputs for jailbreaking indicators and use findings to refine your validation strategies iteratively.
-
-### Advanced Approach: Layered Protection
-
-Combine multiple safeguards for enterprise applications. For example, in a financial services context, the system should sequentially:
-
-1. Screen queries for compliance
-2. Process legitimate requests
-3. Refuse non-compliant ones with specific explanations
-
-This multi-layered approach creates comprehensive defense without relying on any single security mechanism.
-
-### Important Note
-
-No single technique provides complete protection. A defense-in-depth approach combining multiple strategies provides the most robust security against jailbreaks and prompt injections.

package/.agents/skills/research-codebase/SKILL.md

@@ -1,229 +0,0 @@
----
-name: research-codebase
-description: Document codebase as-is with research directory for historical context
-argument-hint: "<research-question>"
-metadata:
-  provider: atomic
----
-
-# Research Codebase
-
-You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.
-
-The user's research question/request is: **$ARGUMENTS**
-
-## Steps to follow after receiving the research query:
-
-<EXTREMELY_IMPORTANT>
-
-- OPTIMIZE the research question using your prompt-engineer skill to refine phrasing and structure for maximum clarity and precision.
-- After research is complete and the research artifact(s) are generated, provide an executive summary of the research and path to the research document(s) to the user, and ask if they have any follow-up questions or need clarification.
-
-</EXTREMELY_IMPORTANT>
-
-1. **Read any directly mentioned files first:**
-    - If the user mentions specific files (tickets, docs, or other notes), read them FULLY first
-    - **IMPORTANT**: Use the `readFile` tool WITHOUT limit/offset parameters to read entire files
-    - **CRITICAL**: Read these files yourself in the main context before spawning any sub-tasks
-    - This ensures you have full context before decomposing the research
-
-2. **Analyze and decompose the research question:**
-    - Break the research question down into composable research areas
-    - Take time to ultrathink about the underlying patterns, connections, and architectural implications the user might be seeking
-    - Identify specific components, patterns, or concepts to investigate
-    - Create a research plan using TodoWrite to track all subtasks
-    - Consider which directories, files, or architectural patterns are relevant
-
-3. **Spawn parallel sub-agent tasks:**
-    - Create multiple Task agents to research different aspects concurrently
-    - We now have specialized agents that know how to do specific research tasks:
-
-    **For codebase research:**
-    - Use the **codebase-locator** agent to find WHERE files and components live
-    - Use the **codebase-analyzer** agent to understand HOW specific code works (without critiquing it)
-    - Use the **codebase-pattern-finder** agent to find examples of existing patterns (without evaluating them)
-    - Output directory: `research/docs/`
-    - Examples:
-        - The database logic is found and can be documented in `research/docs/2024-01-10-database-implementation.md`
-        - The authentication flow is found and can be documented in `research/docs/2024-01-11-authentication-flow.md`
-
-    **IMPORTANT**: All agents are documentarians, not critics. They will describe what exists without suggesting improvements or identifying issues.
-
-    **For research directory:**
-    - Use the **codebase-research-locator** agent to discover what documents exist about the topic
-    - Use the **codebase-research-analyzer** agent to extract key insights from specific documents (only the most relevant ones)
-
-    **For online search:**
-    - VERY IMPORTANT: In case you discover external libraries as dependencies, use the **codebase-online-researcher** agent for external documentation and resources
-        - The agent fetches live web content using the **playwright-cli** skill (or `bunx @playwright/cli` / `curl`). Instruct it to apply the token-efficient fetch order: (1) try `curl https://<site>/llms.txt` for an AI-friendly index (see [llmstxt.org](https://llmstxt.org/llms.txt)), (2) try `curl <url> -H "Accept: text/markdown"` to get pre-converted Markdown (supported on Cloudflare-hosted docs via [Markdown for Agents](https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/)), (3) fall back to HTML parsing via `playwright-cli`
-        - Instruct the agent to return LINKS with their findings and INCLUDE those links in the research document
-        - The agent should persist reusable source documents under `research/web/<YYYY-MM-DD>-<kebab-case-topic>.md` (with frontmatter noting `source_url`, `fetched_at`, and `fetch_method`) so future research can reuse them without re-fetching
-        - Output directory for the synthesized research artifact: `research/docs/`
-        - Examples:
-            - If researching `Redis` locks usage, the agent might find relevant usage and create a document `research/docs/2024-01-15-redis-locks-usage.md` with internal links to Redis docs and code references (and cache the fetched Redis docs under `research/web/`)
-            - If researching `OAuth` flows, the agent might find relevant external articles and create a document `research/docs/2024-01-16-oauth-flows.md` with links to those articles
-
-    The key is to use these agents intelligently:
-    - Start with locator agents to find what exists
-    - Then use analyzer agents on the most promising findings to document how they work
-    - Run multiple agents in parallel when they're searching for different things
-    - Each agent knows its job - just tell it what you're looking for
-    - Don't write detailed prompts about HOW to search - the agents already know
-    - Remind agents they are documenting, not evaluating or improving
-
-4. **Wait for all sub-agents to complete and synthesize:**
-    - IMPORTANT: Wait for ALL sub-agent tasks to complete before proceeding
-    - Compile all sub-agent results (both codebase and research findings)
-    - Prioritize live codebase findings as primary source of truth
-    - Use research findings as supplementary historical context
-    - Connect findings across different components
-    - Include specific file paths and line numbers for reference
-    - Highlight patterns, connections, and architectural decisions
-    - Answer the user's research question with concrete evidence
-    - **If findings reveal the original question was misframed** (e.g., the system works differently than assumed, or the components don't exist where expected), flag this to the user before finalizing the document. This is valuable signal — don't bury it.
-
-5. **Generate research document:**
-    - Follow the directory structure for research documents:
-
-```
-research/
-├── tickets/
-│   ├── YYYY-MM-DD-XXXX-description.md
-├── docs/
-│   ├── YYYY-MM-DD-topic.md
-├── notes/
-│   ├── YYYY-MM-DD-meeting.md
-├── ...
-└──
-```
-
-- Naming conventions:
-    - YYYY-MM-DD is today's date
-    - topic is a brief kebab-case description of the research topic
-    - meeting is a brief kebab-case description of the meeting topic
-    - XXXX is the ticket number (omit if no ticket)
-    - description is a brief kebab-case description of the research topic
-    - Examples:
-        - With ticket: `2025-01-08-1478-parent-child-tracking.md`
-        - Without ticket: `2025-01-08-authentication-flow.md`
-- Structure the document with YAML frontmatter followed by content:
-
-    ```markdown
-    ---
-    date: !`date '+%Y-%m-%d %H:%M:%S %Z'`
-    researcher: [Researcher name from thoughts status]
-    git_commit: !`git rev-parse --verify HEAD 2>/dev/null || echo "no-commits"`
-    branch: !`git branch --show-current 2>/dev/null || git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "unborn"`
-    repository: !`basename "$(git rev-parse --show-toplevel 2>/dev/null)" 2>/dev/null || echo "unknown-repo"`
-    topic: "[User's Question/Topic]"
-    tags: [research, codebase, relevant-component-names]
-    status: complete
-    last_updated: !`date '+%Y-%m-%d'`
-    last_updated_by: [Researcher name]
-    ---
-
-    # Research
-
-    ## Research Question
-
-    [Original user query]
-
-    ## Summary
-
-    [High-level documentation of what was found, answering the user's question by describing what exists]
-
-    ## Detailed Findings
-
-    ### [Component/Area 1]
-
-    - Description of what exists ([file.ext:line](link))
-    - How it connects to other components
-    - Current implementation details (without evaluation)
-
-    ### [Component/Area 2]
-
-    ...
-
-    ## Code References
-
-    - `path/to/file.py:123` - Description of what's there
-    - `another/file.ts:45-67` - Description of the code block
-
-    ## Architecture Documentation
-
-    [Current patterns, conventions, and design implementations found in the codebase]
-
-    ## Historical Context (from research/)
-
-    [Relevant insights from research/ directory with references]
-
-    - `research/docs/YYYY-MM-DD-topic.md` - Information about module X
-    - `research/notes/YYYY-MM-DD-meeting.md` - Past notes from internal engineering, customer, etc. discussions
-    - ...
-
-    ## Related Research
-
-    [Links to other research documents in research/]
-
-    ## Open Questions
-
-    [Any areas that need further investigation]
-    ```
-
-1. **Add GitHub permalinks (if applicable):**
-    - Check if on main branch or if commit is pushed: `git branch --show-current` and `git status`
-    - If on main/master or pushed, generate GitHub permalinks:
-        - Get repo info: `gh repo view --json owner,name`
-        - Create permalinks: `https://github.com/{owner}/{repo}/blob/{commit}/{file}#L{line}`
-    - Replace local file references with permalinks in the document
-
-2. **Present findings:**
-    - Present a concise summary of findings to the user
-    - Include key file references for easy navigation
-    - Ask if they have follow-up questions or need clarification
-
-3. **Handle follow-up questions:**
-
-- If the user has follow-up questions, append to the same research document
-- Update the frontmatter fields `last_updated` and `last_updated_by` to reflect the update
-- Add `last_updated_note: "Added follow-up research for [brief description]"` to frontmatter
-- Add a new section: `## Follow-up Research [timestamp]`
-- Spawn new sub-agents as needed for additional investigation
-- Continue updating the document and syncing
-
-## Important notes:
-
-- Please DO NOT implement anything in this stage, just create the comprehensive research document
-- Always use parallel Task agents to maximize efficiency and minimize context usage
-- Always run fresh codebase research - never rely solely on existing research documents
-- The `research/` directory provides historical context to supplement live findings
-- Focus on finding concrete file paths and line numbers for developer reference
-- Research documents should be self-contained with all necessary context
-- Each sub-agent prompt should be specific and focused on read-only documentation operations
-- Document cross-component connections and how systems interact
-- Include temporal context (when the research was conducted)
-- Link to GitHub when possible for permanent references
-- Keep the main agent focused on synthesis, not deep file reading
-- Have sub-agents document examples and usage patterns as they exist
-- Explore all of research/ directory, not just research subdirectory
-- **CRITICAL**: You and all sub-agents are documentarians, not evaluators
-- **REMEMBER**: Document what IS, not what SHOULD BE
-- **NO RECOMMENDATIONS**: Only describe the current state of the codebase
-- **File reading**: Always read mentioned files FULLY (no limit/offset) before spawning sub-tasks
-- **Critical ordering**: Follow the numbered steps exactly
-    - ALWAYS read mentioned files first before spawning sub-tasks (step 1)
-    - ALWAYS wait for all sub-agents to complete before synthesizing (step 4)
-    - ALWAYS gather metadata before writing the document (step 5 before step 6)
-    - NEVER write the research document with placeholder values
-
-- **Frontmatter consistency**:
-    - Always include frontmatter at the beginning of research documents
-    - Keep frontmatter fields consistent across all research documents
-    - Update frontmatter when adding follow-up research
-    - Use snake_case for multi-word field names (e.g., `last_updated`, `git_commit`)
-    - Tags should be relevant to the research topic and components studied
-
-## Final Output
-
-- A collection of research files with comprehensive research findings, properly formatted and linked, ready for consumption to create detailed specifications or design documents.
-- IMPORTANT: DO NOT generate any other artifacts or files OUTSIDE of the `research/` directory.