cowork-os 0.3.21

package/resources/skills/session-logs.json

@@ -0,0 +1,10 @@
+{
+  "id": "session-logs",
+  "name": "Session-logs",
+  "description": "Search and analyze your own session logs (older/parent conversations) using jq.",
+  "icon": "📜",
+  "category": "Tools",
+  "prompt": "# session-logs\n\nSearch your complete conversation history stored in session JSONL files. Use this when a user references older/parent conversations or asks what was said before.\n\n## Trigger\n\nUse this skill when the user asks about prior chats, parent conversations, or historical context that isn’t in memory files.\n\n## Location\n\nSession logs live at: `~/.CoWork-OSS/agents/<agentId>/sessions/` (use the `agent=<id>` value from the system prompt Runtime line).\n\n- **`sessions.json`** - Index mapping session keys to session IDs\n- **`<session-id>.jsonl`** - Full conversation transcript per session\n\n## Structure\n\nEach `.jsonl` file contains messages with:\n\n- `type`: \"session\" (metadata) or \"message\"\n- `timestamp`: ISO timestamp\n- `message.role`: \"user\", \"assistant\", or \"toolResult\"\n- `message.content[]`: Text, thinking, or tool calls (filter `type==\"text\"` for human-readable content)\n- `message.usage.cost.total`: Cost per response\n\n## Common Queries\n\n### List all sessions by date and size\n\n```bash\nfor f in ~/.CoWork-OSS/agents/<agentId>/sessions/*.jsonl; do\n  date=$(head -1 \"$f\" | jq -r '.timestamp' | cut -dT -f1)\n  size=$(ls -lh \"$f\" | awk '{print $5}')\n  echo \"$date $size $(basename $f)\"\ndone | sort -r\n```\n\n### Find sessions from a specific day\n\n```bash\nfor f in ~/.CoWork-OSS/agents/<agentId>/sessions/*.jsonl; do\n  head -1 \"$f\" | jq -r '.timestamp' | grep -q \"2026-01-06\" && echo \"$f\"\ndone\n```\n\n### Extract user messages from a session\n\n```bash\njq -r 'select(.message.role == \"user\") | .message.content[]? | select(.type == \"text\") | .text' <session>.jsonl\n```\n\n### Search for keyword in assistant responses\n\n```bash\njq -r 'select(.message.role == \"assistant\") | .message.content[]? | select(.type == \"text\") | .text' <session>.jsonl | rg -i \"keyword\"\n```\n\n### Get total cost for a session\n\n```bash\njq -s '[.[] | .message.usage.cost.total // 0] | add' <session>.jsonl\n```\n\n### Daily cost summary\n\n```bash\nfor f in ~/.CoWork-OSS/agents/<agentId>/sessions/*.jsonl; do\n  date=$(head -1 \"$f\" | jq -r '.timestamp' | cut -dT -f1)\n  cost=$(jq -s '[.[] | .message.usage.cost.total // 0] | add' \"$f\")\n  echo \"$date $cost\"\ndone | awk '{a[$1]+=$2} END {for(d in a) print d, \"$\"a[d]}' | sort -r\n```\n\n### Count messages and tokens in a session\n\n```bash\njq -s '{\n  messages: length,\n  user: [.[] | select(.message.role == \"user\")] | length,\n  assistant: [.[] | select(.message.role == \"assistant\")] | length,\n  first: .[0].timestamp,\n  last: .[-1].timestamp\n}' <session>.jsonl\n```\n\n### Tool usage breakdown\n\n```bash\njq -r '.message.content[]? | select(.type == \"toolCall\") | .name' <session>.jsonl | sort | uniq -c | sort -rn\n```\n\n### Search across ALL sessions for a phrase\n\n```bash\nrg -l \"phrase\" ~/.CoWork-OSS/agents/<agentId>/sessions/*.jsonl\n```\n\n## Tips\n\n- Sessions are append-only JSONL (one JSON object per line)\n- Large sessions can be several MB - use `head`/`tail` for sampling\n- The `sessions.json` index maps chat providers (discord, whatsapp, etc.) to session IDs\n- Deleted sessions have `.deleted.<timestamp>` suffix\n\n## Fast text-only hint (low noise)\n\n```bash\njq -r 'select(.type==\"message\") | .message.content[]? | select(.type==\"text\") | .text' ~/.CoWork-OSS/agents/<agentId>/sessions/<id>.jsonl | rg 'keyword'\n```",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/sherpa-onnx-tts.json

@@ -0,0 +1,10 @@
+{
+  "id": "sherpa-onnx-tts",
+  "name": "Sherpa-onnx-tts",
+  "description": "Local text-to-speech via sherpa-onnx (offline, no cloud)",
+  "icon": "🗣️",
+  "category": "Tools",
+  "prompt": "# sherpa-onnx-tts\n\nLocal TTS using the sherpa-onnx offline CLI.\n\n## Install\n\n1. Download the runtime for your OS (extracts into `~/.CoWork-OSS/tools/sherpa-onnx-tts/runtime`)\n2. Download a voice model (extracts into `~/.CoWork-OSS/tools/sherpa-onnx-tts/models`)\n\nUpdate `~/.CoWork-OSS/CoWork-OSS.json`:\n\n```json5\n{\n  skills: {\n    entries: {\n      \"sherpa-onnx-tts\": {\n        env: {\n          SHERPA_ONNX_RUNTIME_DIR: \"~/.CoWork-OSS/tools/sherpa-onnx-tts/runtime\",\n          SHERPA_ONNX_MODEL_DIR: \"~/.CoWork-OSS/tools/sherpa-onnx-tts/models/vits-piper-en_US-lessac-high\",\n        },\n      },\n    },\n  },\n}\n```\n\nThe wrapper lives in this skill folder. Run it directly, or add the wrapper to PATH:\n\n```bash\nexport PATH=\"{baseDir}/bin:$PATH\"\n```\n\n## Usage\n\n```bash\n{baseDir}/bin/sherpa-onnx-tts -o ./tts.wav \"Hello from local TTS.\"\n```\n\nNotes:\n\n- Pick a different model from the sherpa-onnx `tts-models` release if you want another voice.\n- If the model dir has multiple `.onnx` files, set `SHERPA_ONNX_MODEL_FILE` or pass `--model-file`.\n- You can also pass `--tokens-file` or `--data-dir` to override the defaults.\n- Windows: run `node {baseDir}\\\\bin\\\\sherpa-onnx-tts -o tts.wav \"Hello from local TTS.\"`",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/skill-creator.json

@@ -0,0 +1,15 @@
+{
+  "id": "skill-creator",
+  "name": "Skill-creator",
+  "description": "Create or update AgentSkills for CoWork-OSS. Use when designing, structuring, or packaging skills. Supports JSON format with requirements, installation specs, and metadata.",
+  "icon": "✨",
+  "category": "Tools",
+  "metadata": {
+    "version": "2.0.0",
+    "author": "CoWork-OSS",
+    "tags": ["development", "skills", "authoring"]
+  },
+  "prompt": "# Skill Creator (CoWork-OSS)\n\n## CoWork-OSS JSON Skill Format\n\nCoWork-OSS uses JSON files for skills. Each skill is a `.json` file with the following structure:\n\n```json\n{\n  \"id\": \"my-skill\",\n  \"name\": \"My Skill\",\n  \"description\": \"What this skill does and when to use it\",\n  \"icon\": \"emoji-here\",\n  \"category\": \"Category Name\",\n  \"prompt\": \"The instructions/content injected into context\",\n  \"parameters\": [],\n  \"enabled\": true,\n  \"type\": \"task\",\n  \"requires\": {\n    \"bins\": [\"required-binary\"],\n    \"anyBins\": [\"npm\", \"pnpm\", \"yarn\"],\n    \"env\": [\"API_KEY\"],\n    \"os\": [\"darwin\"]\n  },\n  \"install\": [\n    {\n      \"id\": \"npm\",\n      \"kind\": \"npm\",\n      \"package\": \"package-name\",\n      \"label\": \"Install via npm\",\n      \"bins\": [\"binary-name\"]\n    }\n  ],\n  \"metadata\": {\n    \"version\": \"1.0.0\",\n    \"author\": \"Author Name\",\n    \"homepage\": \"https://example.com\",\n    \"tags\": [\"tag1\", \"tag2\"]\n  }\n}\n```\n\n### Required Fields\n- `id`: Unique identifier (lowercase, hyphens allowed)\n- `name`: Display name\n- `description`: What the skill does (used for triggering)\n- `icon`: Emoji or icon\n- `prompt`: The content/instructions\n\n### Optional Fields\n- `category`: For grouping in UI\n- `parameters`: Array of input parameters\n- `enabled`: Whether skill is active (default: true)\n- `type`: \"task\" (default) or \"guideline\"\n- `requires`: Requirements for eligibility\n- `install`: Installation specs for dependencies\n- `metadata`: Extended information\n\n### Requirements (`requires`)\n- `bins`: All these binaries must exist\n- `anyBins`: At least one must exist\n- `env`: All these env vars must be set\n- `os`: Must match current OS (darwin/linux/win32)\n\n### Skill Types\n- `task`: Executable skill selected for tasks\n- `guideline`: Always injected into system prompt when enabled\n\n### Skill Sources\nSkills are loaded from three locations (highest precedence wins):\n1. **Workspace** (`workspace/skills/`) - User's project skills\n2. **Managed** (`~/Library/Application Support/cowork-oss/skills/`) - From SkillHub\n3. **Bundled** (`resources/skills/`) - Pre-packaged with app\n\n---\n\n# Skill Creator\n\nThis skill provides guidance for creating effective skills.\n\n## About Skills\n\nSkills are modular, self-contained packages that extend Codex's capabilities by providing\nspecialized knowledge, workflows, and tools. Think of them as \"onboarding guides\" for specific\ndomains or tasks—they transform Codex from a general-purpose agent into a specialized agent\nequipped with procedural knowledge that no model can fully possess.\n\n### What Skills Provide\n\n1. Specialized workflows - Multi-step procedures for specific domains\n2. Tool integrations - Instructions for working with specific file formats or APIs\n3. Domain expertise - Company-specific knowledge, schemas, business logic\n4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks\n\n## Core Principles\n\n### Concise is Key\n\nThe context window is a public good. Skills share the context window with everything else Codex needs: system prompt, conversation history, other Skills' metadata, and the actual user request.\n\n**Default assumption: Codex is already very smart.** Only add context Codex doesn't already have. Challenge each piece of information: \"Does Codex really need this explanation?\" and \"Does this paragraph justify its token cost?\"\n\nPrefer concise examples over verbose explanations.\n\n### Set Appropriate Degrees of Freedom\n\nMatch the level of specificity to the task's fragility and variability:\n\n**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.\n\n**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.\n\n**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.\n\nThink of Codex as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).\n\n### Anatomy of a Skill\n\nEvery skill consists of a required SKILL.md file and optional bundled resources:\n\n```\nskill-name/\n├── SKILL.md (required)\n│   ├── YAML frontmatter metadata (required)\n│   │   ├── name: (required)\n│   │   └── description: (required)\n│   └── Markdown instructions (required)\n└── Bundled Resources (optional)\n    ├── scripts/          - Executable code (Python/Bash/etc.)\n    ├── references/       - Documentation intended to be loaded into context as needed\n    └── assets/           - Files used in output (templates, icons, fonts, etc.)\n```\n\n#### SKILL.md (required)\n\nEvery SKILL.md consists of:\n\n- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Codex reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.\n- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).\n\n#### Bundled Resources (optional)\n\n##### Scripts (`scripts/`)\n\nExecutable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.\n\n- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed\n- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks\n- **Benefits**: Token efficient, deterministic, may be executed without loading into context\n- **Note**: Scripts may still need to be read by Codex for patching or environment-specific adjustments\n\n##### References (`references/`)\n\nDocumentation and reference material intended to be loaded as needed into context to inform Codex's process and thinking.\n\n- **When to include**: For documentation that Codex should reference while working\n- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications\n- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides\n- **Benefits**: Keeps SKILL.md lean, loaded only when Codex determines it's needed\n- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md\n- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.\n\n##### Assets (`assets/`)\n\nFiles not intended to be loaded into context, but rather used within the output Codex produces.\n\n- **When to include**: When the skill needs files that will be used in the final output\n- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography\n- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified\n- **Benefits**: Separates output resources from documentation, enables Codex to use files without loading them into context\n\n#### What to Not Include in a Skill\n\nA skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:\n\n- README.md\n- INSTALLATION_GUIDE.md\n- QUICK_REFERENCE.md\n- CHANGELOG.md\n- etc.\n\nThe skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxiliary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.\n\n### Progressive Disclosure Design Principle\n\nSkills use a three-level loading system to manage context efficiently:\n\n1. **Metadata (name + description)** - Always in context (~100 words)\n2. **SKILL.md body** - When skill triggers (<5k words)\n3. **Bundled resources** - As needed by Codex (Unlimited because scripts can be executed without reading into context window)\n\n#### Progressive Disclosure Patterns\n\nKeep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.\n\n**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.\n\n**Pattern 1: High-level guide with references**\n\n```markdown\n# PDF Processing\n\n## Quick start\n\nExtract text with pdfplumber:\n[code example]\n\n## Advanced features\n\n- **Form filling**: See [FORMS.md](FORMS.md) for complete guide\n- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods\n- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns\n```\n\nCodex loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.\n\n**Pattern 2: Domain-specific organization**\n\nFor Skills with multiple domains, organize content by domain to avoid loading irrelevant context:\n\n```\nbigquery-skill/\n├── SKILL.md (overview and navigation)\n└── reference/\n    ├── finance.md (revenue, billing metrics)\n    ├── sales.md (opportunities, pipeline)\n    ├── product.md (API usage, features)\n    └── marketing.md (campaigns, attribution)\n```\n\nWhen a user asks about sales metrics, Codex only reads sales.md.\n\nSimilarly, for skills supporting multiple frameworks or variants, organize by variant:\n\n```\ncloud-deploy/\n├── SKILL.md (workflow + provider selection)\n└── references/\n    ├── aws.md (AWS deployment patterns)\n    ├── gcp.md (GCP deployment patterns)\n    └── azure.md (Azure deployment patterns)\n```\n\nWhen the user chooses AWS, Codex only reads aws.md.\n\n**Pattern 3: Conditional details**\n\nShow basic content, link to advanced content:\n\n```markdown\n# DOCX Processing\n\n## Creating documents\n\nUse docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).\n\n## Editing documents\n\nFor simple edits, modify the XML directly.\n\n**For tracked changes**: See [REDLINING.md](REDLINING.md)\n**For OOXML details**: See [OOXML.md](OOXML.md)\n```\n\nCodex reads REDLINING.md or OOXML.md only when the user needs those features.\n\n**Important guidelines:**\n\n- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.\n- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so Codex can see the full scope when previewing.\n\n## Skill Creation Process\n\nSkill creation involves these steps:\n\n1. Understand the skill with concrete examples\n2. Plan reusable skill contents (scripts, references, assets)\n3. Initialize the skill (run init_skill.py)\n4. Edit the skill (implement resources and write SKILL.md)\n5. Package the skill (run package_skill.py)\n6. Iterate based on real usage\n\nFollow these steps in order, skipping only if there is a clear reason why they are not applicable.\n\n### Skill Naming\n\n- Use lowercase letters, digits, and hyphens only; normalize user-provided titles to hyphen-case (e.g., \"Plan Mode\" -> `plan-mode`).\n- When generating names, generate a name under 64 characters (letters, digits, hyphens).\n- Prefer short, verb-led phrases that describe the action.\n- Namespace by tool when it improves clarity or triggering (e.g., `gh-address-comments`, `linear-address-issue`).\n- Name the skill folder exactly after the skill name.\n\n### Step 1: Understanding the Skill with Concrete Examples\n\nSkip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.\n\nTo create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.\n\nFor example, when building an image-editor skill, relevant questions include:\n\n- \"What functionality should the image-editor skill support? Editing, rotating, anything else?\"\n- \"Can you give some examples of how this skill would be used?\"\n- \"I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?\"\n- \"What would a user say that should trigger this skill?\"\n\nTo avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.\n\nConclude this step when there is a clear sense of the functionality the skill should support.\n\n### Step 2: Planning the Reusable Skill Contents\n\nTo turn concrete examples into an effective skill, analyze each example by:\n\n1. Considering how to execute on the example from scratch\n2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly\n\nExample: When building a `pdf-editor` skill to handle queries like \"Help me rotate this PDF,\" the analysis shows:\n\n1. Rotating a PDF requires re-writing the same code each time\n2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill\n\nExample: When designing a `frontend-webapp-builder` skill for queries like \"Build me a todo app\" or \"Build me a dashboard to track my steps,\" the analysis shows:\n\n1. Writing a frontend webapp requires the same boilerplate HTML/React each time\n2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill\n\nExample: When building a `big-query` skill to handle queries like \"How many users have logged in today?\" the analysis shows:\n\n1. Querying BigQuery requires re-discovering the table schemas and relationships each time\n2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill\n\nTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.\n\n### Step 3: Initializing the Skill\n\nAt this point, it is time to actually create the skill.\n\nSkip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.\n\nWhen creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.\n\nUsage:\n\n```bash\nscripts/init_skill.py <skill-name> --path <output-directory> [--resources scripts,references,assets] [--examples]\n```\n\nExamples:\n\n```bash\nscripts/init_skill.py my-skill --path skills/public\nscripts/init_skill.py my-skill --path skills/public --resources scripts,references\nscripts/init_skill.py my-skill --path skills/public --resources scripts --examples\n```\n\nThe script:\n\n- Creates the skill directory at the specified path\n- Generates a SKILL.md template with proper frontmatter and TODO placeholders\n- Optionally creates resource directories based on `--resources`\n- Optionally adds example files when `--examples` is set\n\nAfter initialization, customize the SKILL.md and add resources as needed. If you used `--examples`, replace or delete placeholder files.\n\n### Step 4: Edit the Skill\n\nWhen editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Codex to use. Include information that would be beneficial and non-obvious to Codex. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Codex instance execute these tasks more effectively.\n\n#### Learn Proven Design Patterns\n\nConsult these helpful guides based on your skill's needs:\n\n- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic\n- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns\n\nThese files contain established best practices for effective skill design.\n\n#### Start with Reusable Skill Contents\n\nTo begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.\n\nAdded scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.\n\nIf you used `--examples`, delete any placeholder files that are not needed for the skill. Only create resource directories that are actually required.\n\n#### Update SKILL.md\n\n**Writing Guidelines:** Always use imperative/infinitive form.\n\n##### Frontmatter\n\nWrite the YAML frontmatter with `name` and `description`:\n\n- `name`: The skill name\n- `description`: This is the primary triggering mechanism for your skill, and helps Codex understand when to use the skill.\n  - Include both what the Skill does and specific triggers/contexts for when to use it.\n  - Include all \"when to use\" information here - Not in the body. The body is only loaded after triggering, so \"When to Use This Skill\" sections in the body are not helpful to Codex.\n  - Example description for a `docx` skill: \"Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when Codex needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks\"\n\nDo not include any other fields in YAML frontmatter.\n\n##### Body\n\nWrite instructions for using the skill and its bundled resources.\n\n### Step 5: Packaging a Skill\n\nOnce development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:\n\n```bash\nscripts/package_skill.py <path/to/skill-folder>\n```\n\nOptional output directory specification:\n\n```bash\nscripts/package_skill.py <path/to/skill-folder> ./dist\n```\n\nThe packaging script will:\n\n1. **Validate** the skill automatically, checking:\n   - YAML frontmatter format and required fields\n   - Skill naming conventions and directory structure\n   - Description completeness and quality\n   - File organization and resource references\n\n2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.\n\nIf validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.\n\n### Step 6: Iterate\n\nAfter testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.\n\n**Iteration workflow:**\n\n1. Use the skill on real tasks\n2. Notice struggles or inefficiencies\n3. Identify how SKILL.md or bundled resources should be updated\n4. Implement changes and test again",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/skill-hub.json

@@ -0,0 +1,29 @@
+{
+  "id": "skill-hub",
+  "name": "skill-hub",
+  "description": "Use the skill-hub CLI to search, install, update, and publish agent skills from skill-hub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed skill-hub CLI.",
+  "icon": "🔧",
+  "category": "Tools",
+  "prompt": "# skill-hub CLI\n\nInstall\n\n```bash\nnpm i -g skill-hub\n```\n\nAuth (publish)\n\n```bash\nskill-hub login\nskill-hub whoami\n```\n\nSearch\n\n```bash\nskill-hub search \"postgres backups\"\n```\n\nInstall\n\n```bash\nskill-hub install my-skill\nskill-hub install my-skill --version 1.2.3\n```\n\nUpdate (hash-based match + upgrade)\n\n```bash\nskill-hub update my-skill\nskill-hub update my-skill --version 1.2.3\nskill-hub update --all\nskill-hub update my-skill --force\nskill-hub update --all --no-input --force\n```\n\nList\n\n```bash\nskill-hub list\n```\n\nPublish\n\n```bash\nskill-hub publish ./my-skill --slug my-skill --name \"My Skill\" --version 1.2.0 --changelog \"Fixes + docs\"\n```\n\nNotes\n\n- Default registry: https://skill-hub.com (override with skill-hub_REGISTRY or --registry)\n- Default workdir: cwd (falls back to CoWork-OSS workspace); install dir: ./skills (override with --workdir / --dir / skill-hub_WORKDIR)\n- Update command hashes local files, resolves matching version, and upgrades to latest unless --version is set",
+  "parameters": [],
+  "enabled": true,
+  "requires": {
+    "bins": ["skill-hub"],
+    "anyBins": ["npm", "pnpm", "yarn"]
+  },
+  "install": [
+    {
+      "id": "npm",
+      "kind": "npm",
+      "package": "skill-hub",
+      "label": "Install via npm (npm i -g skill-hub)",
+      "bins": ["skill-hub"]
+    }
+  ],
+  "metadata": {
+    "version": "1.0.0",
+    "author": "CoWork-OSS",
+    "homepage": "https://skill-hub.com",
+    "tags": ["cli", "registry", "skills"]
+  }
+}

package/resources/skills/slack.json

@@ -0,0 +1,10 @@
+{
+  "id": "slack",
+  "name": "Slack",
+  "description": "Use when you need to control Slack from CoWork-OSS via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.",
+  "icon": "💬",
+  "category": "Tools",
+  "prompt": "# Slack Actions\n\n## Overview\n\nUse `slack` to react, manage pins, send/edit/delete messages, and fetch member info. The tool uses the bot token configured for CoWork-OSS.\n\n## Inputs to collect\n\n- `channelId` and `messageId` (Slack message timestamp, e.g. `1712023032.1234`).\n- For reactions, an `emoji` (Unicode or `:name:`).\n- For message sends, a `to` target (`channel:<id>` or `user:<id>`) and `content`.\n\nMessage context lines include `slack message id` and `channel` fields you can reuse directly.\n\n## Actions\n\n### Action groups\n\n| Action group | Default | Notes                  |\n| ------------ | ------- | ---------------------- |\n| reactions    | enabled | React + list reactions |\n| messages     | enabled | Read/send/edit/delete  |\n| pins         | enabled | Pin/unpin/list         |\n| memberInfo   | enabled | Member info            |\n| emojiList    | enabled | Custom emoji list      |\n\n### React to a message\n\n```json\n{\n  \"action\": \"react\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\",\n  \"emoji\": \"✅\"\n}\n```\n\n### List reactions\n\n```json\n{\n  \"action\": \"reactions\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\"\n}\n```\n\n### Send a message\n\n```json\n{\n  \"action\": \"sendMessage\",\n  \"to\": \"channel:C123\",\n  \"content\": \"Hello from CoWork-OSS\"\n}\n```\n\n### Edit a message\n\n```json\n{\n  \"action\": \"editMessage\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\",\n  \"content\": \"Updated text\"\n}\n```\n\n### Delete a message\n\n```json\n{\n  \"action\": \"deleteMessage\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\"\n}\n```\n\n### Read recent messages\n\n```json\n{\n  \"action\": \"readMessages\",\n  \"channelId\": \"C123\",\n  \"limit\": 20\n}\n```\n\n### Pin a message\n\n```json\n{\n  \"action\": \"pinMessage\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\"\n}\n```\n\n### Unpin a message\n\n```json\n{\n  \"action\": \"unpinMessage\",\n  \"channelId\": \"C123\",\n  \"messageId\": \"1712023032.1234\"\n}\n```\n\n### List pinned items\n\n```json\n{\n  \"action\": \"listPins\",\n  \"channelId\": \"C123\"\n}\n```\n\n### Member info\n\n```json\n{\n  \"action\": \"memberInfo\",\n  \"userId\": \"U123\"\n}\n```\n\n### Emoji list\n\n```json\n{\n  \"action\": \"emojiList\"\n}\n```\n\n## Ideas to try\n\n- React with ✅ to mark completed tasks.\n- Pin key decisions or weekly status updates.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/songsee.json

@@ -0,0 +1,10 @@
+{
+  "id": "songsee",
+  "name": "Songsee",
+  "description": "Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.",
+  "icon": "🌊",
+  "category": "Tools",
+  "prompt": "# songsee\n\nGenerate spectrograms + feature panels from audio.\n\nQuick start\n\n- Spectrogram: `songsee track.mp3`\n- Multi-panel: `songsee track.mp3 --viz spectrogram,mel,chroma,hpss,selfsim,loudness,tempogram,mfcc,flux`\n- Time slice: `songsee track.mp3 --start 12.5 --duration 8 -o slice.jpg`\n- Stdin: `cat track.mp3 | songsee - --format png -o out.png`\n\nCommon flags\n\n- `--viz` list (repeatable or comma-separated)\n- `--style` palette (classic, magma, inferno, viridis, gray)\n- `--width` / `--height` output size\n- `--window` / `--hop` FFT settings\n- `--min-freq` / `--max-freq` frequency range\n- `--start` / `--duration` time slice\n- `--format` jpg|png\n\nNotes\n\n- WAV/MP3 decode native; other formats use ffmpeg if available.\n- Multiple `--viz` renders a grid.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/sonoscli.json

@@ -0,0 +1,10 @@
+{
+  "id": "sonoscli",
+  "name": "Sonoscli",
+  "description": "Control Sonos speakers (discover/status/play/volume/group).",
+  "icon": "🔊",
+  "category": "Tools",
+  "prompt": "# Sonos CLI\n\nUse `sonos` to control Sonos speakers on the local network.\n\nQuick start\n\n- `sonos discover`\n- `sonos status --name \"Kitchen\"`\n- `sonos play|pause|stop --name \"Kitchen\"`\n- `sonos volume set 15 --name \"Kitchen\"`\n\nCommon tasks\n\n- Grouping: `sonos group status|join|unjoin|party|solo`\n- Favorites: `sonos favorites list|open`\n- Queue: `sonos queue list|play|clear`\n- Spotify search (via SMAPI): `sonos smapi search --service \"Spotify\" --category tracks \"query\"`\n\nNotes\n\n- If SSDP fails, specify `--ip <speaker-ip>`.\n- Spotify Web API search is optional and requires `SPOTIFY_CLIENT_ID/SECRET`.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/spotify-player.json

@@ -0,0 +1,10 @@
+{
+  "id": "spotify-player",
+  "name": "Spotify-player",
+  "description": "Terminal Spotify playback/search via spogo (preferred) or spotify_player.",
+  "icon": "🎵",
+  "category": "Tools",
+  "prompt": "# spogo / spotify_player\n\nUse `spogo` **(preferred)** for Spotify playback/search. Fall back to `spotify_player` if needed.\n\nRequirements\n\n- Spotify Premium account.\n- Either `spogo` or `spotify_player` installed.\n\nspogo setup\n\n- Import cookies: `spogo auth import --browser chrome`\n\nCommon CLI commands\n\n- Search: `spogo search track \"query\"`\n- Playback: `spogo play|pause|next|prev`\n- Devices: `spogo device list`, `spogo device set \"<name|id>\"`\n- Status: `spogo status`\n\nspotify_player commands (fallback)\n\n- Search: `spotify_player search \"query\"`\n- Playback: `spotify_player playback play|pause|next|previous`\n- Connect device: `spotify_player connect`\n- Like track: `spotify_player like`\n\nNotes\n\n- Config folder: `~/.config/spotify-player` (e.g., `app.toml`).\n- For Spotify Connect integration, set a user `client_id` in config.\n- TUI shortcuts are available via `?` in the app.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/startup-cfo.json

@@ -0,0 +1,55 @@
+{
+  "id": "startup-cfo",
+  "name": "Startup CFO",
+  "description": "AI CFO for bootstrapped startups. Provides financial frameworks for cash management, runway calculations, unit economics (LTV:CAC), capital allocation, hiring ROI, burn rate analysis, working capital optimization, and forecasting.",
+  "icon": "💰",
+  "category": "Finance",
+  "prompt": "# CFO Analysis Request\n\n**Area:** {{topic}}\n**Question:** {{question}}\n\n**Current Metrics (if provided):**\n- ARR: {{arr}}\n- Monthly Churn: {{monthlyChurn}}\n- CAC: {{cac}}\n- LTV: {{ltv}}\n\nUsing the bootstrapped financial management framework below, analyze this question and provide specific, actionable guidance. If metrics are provided, calculate relevant ratios and compare against benchmarks.\n\n---\n\n# Bootstrapped Financial Management Reference\n\n## Core Mental Models\n\n**Profit is a constraint, not a goal.** Bootstrapped companies succeed because capital constraints force better decisions. Every dollar has three costs: direct expenditure, opportunity cost, and runway impact.\n\n**Unit economics are survival requirements:**\n- LTV >= 3x CAC (best-in-class: 7-8x)\n- CAC payback < 12 months (high performers: 5-7 months)\n- Violating these creates a death spiral bootstrapped companies cannot survive\n\n**Revenue per employee is your efficiency scorecard:**\n- $110-150K at $1-5M ARR\n- $200-250K at $10-50M ARR\n- $400K+ at maturity\n- Bootstrapped companies run 40-70% higher than VC-backed peers\n\n## Cash Management Rules\n\n**Runway targets:**\n- Minimum: 24-36 months\n- Danger zone: <12 months (you've lost control)\n- Never fundraise your way out of a cash crisis\n\n**Reserve structure:**\n| Reserve | Amount | Purpose |\n|---------|--------|--------|\n| Operating | 3-6 months fixed costs | Payroll, rent, essential software |\n| Contingency | 1-2 months expenses | Emergencies |\n| Growth | Excess | Opportunistic investments |\n\n**Burn multiple** = Net Burn / Net New ARR\n- <1x: Excellent\n- 1-1.5x: Good\n- >2x: Concerning\n- Bootstrapped target: Zero or negative (profitable growth)\n\n## Capital Allocation Framework\n\n**Every investment question:** What is the payback period? Target <12 months.\n\n**Rule of 40:** Revenue Growth % + EBITDA Margin % >= 40%\n- High growth path: 40% + 0%\n- Balanced path: 20% + 20%\n- Profit path: 10% + 30%\n\n**Hiring decisions:**\n1. Will this hire directly contribute to revenue?\n2. What's the time-to-productivity? (Factor into ROI)\n3. What else could this salary fund?\n4. Does this make existing team more productive?\n\n**Never grow a department >50% at once** - productivity drops to zero during training.\n\n## Working Capital Optimization\n\n**Cash Conversion Cycle (CCC):** DIO + DSO - DPO\n- SaaS target: Negative (-30 to -90 days)\n- Every 10-day reduction frees significant working capital\n\n**AR discipline:** Target 30-45 days DSO\n**AP strategy:** Pay on due date, not early, unless discount > cost of capital\n**Annual prepay:** Offer 15-20% discount for 30% lower churn, 27-40% higher LTV\n\n## Key Metrics & Benchmarks\n\n### LTV:CAC Ratio\n| Ratio | Interpretation |\n|-------|----------------|\n| <1:1 | Losing money on every customer |\n| 1-2:1 | Unsustainable, need to improve |\n| 3:1 | Healthy minimum threshold |\n| 5:1+ | Excellent, may be underinvesting in growth |\n| 7-8:1 | Best-in-class |\n\n### Churn Rates by Segment\n| Segment | Monthly Churn | Annual Churn |\n|---------|---------------|---------------|\n| SMB | 3-5% | 30-50% |\n| Mid-Market | 1-2% | 10-20% |\n| Enterprise | 0.5-1% | 5-10% |\n| Best-in-class | <1% monthly | <10% annual |\n\n### Net Revenue Retention (NRR)\n| NRR | Interpretation |\n|-----|----------------|\n| <90% | Leaky bucket, growth unsustainable |\n| 90-100% | Acceptable, but limited expansion |\n| 100-110% | Good, expansion offsetting churn |\n| 110-130% | Excellent |\n| >130% | World-class |\n\n### Revenue per Employee\n| ARR Stage | Target RPE |\n|-----------|------------|\n| $1-5M | $110-150K |\n| $5-10M | $150-200K |\n| $10-50M | $200-250K |\n| $50M+ | $300-400K+ |\n\n### Spending Benchmarks ($3-5M ARR)\n- Sales: 10-15% of ARR\n- Marketing: 8-10% of ARR\n- R&D: 25-30% of ARR\n- Customer Success: 8-12% of ARR\n- G&A: ~14% of ARR\n- **Total: ~95%** (vs. 107% for VC-backed)\n\n## Formulas\n\n**LTV** = (ARPU x Gross Margin) / Monthly Churn Rate\n**CAC** = (Sales + Marketing Spend) / New Customers Acquired\n**CAC Payback** = CAC / (Monthly ARPU x Gross Margin)\n**NRR** = (Starting MRR + Expansion - Churn - Contraction) / Starting MRR\n**Magic Number** = (QoQ ARR Growth) / (Prior Quarter S&M Spend)\n**CCC** = DIO + DSO - DPO",
+  "parameters": [
+    {
+      "name": "topic",
+      "type": "select",
+      "description": "Area of focus",
+      "required": true,
+      "options": [
+        "Cash Management & Runway",
+        "Unit Economics (LTV/CAC)",
+        "Hiring & Capital Allocation",
+        "Forecasting & Planning",
+        "Working Capital",
+        "General Financial Strategy"
+      ]
+    },
+    {
+      "name": "question",
+      "type": "string",
+      "description": "Your specific question",
+      "required": true
+    },
+    {
+      "name": "arr",
+      "type": "string",
+      "description": "Annual Recurring Revenue (e.g., $2M)",
+      "required": false
+    },
+    {
+      "name": "monthlyChurn",
+      "type": "string",
+      "description": "Monthly churn rate (e.g., 2.5%)",
+      "required": false
+    },
+    {
+      "name": "cac",
+      "type": "string",
+      "description": "Customer Acquisition Cost (e.g., $500)",
+      "required": false
+    },
+    {
+      "name": "ltv",
+      "type": "string",
+      "description": "Lifetime Value (e.g., $3000)",
+      "required": false
+    }
+  ],
+  "enabled": true
+}

package/resources/skills/summarize-folder.json

@@ -0,0 +1,18 @@
+{
+  "id": "summarize-folder",
+  "name": "Summarize Folder",
+  "description": "Create a summary of all files in a folder",
+  "icon": "📋",
+  "category": "Documentation",
+  "prompt": "Please analyze all the files in {{path}} and create a comprehensive summary.\n\nInclude:\n- Overview of the folder structure\n- Purpose of each file/module\n- Key functions and classes\n- Dependencies and relationships between files\n- Any notable patterns or conventions\n\nFormat the output as a clear, well-organized document.",
+  "parameters": [
+    {
+      "name": "path",
+      "type": "string",
+      "description": "Folder path to summarize",
+      "required": true,
+      "default": "."
+    }
+  ],
+  "enabled": true
+}

package/resources/skills/summarize.json

@@ -0,0 +1,10 @@
+{
+  "id": "summarize",
+  "name": "Summarize",
+  "description": "Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).",
+  "icon": "🧾",
+  "category": "Tools",
+  "prompt": "# Summarize\n\nFast CLI to summarize URLs, local files, and YouTube links.\n\n## When to use (trigger phrases)\n\nUse this skill immediately when the user asks any of:\n\n- “use summarize.sh”\n- “what’s this link/video about?”\n- “summarize this URL/article”\n- “transcribe this YouTube/video” (best-effort transcript extraction; no `yt-dlp` needed)\n\n## Quick start\n\n```bash\nsummarize \"https://example.com\" --model google/gemini-3-flash-preview\nsummarize \"/path/to/file.pdf\" --model google/gemini-3-flash-preview\nsummarize \"https://youtu.be/dQw4w9WgXcQ\" --youtube auto\n```\n\n## YouTube: summary vs transcript\n\nBest-effort transcript (URLs only):\n\n```bash\nsummarize \"https://youtu.be/dQw4w9WgXcQ\" --youtube auto --extract-only\n```\n\nIf the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand.\n\n## Model + keys\n\nSet the API key for your chosen provider:\n\n- OpenAI: `OPENAI_API_KEY`\n- Anthropic: `ANTHROPIC_API_KEY`\n- xAI: `XAI_API_KEY`\n- Google: `GEMINI_API_KEY` (aliases: `GOOGLE_GENERATIVE_AI_API_KEY`, `GOOGLE_API_KEY`)\n\nDefault model is `google/gemini-3-flash-preview` if none is set.\n\n## Useful flags\n\n- `--length short|medium|long|xl|xxl|<chars>`\n- `--max-output-tokens <count>`\n- `--extract-only` (URLs only)\n- `--json` (machine readable)\n- `--firecrawl auto|off|always` (fallback extraction)\n- `--youtube auto` (Apify fallback if `APIFY_API_TOKEN` set)\n\n## Config\n\nOptional config file: `~/.summarize/config.json`\n\n```json\n{ \"model\": \"openai/gpt-5.2\" }\n```\n\nOptional services:\n\n- `FIRECRAWL_API_KEY` for blocked sites\n- `APIFY_API_TOKEN` for YouTube fallback",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/things-mac.json

@@ -0,0 +1,10 @@
+{
+  "id": "things-mac",
+  "name": "Things-mac",
+  "description": "Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks CoWork-OSS to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.",
+  "icon": "✅",
+  "category": "Tools",
+  "prompt": "# Things 3 CLI\n\nUse `things` to read your local Things database (inbox/today/search/projects/areas/tags) and to add/update todos via the Things URL scheme.\n\nSetup\n\n- Install (recommended, Apple Silicon): `GOBIN=/opt/homebrew/bin go install github.com/ossianhempel/things3-cli/cmd/things@latest`\n- If DB reads fail: grant **Full Disk Access** to the calling app (Terminal for manual runs; `CoWork-OSS.app` for gateway runs).\n- Optional: set `THINGSDB` (or pass `--db`) to point at your `ThingsData-*` folder.\n- Optional: set `THINGS_AUTH_TOKEN` to avoid passing `--auth-token` for update ops.\n\nRead-only (DB)\n\n- `things inbox --limit 50`\n- `things today`\n- `things upcoming`\n- `things search \"query\"`\n- `things projects` / `things areas` / `things tags`\n\nWrite (URL scheme)\n\n- Prefer safe preview: `things --dry-run add \"Title\"`\n- Add: `things add \"Title\" --notes \"...\" --when today --deadline 2026-01-02`\n- Bring Things to front: `things --foreground add \"Title\"`\n\nExamples: add a todo\n\n- Basic: `things add \"Buy milk\"`\n- With notes: `things add \"Buy milk\" --notes \"2% + bananas\"`\n- Into a project/area: `things add \"Book flights\" --list \"Travel\"`\n- Into a project heading: `things add \"Pack charger\" --list \"Travel\" --heading \"Before\"`\n- With tags: `things add \"Call dentist\" --tags \"health,phone\"`\n- Checklist: `things add \"Trip prep\" --checklist-item \"Passport\" --checklist-item \"Tickets\"`\n- From STDIN (multi-line => title + notes):\n  - `cat <<'EOF' | things add -`\n  - `Title line`\n  - `Notes line 1`\n  - `Notes line 2`\n  - `EOF`\n\nExamples: modify a todo (needs auth token)\n\n- First: get the ID (UUID column): `things search \"milk\" --limit 5`\n- Auth: set `THINGS_AUTH_TOKEN` or pass `--auth-token <TOKEN>`\n- Title: `things update --id <UUID> --auth-token <TOKEN> \"New title\"`\n- Notes replace: `things update --id <UUID> --auth-token <TOKEN> --notes \"New notes\"`\n- Notes append/prepend: `things update --id <UUID> --auth-token <TOKEN> --append-notes \"...\"` / `--prepend-notes \"...\"`\n- Move lists: `things update --id <UUID> --auth-token <TOKEN> --list \"Travel\" --heading \"Before\"`\n- Tags replace/add: `things update --id <UUID> --auth-token <TOKEN> --tags \"a,b\"` / `things update --id <UUID> --auth-token <TOKEN> --add-tags \"a,b\"`\n- Complete/cancel (soft-delete-ish): `things update --id <UUID> --auth-token <TOKEN> --completed` / `--canceled`\n- Safe preview: `things --dry-run update --id <UUID> --auth-token <TOKEN> --completed`\n\nDelete a todo?\n\n- Not supported by `things3-cli` right now (no “delete/move-to-trash” write command; `things trash` is read-only listing).\n- Options: use Things UI to delete/trash, or mark as `--completed` / `--canceled` via `things update`.\n\nNotes\n\n- macOS-only.\n- `--dry-run` prints the URL and does not open Things.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/tmux.json

@@ -0,0 +1,10 @@
+{
+  "id": "tmux",
+  "name": "Tmux",
+  "description": "Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.",
+  "icon": "🧵",
+  "category": "Tools",
+  "prompt": "# tmux Skill (CoWork-OSS)\n\nUse tmux only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks.\n\n## Quickstart (isolated socket, exec tool)\n\n```bash\nSOCKET_DIR=\"${CoWork-OSS_TMUX_SOCKET_DIR:-${CoWork-OSSBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/CoWork-OSS-tmux-sockets}}\"\nmkdir -p \"$SOCKET_DIR\"\nSOCKET=\"$SOCKET_DIR/CoWork-OSS.sock\"\nSESSION=CoWork-OSS-python\n\ntmux -S \"$SOCKET\" new -d -s \"$SESSION\" -n shell\ntmux -S \"$SOCKET\" send-keys -t \"$SESSION\":0.0 -- 'PYTHON_BASIC_REPL=1 python3 -q' Enter\ntmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200\n```\n\nAfter starting a session, always print monitor commands:\n\n```\nTo monitor:\n  tmux -S \"$SOCKET\" attach -t \"$SESSION\"\n  tmux -S \"$SOCKET\" capture-pane -p -J -t \"$SESSION\":0.0 -S -200\n```\n\n## Socket convention\n\n- Use `CoWork-OSS_TMUX_SOCKET_DIR` (legacy `CoWork-OSSBOT_TMUX_SOCKET_DIR` also supported).\n- Default socket path: `\"$CoWork-OSS_TMUX_SOCKET_DIR/CoWork-OSS.sock\"`.\n\n## Targeting panes and naming\n\n- Target format: `session:window.pane` (defaults to `:0.0`).\n- Keep names short; avoid spaces.\n- Inspect: `tmux -S \"$SOCKET\" list-sessions`, `tmux -S \"$SOCKET\" list-panes -a`.\n\n## Finding sessions\n\n- List sessions on your socket: `{baseDir}/scripts/find-sessions.sh -S \"$SOCKET\"`.\n- Scan all sockets: `{baseDir}/scripts/find-sessions.sh --all` (uses `CoWork-OSS_TMUX_SOCKET_DIR`).\n\n## Sending input safely\n\n- Prefer literal sends: `tmux -S \"$SOCKET\" send-keys -t target -l -- \"$cmd\"`.\n- Control keys: `tmux -S \"$SOCKET\" send-keys -t target C-c`.\n\n## Watching output\n\n- Capture recent history: `tmux -S \"$SOCKET\" capture-pane -p -J -t target -S -200`.\n- Wait for prompts: `{baseDir}/scripts/wait-for-text.sh -t session:0.0 -p 'pattern'`.\n- Attaching is OK; detach with `Ctrl+b d`.\n\n## Spawning processes\n\n- For python REPLs, set `PYTHON_BASIC_REPL=1` (non-basic REPL breaks send-keys flows).\n\n## Windows / WSL\n\n- tmux is supported on macOS/Linux. On Windows, use WSL and install tmux inside WSL.\n- This skill is gated to `darwin`/`linux` and requires `tmux` on PATH.\n\n## Orchestrating Coding Agents (Codex, Claude Code)\n\ntmux excels at running multiple coding agents in parallel:\n\n```bash\nSOCKET=\"${TMPDIR:-/tmp}/codex-army.sock\"\n\n# Create multiple sessions\nfor i in 1 2 3 4 5; do\n  tmux -S \"$SOCKET\" new-session -d -s \"agent-$i\"\ndone\n\n# Launch agents in different workdirs\ntmux -S \"$SOCKET\" send-keys -t agent-1 \"cd /tmp/project1 && codex --yolo 'Fix bug X'\" Enter\ntmux -S \"$SOCKET\" send-keys -t agent-2 \"cd /tmp/project2 && codex --yolo 'Fix bug Y'\" Enter\n\n# Poll for completion (check if prompt returned)\nfor sess in agent-1 agent-2; do\n  if tmux -S \"$SOCKET\" capture-pane -p -t \"$sess\" -S -3 | grep -q \"❯\"; then\n    echo \"$sess: DONE\"\n  else\n    echo \"$sess: Running...\"\n  fi\ndone\n\n# Get full output from completed session\ntmux -S \"$SOCKET\" capture-pane -p -t agent-1 -S -500\n```\n\n**Tips:**\n\n- Use separate git worktrees for parallel fixes (no branch conflicts)\n- `pnpm install` first before running codex in fresh clones\n- Check for shell prompt (`❯` or `$`) to detect completion\n- Codex needs `--yolo` or `--full-auto` for non-interactive fixes\n\n## Cleanup\n\n- Kill a session: `tmux -S \"$SOCKET\" kill-session -t \"$SESSION\"`.\n- Kill all sessions on a socket: `tmux -S \"$SOCKET\" list-sessions -F '#{session_name}' | xargs -r -n1 tmux -S \"$SOCKET\" kill-session -t`.\n- Remove everything on the private socket: `tmux -S \"$SOCKET\" kill-server`.\n\n## Helper: wait-for-text.sh\n\n`{baseDir}/scripts/wait-for-text.sh` polls a pane for a regex (or fixed string) with a timeout.\n\n```bash\n{baseDir}/scripts/wait-for-text.sh -t session:0.0 -p 'pattern' [-F] [-T 20] [-i 0.5] [-l 2000]\n```\n\n- `-t`/`--target` pane target (required)\n- `-p`/`--pattern` regex to match (required); add `-F` for fixed string\n- `-T` timeout seconds (integer, default 15)\n- `-i` poll interval seconds (default 0.5)\n- `-l` history lines to search (integer, default 1000)",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/translate.json

@@ -0,0 +1,36 @@
+{
+  "id": "translate",
+  "name": "Translate",
+  "description": "Translate content to another language",
+  "icon": "🌐",
+  "category": "Writing",
+  "prompt": "Please translate the content in {{path}} to {{language}}.\n\nRequirements:\n- Maintain the original meaning and tone\n- Preserve formatting (markdown, code blocks, etc.)\n- Keep technical terms consistent\n- Adapt idioms appropriately for the target language\n- Preserve any code snippets unchanged\n\nSave the translated content to a new file with the language code suffix (e.g., README_es.md).",
+  "parameters": [
+    {
+      "name": "path",
+      "type": "string",
+      "description": "Path to the file to translate",
+      "required": true
+    },
+    {
+      "name": "language",
+      "type": "select",
+      "description": "Target language",
+      "required": true,
+      "default": "Spanish",
+      "options": [
+        "Spanish",
+        "French",
+        "German",
+        "Chinese",
+        "Japanese",
+        "Korean",
+        "Portuguese",
+        "Italian",
+        "Russian",
+        "Arabic"
+      ]
+    }
+  ],
+  "enabled": true
+}

package/resources/skills/trello.json

@@ -0,0 +1,10 @@
+{
+  "id": "trello",
+  "name": "Trello",
+  "description": "Manage Trello boards, lists, and cards via the Trello REST API.",
+  "icon": "📋",
+  "category": "Tools",
+  "prompt": "# Trello Skill\n\nManage Trello boards, lists, and cards directly from CoWork-OSS.\n\n## Setup\n\n1. Get your API key: https://trello.com/app-key\n2. Generate a token (click \"Token\" link on that page)\n3. Set environment variables:\n   ```bash\n   export TRELLO_API_KEY=\"your-api-key\"\n   export TRELLO_TOKEN=\"your-token\"\n   ```\n\n## Usage\n\nAll commands use curl to hit the Trello REST API.\n\n### List boards\n\n```bash\ncurl -s \"https://api.trello.com/1/members/me/boards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" | jq '.[] | {name, id}'\n```\n\n### List lists in a board\n\n```bash\ncurl -s \"https://api.trello.com/1/boards/{boardId}/lists?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" | jq '.[] | {name, id}'\n```\n\n### List cards in a list\n\n```bash\ncurl -s \"https://api.trello.com/1/lists/{listId}/cards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" | jq '.[] | {name, id, desc}'\n```\n\n### Create a card\n\n```bash\ncurl -s -X POST \"https://api.trello.com/1/cards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" \\\n  -d \"idList={listId}\" \\\n  -d \"name=Card Title\" \\\n  -d \"desc=Card description\"\n```\n\n### Move a card to another list\n\n```bash\ncurl -s -X PUT \"https://api.trello.com/1/cards/{cardId}?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" \\\n  -d \"idList={newListId}\"\n```\n\n### Add a comment to a card\n\n```bash\ncurl -s -X POST \"https://api.trello.com/1/cards/{cardId}/actions/comments?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" \\\n  -d \"text=Your comment here\"\n```\n\n### Archive a card\n\n```bash\ncurl -s -X PUT \"https://api.trello.com/1/cards/{cardId}?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" \\\n  -d \"closed=true\"\n```\n\n## Notes\n\n- Board/List/Card IDs can be found in the Trello URL or via the list commands\n- The API key and token provide full access to your Trello account - keep them secret!\n- Rate limits: 300 requests per 10 seconds per API key; 100 requests per 10 seconds per token; `/1/members` endpoints are limited to 100 requests per 900 seconds\n\n## Examples\n\n```bash\n# Get all boards\ncurl -s \"https://api.trello.com/1/members/me/boards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN&fields=name,id\" | jq\n\n# Find a specific board by name\ncurl -s \"https://api.trello.com/1/members/me/boards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" | jq '.[] | select(.name | contains(\"Work\"))'\n\n# Get all cards on a board\ncurl -s \"https://api.trello.com/1/boards/{boardId}/cards?key=$TRELLO_API_KEY&token=$TRELLO_TOKEN\" | jq '.[] | {name, list: .idList}'\n```",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/video-frames.json

@@ -0,0 +1,10 @@
+{
+  "id": "video-frames",
+  "name": "Video-frames",
+  "description": "Extract frames or short clips from videos using ffmpeg.",
+  "icon": "🎞️",
+  "category": "Tools",
+  "prompt": "# Video Frames (ffmpeg)\n\nExtract a single frame from a video, or create quick thumbnails for inspection.\n\n## Quick start\n\nFirst frame:\n\n```bash\n{baseDir}/scripts/frame.sh /path/to/video.mp4 --out /tmp/frame.jpg\n```\n\nAt a timestamp:\n\n```bash\n{baseDir}/scripts/frame.sh /path/to/video.mp4 --time 00:00:10 --out /tmp/frame-10s.jpg\n```\n\n## Notes\n\n- Prefer `--time` for “what is happening around here?”.\n- Use a `.jpg` for quick share; use `.png` for crisp UI frames.",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/voice-call.json

@@ -0,0 +1,10 @@
+{
+  "id": "voice-call",
+  "name": "Voice-call",
+  "description": "Start voice calls via the CoWork-OSS voice-call plugin.",
+  "icon": "📞",
+  "category": "Tools",
+  "prompt": "# Voice Call\n\nUse the voice-call plugin to start or inspect calls (Twilio, Telnyx, Plivo, or mock).\n\n## CLI\n\n```bash\nCoWork-OSS voicecall call --to \"+15555550123\" --message \"Hello from CoWork-OSS\"\nCoWork-OSS voicecall status --call-id <id>\n```\n\n## Tool\n\nUse `voice_call` for agent-initiated calls.\n\nActions:\n\n- `initiate_call` (message, to?, mode?)\n- `continue_call` (callId, message)\n- `speak_to_user` (callId, message)\n- `end_call` (callId)\n- `get_status` (callId)\n\nNotes:\n\n- Requires the voice-call plugin to be enabled.\n- Plugin config lives under `plugins.entries.voice-call.config`.\n- Twilio config: `provider: \"twilio\"` + `twilio.accountSid/authToken` + `fromNumber`.\n- Telnyx config: `provider: \"telnyx\"` + `telnyx.apiKey/connectionId` + `fromNumber`.\n- Plivo config: `provider: \"plivo\"` + `plivo.authId/authToken` + `fromNumber`.\n- Dev fallback: `provider: \"mock\"` (no network).",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/wacli.json

@@ -0,0 +1,10 @@
+{
+  "id": "wacli",
+  "name": "Wacli",
+  "description": "Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).",
+  "icon": "📱",
+  "category": "Tools",
+  "prompt": "# wacli\n\nUse `wacli` only when the user explicitly asks you to message someone else on WhatsApp or when they ask to sync/search WhatsApp history.\nDo NOT use `wacli` for normal user chats; CoWork-OSS routes WhatsApp conversations automatically.\nIf the user is chatting with you on WhatsApp, you should not reach for this tool unless they ask you to contact a third party.\n\nSafety\n\n- Require explicit recipient + message text.\n- Confirm recipient + message before sending.\n- If anything is ambiguous, ask a clarifying question.\n\nAuth + sync\n\n- `wacli auth` (QR login + initial sync)\n- `wacli sync --follow` (continuous sync)\n- `wacli doctor`\n\nFind chats + messages\n\n- `wacli chats list --limit 20 --query \"name or number\"`\n- `wacli messages search \"query\" --limit 20 --chat <jid>`\n- `wacli messages search \"invoice\" --after 2025-01-01 --before 2025-12-31`\n\nHistory backfill\n\n- `wacli history backfill --chat <jid> --requests 2 --count 50`\n\nSend\n\n- Text: `wacli send text --to \"+14155551212\" --message \"Hello! Are you free at 3pm?\"`\n- Group: `wacli send text --to \"1234567890-123456789@g.us\" --message \"Running 5 min late.\"`\n- File: `wacli send file --to \"+14155551212\" --file /path/agenda.pdf --caption \"Agenda\"`\n\nNotes\n\n- Store dir: `~/.wacli` (override with `--store`).\n- Use `--json` for machine-readable output when parsing.\n- Backfill requires your phone online; results are best-effort.\n- WhatsApp CLI is not needed for routine user chats; it’s for messaging other people.\n- JIDs: direct chats look like `<number>@s.whatsapp.net`; groups look like `<id>@g.us` (use `wacli chats list` to find).",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/weather.json

@@ -0,0 +1,10 @@
+{
+  "id": "weather",
+  "name": "Weather",
+  "description": "Get current weather and forecasts (no API key required).",
+  "icon": "🌤️",
+  "category": "Tools",
+  "prompt": "# Weather\n\nTwo free services, no API keys needed.\n\n## wttr.in (primary)\n\nQuick one-liner:\n\n```bash\ncurl -s \"wttr.in/London?format=3\"\n# Output: London: ⛅️ +8°C\n```\n\nCompact format:\n\n```bash\ncurl -s \"wttr.in/London?format=%l:+%c+%t+%h+%w\"\n# Output: London: ⛅️ +8°C 71% ↙5km/h\n```\n\nFull forecast:\n\n```bash\ncurl -s \"wttr.in/London?T\"\n```\n\nFormat codes: `%c` condition · `%t` temp · `%h` humidity · `%w` wind · `%l` location · `%m` moon\n\nTips:\n\n- URL-encode spaces: `wttr.in/New+York`\n- Airport codes: `wttr.in/JFK`\n- Units: `?m` (metric) `?u` (USCS)\n- Today only: `?1` · Current only: `?0`\n- PNG: `curl -s \"wttr.in/Berlin.png\" -o /tmp/weather.png`\n\n## Open-Meteo (fallback, JSON)\n\nFree, no key, good for programmatic use:\n\n```bash\ncurl -s \"https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12&current_weather=true\"\n```\n\nFind coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.\n\nDocs: https://open-meteo.com/en/docs",
+  "parameters": [],
+  "enabled": true
+}

package/resources/skills/write-tests.json

@@ -0,0 +1,31 @@
+{
+  "id": "write-tests",
+  "name": "Write Tests",
+  "description": "Generate unit tests for existing code",
+  "icon": "🧪",
+  "category": "Development",
+  "prompt": "Please analyze the code in {{path}} and write comprehensive unit tests for it.\n\nRequirements:\n- Use {{framework}} testing framework\n- Cover edge cases and error handling\n- Include both positive and negative test cases\n- Add clear test descriptions\n\nSave the tests in a file with appropriate naming convention.",
+  "parameters": [
+    {
+      "name": "path",
+      "type": "string",
+      "description": "Path to the file to test",
+      "required": true
+    },
+    {
+      "name": "framework",
+      "type": "select",
+      "description": "Testing framework to use",
+      "required": true,
+      "default": "jest",
+      "options": [
+        "jest",
+        "mocha",
+        "vitest",
+        "pytest",
+        "unittest"
+      ]
+    }
+  ],
+  "enabled": true
+}