process-needs-action
This skill should be used when you need to process pending action items from a designated folder and generate detailed implementation plans based on organizational rules. Ideal for task management workflows that require systematic processing of pending items, plan creation, and dashboard updates. Use when the user asks to process action items, review pending tasks, or generate plans from a backlog.
Best use case
process-needs-action is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
This skill should be used when you need to process pending action items from a designated folder and generate detailed implementation plans based on organizational rules. Ideal for task management workflows that require systematic processing of pending items, plan creation, and dashboard updates. Use when the user asks to process action items, review pending tasks, or generate plans from a backlog.
Teams using process-needs-action should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/process-needs-action/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How process-needs-action Compares
| Feature / Agent | process-needs-action | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
This skill should be used when you need to process pending action items from a designated folder and generate detailed implementation plans based on organizational rules. Ideal for task management workflows that require systematic processing of pending items, plan creation, and dashboard updates. Use when the user asks to process action items, review pending tasks, or generate plans from a backlog.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Process Needs Action Process pending action items from a designated folder and create detailed implementation plans based on organizational rules. ## Required Clarifications Before processing, gather these essential details: 1. **What is your vault/workspace directory path?** (e.g., `AI_Employee_Vault/`, `workspace/`, etc.) 2. **What should I filter by?** (Process all pending items, or filter by priority: high/medium/low?) ## Optional Clarifications 3. **Should I preview plans before creating them?** (Show plan content for approval before saving) 4. **Should I auto-update file statuses?** (Change from `pending` to `in_progress` automatically, or ask first) Note: Avoid asking all questions at once. Ask required questions first, then optional ones if needed. ## Before Implementation Gather context to ensure successful processing: | Source | Gather | |--------|--------| | **User Input** | Vault directory path, processing preferences, priority filter | | **Codebase** | Verify paths exist, validate directory structure | | **Conversation** | Any specific processing rules or preferences discussed | | **Handbook/Rules** | Read organizational processing rules if available | ## Instructions ### 1. Validate Structure Check that required paths exist: - Verify `<vault_dir>/Needs_Action/` directory exists - Check for `<vault_dir>/Company_Handbook.md` (optional but recommended) - Ensure `<vault_dir>/Plans/` directory exists (create if missing) - Verify `<vault_dir>/Dashboard.md` exists (create if missing) ### 2. Read Processing Rules - If `<vault_dir>/Company_Handbook.md` exists, read it to understand processing rules - Note priority keywords (e.g., URGENT, CLIENT, INVOICE, DEADLINE) - Note file handling guidelines - If handbook doesn't exist, use default processing rules ### 3. Scan Needs_Action Folder - List all markdown files in `<vault_dir>/Needs_Action/` - Filter for files with `status: pending` in frontmatter - Apply priority filter if specified by user - Sort by priority (high → medium → low) ### 4. Process Each Action Item For each pending file: **a. Read and Parse** - Read the full file content - Extract frontmatter metadata (type, priority, source_file, detected) - Identify the source file type and context **b. Analyze Content** - Based on file type (PDF, TXT, image, etc.), determine appropriate action - Check for priority keywords (URGENT, CLIENT, INVOICE, DEADLINE) - Cross-reference with Company Handbook rules - Consider Business_Goals.md priorities **c. Create Detailed Plan** - Create a new file in `<vault_dir>/Plans/` - Filename: `PLAN_[YYYYMMDD_HHMMSS]_[source_filename].md` - Use plan template from `references/plan-template.md` - Include: - Clear objective - Step-by-step actions with checkboxes - Required information or approvals - Expected outcome - Links to related files - If preview mode enabled, show plan to user for approval before saving **d. Update Action File** - Change status from `pending` to `in_progress` (or ask user if auto-update disabled) - Add processing timestamp - Add link to created plan ### 5. Update Dashboard - Update `<vault_dir>/Dashboard.md` - List all pending actions with priorities - Show count of items processed - Update "Last Check" timestamp - If Dashboard.md doesn't exist, create it with basic structure ### 6. Log Activity (Optional) - If `<vault_dir>/Logs/` directory exists, append to today's log file - Filename: `<vault_dir>/Logs/YYYY-MM-DD.json` - Record: files processed, plans created, any errors ## Error Handling Handle these scenarios gracefully: | Scenario | Action | |----------|--------| | **No pending files found** | Inform user "No pending action items found" and exit gracefully | | **Vault directory doesn't exist** | Ask user to confirm path or provide correct vault directory | | **Company Handbook missing** | Proceed with default processing rules, inform user | | **Malformed frontmatter** | Log error, skip file, continue with next file | | **File permission errors** | Log error with filename, skip file, continue processing | | **Plans directory doesn't exist** | Create `<vault_dir>/Plans/` directory automatically | | **Dashboard.md missing** | Create basic dashboard with template structure | ## What NOT to Do Avoid these anti-patterns: - **Don't modify source files directly** - Only update frontmatter status, never change content - **Don't skip updating the dashboard** - Always update dashboard to reflect current state - **Don't create plans without context** - Read source file completely before creating plan - **Don't process without checking status** - Only process files with `status: pending` - **Don't hardcode paths** - Use user-provided vault directory path - **Don't fail silently** - Log all errors and inform user of issues ## Plan Template See `references/plan-template.md` for the complete plan template structure. ## Success Criteria - [ ] All pending action files matching filter criteria are reviewed - [ ] Detailed plan created for each action item - [ ] Action files updated to `in_progress` (if auto-update enabled) - [ ] Dashboard updated with current status and counts - [ ] All errors logged and reported to user - [ ] User informed of completion with summary ## Example Usage **User request:** "Process all high-priority action items" **Workflow:** 1. Ask required clarifications (vault path, priority filter) 2. Validate directory structure at `<vault_dir>/` 3. Read `<vault_dir>/Company_Handbook.md` if available 4. Scan `<vault_dir>/Needs_Action/` for files with `status: pending` and `priority: high` 5. For each high-priority file: - Read and analyze content - Create detailed plan in `<vault_dir>/Plans/` - Update action file status 6. Update `<vault_dir>/Dashboard.md` with processing results 7. Report summary: "Processed 3 high-priority items, created 3 plans"
Related Skills
acc-create-action
Generates ADR Action classes for PHP 8.5. Creates single-responsibility HTTP endpoint handlers with PSR-7 support. Includes unit tests.
acc-check-leaky-abstractions
Detects leaky abstractions in PHP code. Identifies implementation details exposed in interfaces, concrete returns from abstract methods, framework leakage into domain, and infrastructure concerns in application layer.
abaqus-interaction
Define contact and interactions - contact pairs, tie constraints, connectors. Use when user mentions contact, friction, tie, parts touching, or bonded surfaces.
pattern-extraction
Extract design systems, architecture patterns, and methodology from codebases into reusable skills and documentation. Use when analyzing a project to capture patterns, creating skills from existing code, extracting design tokens, or documenting how a project was built. Triggers on "extract patterns", "extract from this repo", "analyze this codebase", "create skills from this project", "extract design system".
asyncredux-sync-actions
Creates AsyncRedux (Flutter) synchronous actions that update state immediately by implementing reduce() to return a new state.
asyncredux-action-status
Checks an AsyncRedux (Flutter) action's completion status using ActionStatus right after the dispatch returns. Use only when you need to know whether an action completed, whether it failed with an error, what error it produced, or how to navigate based on success or failure.
analysis-process
Turn the idea for a feature into a fully-formed PRD/design/specification and implementation-plan. Use when you have a spec or requirements that needs implementation. Use in pre-implementation (idea-to-design) stages to make sure you understand the spec/requirements and ensure you have a correct implementation plan before writing actual code.
ai-interaction-patterns
AI-specific interaction design patterns covering wayfinding, prompt UX, human-in-the-loop controls, trust & transparency, AI identity, and context management. Based on Shape of AI (shapeof.ai). Use when asking about 'AI UX', 'AI interaction', 'prompt UX', 'AI trust', 'AI disclosure', 'AI avatar', 'AI personality', 'AI memory UX', 'action plan UX', 'stream of thought', 'AI citations', 'AI controls', 'AI wayfinding', 'AI suggestions', 'gallery pattern', 'follow-up pattern', 'draft mode', 'AI variations', 'AI consent', 'AI caveat', 'human-in-the-loop', 'AI transparency', 'AI state', 'prompt design', 'AI onboarding', or 'generative UI'.
agency-processor
Extract agency data and generate a branded demo landing page with real-time progress updates. Optimized for speed and conversion.
synapse-action-development
Explains how to create Synapse plugin actions. Use when the user asks to "create an action", "write an action", uses "@action decorator", "BaseAction class", "function-based action", "class-based action", "Pydantic params", "ActionPipeline", "DataType", "input_type", "output_type", "semantic types", "YOLODataset", "ModelWeights", "pipeline chaining", or needs help with synapse plugin action development.
apache-spark-data-processing
Complete guide for Apache Spark data processing including RDDs, DataFrames, Spark SQL, streaming, MLlib, and production deployment
action_logger
Keep an audit trail of changes, commands, and verification.