Agent skill

work-plan

This skill should be used when the user asks to "show work plan", "what's the plan for feature N", "show progress", "view execution plan", or wants to see phase breakdown, progress status, and next actions for a feature.

Stars 0
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/ianphil/my-skills/tree/main/work-plan

SKILL.md

Work Plan

Generate a comprehensive execution plan showing current status, phase breakdown, and next actions. Writes output to {feature-path}/work-plan.md for persistent tracking.

User Input

FEATURE_ID = $ARGUMENT (optional, defaults to current branch feature)

Accept feature ID like "001" or "001-mcp-integration". If not provided, extract from current git branch.

Output Behavior

  • Primary output: Write full work plan to {feature-path}/work-plan.md
  • Console output: Show condensed summary with key status and next action
  • Updates: Subsequent runs overwrite the file with current state (timestamp included)

Workflow

Step 1: Extract Feature ID

  1. If ARGUMENT provided:
    • Format "NNN" (e.g., "001"): Search backlog/plans/ and backlog/plans/_completed/ for matching folder
    • Format "NNN-slug" (e.g., "001-mcp-integration"): Use directly
  2. If no ARGUMENT:
    • Run git branch --show-current
    • Extract feature ID from branch name (e.g., feature/001-mcp-integration001-mcp-integration)
    • If not on a feature branch, show error and list available features

Note: In-progress features are in backlog/plans/{NNN}-{slug}/, completed features in backlog/plans/_completed/{NNN}-{slug}/

Step 2: Load Feature Context

Read the following files:

  • {feature-path}/tasks.md (required)
  • {feature-path}/spec.md (for feature name/description)
  • specs/tests/{feature-id}.md (if exists, for spec test info)
  • Current git branch status

Step 3: Parse tasks.md

Extract:

Phase Information:

  • Phase headers: ## Phase N: Name
  • For each phase: number, name, description, task range, task count, completed count
  • Entry spec test task ([SPEC] with "→ expect ALL FAIL")
  • Exit spec test task ([SPEC] with "→ expect ALL PASS")

Dependency Information:

  • Find dependency diagram (after "## Dependencies" header)
  • Parse dependency arrows (──►, ──┬──►, etc.)
  • Build dependency graph

Overall Metrics:

  • Total task count, completed count, percentage

Step 4: Determine Status

For each phase:

  • Complete: All tasks checked (- [x])
  • In Progress: Some tasks checked
  • Not Started: No tasks checked
  • Blocked: Depends on incomplete phases

Identify current phase and next action.

Step 5: Generate Work Plan

Build the work plan with these sections (see references/output-format.md for detailed templates):

  1. Current Status - Feature name, branch, progress, current phase
  2. Phase Overview - Table with status, progress, blocks
  3. Recommended Execution Plan - Per-phase commands and goals
  4. Parallel Execution Strategy - Wave structure for independent phases
  5. Quick Commands Reference - Command table
  6. Success Criteria - Completion checklist
  7. Manual Testing Strategy - What needs manual testing and when
  8. Next Action - Specific recommended command

Step 6: Write to File

Write the complete work plan to {feature-path}/work-plan.md:

markdown
<!-- Auto-generated by /work-plan - Updated: {ISO timestamp} -->

# Work Plan: Feature {NNN} - {Feature Name}

{All sections from Step 5}

File behavior:

  • Creates new file if doesn't exist
  • Overwrites existing file with fresh state on each run
  • Includes timestamp header for tracking when last updated

Step 7: Display Summary to Console

Show a condensed summary to the user (NOT the full file contents):

✅ Work plan written to: {feature-path}/work-plan.md

## Quick Status
- **Progress**: {completed}/{total} tasks ({percentage}%)
- **Current Phase**: {phase-name} ({status})

## Next Action
{next action recommendation with command}

This keeps console output minimal while the full details live in the file.

Next Action Logic

State Recommendation
Wrong branch / no tasks Prime and start Phase 1
Phase in progress Continue current phase
Phase blocked Complete blocking phase first
Ready for next Start next phase
Multiple independent ready Run phases in parallel
All complete Final verification, create PR

Error Handling

Feature not found:

❌ Error: Feature '{feature-id}' not found

Available features:
{list folders in backlog/plans/ and backlog/plans/_completed/}

Usage: /work-plan {feature-number}

tasks.md not found:

❌ Error: tasks.md not found at {feature-path}/tasks.md

This feature may not follow the methodology structure.

Output Guidelines

  • Keep output concise but actionable
  • Use emojis for visual clarity (✓, ⚠️, ✅, 🔄, ⏸️, 🔒)
  • Provide specific commands, not just guidance
  • Always include "Next Action" - never leave user wondering what to do

Additional Resources

Reference Files

For detailed output templates, consult:

  • references/output-format.md - Full templates for all output sections

Expand your agent's capabilities with these related and highly-rated skills.

ianphil/my-skills

commit

This skill should be used when the user asks to "commit changes", "push my code", "commit and push", "save my work", or wants to stage all changes and push to remote.

0 0
Explore
ianphil/my-skills

prime-feat

This skill should be used when the user asks to "load feature context", "resume feature work", "prime feature N", "continue feature N", or wants to load all planning artifacts for a specific feature number.

0 0
Explore
ianphil/my-skills

implement-agents

This skill should be used when the user asks to "implement in parallel", "run phases concurrently", "parallel implement", "implement-agents phase X phase Y", or wants to orchestrate multiple agents running /implement simultaneously.

0 0
Explore
ianphil/my-skills

code-walkthrough

Generate structured, hallucination-proof code walkthroughs using Showboat. Use when the user asks to "walk me through this code", "explain this codebase", "create a walkthrough", "document how this works", "give me a tour of this repo", or wants a readable narrative document that explains code with real verified snippets. Also triggers on "showboat", "linear walkthrough", or "code documentation". Not for quick code questions — this produces a full markdown document.

0 0
Explore
ianphil/my-skills

ainotes

This skill should be used when the user asks to "consolidate notes", "summarize ainotes", "clean up notes", "ainotes", or wants to consolidate accumulated agent observations into a compact summary.

0 0
Explore
ianphil/my-skills

implement

This skill should be used when the user asks to "implement phase N", "implement task T001", "do TDD for phase", "implement T001-T009", or wants to execute tasks following strict TDD red-green-refactor workflow.

0 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results