src/skills/planning/SKILL.md
Creates and manages persistent markdown planning files (task_plan.md, findings.md, progress.md) for complex task execution. Use when starting multi-step tasks, research projects, or any task requiring >5 tool calls. Solves the EXECUTION problem - staying focused during long-running tasks.
npx skillsauth add 23blocks-os/ai-maestro-plugins planningInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
4 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill solves the execution problem - losing focus during complex tasks:
| Problem | Symptom | This Skill Fixes It | |---------|---------|---------------------| | Goal drift | Forgot original objective after 50 tool calls | Re-read plan before decisions | | Lost progress | Can't remember what phase I'm in | Phase tracking in task_plan.md | | Repeated errors | Make same mistake twice | Error log prevents repetition | | Session loss | Can't resume after /clear | Planning files persist on disk |
Note: This is different from the Memory skill (which solves recall of past conversations). Planning solves staying focused NOW.
Context Window = RAM (volatile, limited, fast)
Filesystem = Disk (persistent, unlimited, explicit read required)
Anything important gets written to disk.
Planning output files (task_plan.md, findings.md, progress.md) should be written to:
AIMAESTRO_PLANNING_DIR environment variable (if set)docs_dev/ in the current project rootDo NOT write planning files to the project root — use docs_dev/ to avoid cluttering the project.
Create these files in docs_dev/ (not the project root or the skill directory):
| File | Purpose | Update When |
|------|---------|-------------|
| task_plan.md | Goals, phases, decisions, errors | After each phase |
| findings.md | Research, discoveries, resources | During research |
| progress.md | Session log, test results | Throughout session |
Before any complex task (3+ steps):
# 1. Determine output directory
PLAN_DIR="${AIMAESTRO_PLANNING_DIR:-docs_dev}"
mkdir -p "$PLAN_DIR"
# 2. Create planning files from templates
cat ~/.claude/skills/planning/templates/task_plan.md > "$PLAN_DIR/task_plan.md"
cat ~/.claude/skills/planning/templates/findings.md > "$PLAN_DIR/findings.md"
cat ~/.claude/skills/planning/templates/progress.md > "$PLAN_DIR/progress.md"
# 3. Edit task_plan.md with your specific goal and phases
Then follow the rules below.
NEVER start a complex task without creating task_plan.md.
Before writing any code or making any changes:
Before any major decision, re-read the plan:
cat "${AIMAESTRO_PLANNING_DIR:-docs_dev}/task_plan.md" | head -50
This refreshes your goals in the context window, preventing drift.
After completing any phase:
[x] completeAfter every 2 search/view/browse operations, immediately save key findings to findings.md.
Visual content (screenshots, PDFs, browser results) doesn't persist in context. Write it down NOW.
Every error goes in task_plan.md:
## Errors Encountered
| Error | Attempt | Resolution |
|-------|---------|------------|
| FileNotFoundError | 1 | Created missing config |
| API timeout | 2 | Added retry with backoff |
This prevents repeating the same mistakes.
if action_failed:
next_action != same_action
After a failure, CHANGE your approach. Don't retry the exact same thing.
Attempt 1: Diagnose & Fix
Attempt 2: Alternative Approach
Attempt 3: Broader Rethink
After 3 Failures: Escalate
| Situation | Action | Why | |-----------|--------|-----| | Just wrote a file | DON'T read | Content is in context | | Viewed image/PDF | Write findings NOW | Visual content doesn't persist | | Browser returned data | Write to findings.md | Screenshots don't persist | | Starting new phase | Read task_plan.md | Re-orient from plan | | Error occurred | Read relevant file | Need current state | | Resuming after gap | Read ALL planning files | Recover context |
Lost? Answer these questions:
| Question | Find Answer In | |----------|----------------| | Where am I? | Current phase in task_plan.md | | Where am I going? | Remaining phases in task_plan.md | | What's the goal? | Goal section in task_plan.md | | What have I learned? | findings.md | | What have I done? | progress.md |
USE for:
SKIP for:
| DON'T | DO Instead | |-------|------------| | Use TodoWrite for complex tasks | Create task_plan.md file | | State goals once and forget | Re-read plan before decisions | | Hide errors and retry | Document errors in plan | | Stuff everything in context | Store large content in files | | Start executing immediately | Create plan FIRST | | Repeat failed actions | Track attempts, change approach |
Planning and Memory solve different problems:
| Skill | Problem | Timescale | |-------|---------|-----------| | Memory | "What did we discuss last week?" | Days/weeks/months | | Planning | "What am I supposed to do next?" | Minutes/hours |
Use BOTH for complex work:
Templates are in ~/.claude/skills/planning/templates/:
task_plan.md - Phase and progress trackingfindings.md - Research and discoveriesprogress.md - Session loggingNote: The template path depends on how the skill was installed:
~/.claude/skills/planning/templates/<project>/.claude/skills/planning/templates/Copy to docs_dev/ and customize.
User: "Build a new authentication system"
1. CREATE PLAN
- Copy templates to docs_dev/
- Define goal: "Implement JWT authentication"
- Break into phases: Research, Design, Implement, Test, Document
2. EXECUTE PHASE 1 (Research)
- Search memory: memory-search.sh "authentication"
- Search docs: docs-search.sh "auth patterns"
- Write findings to findings.md
- Mark Phase 1 complete in task_plan.md
3. EXECUTE PHASE 2 (Design)
- READ task_plan.md (refresh goals)
- READ findings.md (recall research)
- Design approach, document decisions
- Mark Phase 2 complete
4. CONTINUE...
- Always read plan before major decisions
- Always update after completing phases
- Always log errors
Templates not found:
ls ~/.claude/skills/planning/templates/
If missing, reinstall the skill or copy from AI Maestro repo.
Forgot the goal:
cat "${AIMAESTRO_PLANNING_DIR:-docs_dev}/task_plan.md" | head -20
Lost track of progress:
grep -E "^\s*-\s*\[" "${AIMAESTRO_PLANNING_DIR:-docs_dev}/task_plan.md"
Shows all checkboxes and their status.
tools
Create, manage, and interact with canvas HTML pages. Write visual UIs that users see in the AI Maestro dashboard, receive structured interactions when users click/submit/select, and update pages in response. Full lifecycle management for agent-rendered canvases.
tools
Creates, manages, and orchestrates AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "rename agent", "hibernate agent", "wake agent", "install plugin", "show agent", "export agent", "restart agent", "install marketplace", or any agent lifecycle management task.
tools
Creates, manages, and orchestrates AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "rename agent", "hibernate agent", "wake agent", "install plugin", "show agent", "export agent", "restart agent", "install marketplace", or any agent lifecycle management task.
documentation
Authenticate AI agents with auth servers using the Agent Identity (AID) protocol. Supports Ed25519 identity documents, proof of possession, OAuth 2.0 token exchange, and scoped JWT tokens. Self-contained — works independently without other protocols.