Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create and manage persistent markdown planning files for structured task execution. Use when the user asks to "create a plan", "track progress", "start a research project", or when a task requires more than 5 tool calls and needs structured phase tracking to stay focused and avoid goal drift.
.claude/skills/davila7-planning/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 11 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 6% | 0% |
Solve the execution problem -- staying focused during complex, multi-step tasks. Uses persistent markdown files to track goals, findings, and progress so you never lose context. Part of the AI Maestro suite.
Create in docs_dev/ (or $AIMAESTRO_PLANNING_DIR):
| File | Purpose | Update When | |------|---------|-------------| | task_plan.md | Goals, phases, decisions, errors | After each phase | | findings.md | Research, discoveries, resources | During research | | progress.md | Session log, test results | Throughout session |
bashPLAN_DIR="${AIMAESTRO_PLANNING_DIR:-docs_dev}" mkdir -p "$PLAN_DIR"
Then create task_plan.md with:
markdown# Task: [Goal] ## Phases - [ ] Phase 1: Research - [ ] Phase 2: Design - [ ] Phase 3: Implement - [ ] Phase 4: Test ## Decisions | Decision | Rationale | Date | |----------|-----------|------| ## Errors Encountered | Error | Attempt | Resolution | |-------|---------|------------|
task_plan.mdfindings.md| Strike | Action | |--------|--------| | 1 | Diagnose root cause, apply targeted fix | | 2 | Try a different approach entirely | | 3 | Question assumptions, search for similar issues | | After 3 | Escalate to user with all attempts documented |
Lost? Answer these from your planning files:
task_plan.md)findings.md)progress.md)This skill works standalone with no dependencies. For the complete experience including memory search, docs search, graph query, agent messaging, and agent management, install the full AI Maestro platform.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 17,683 | 11,507 | -35% | 1 | 1 | 0% | 3,150 | 1,744 | -45% | 0 | 0 | — |
case-02 | fail→pass | 27,228 | 23,997 | -12% | 1 | 1 | 0% | 4,337 | 4,772 | +10% | 0 | 0 | — |
case-01 | fail→fail | 17,068 | 5,403 | -68% | 1 | 1 | 0% | 2,850 | 1,049 | -63% | 0 | 0 | — |
case-04 | fail→pass | 17,982 | 4,655 | -74% | 1 | 1 | 0% | 4,015 | 1,557 | -61% | 0 | 0 | — |
case-05 | fail→pass | 4,388 | 2,963 | -32% | 1 | 1 | 0% | 727 | 1,246 | +71% | 0 | 0 | — |
case-06 | pass→pass | 7,821 | 3,233 | -59% | 1 | 1 | 0% | 1,356 | 1,257 | -7% | 0 | 0 | — |
case-07 | pass→pass | 9,794 | 4,674 | -52% | 1 | 1 | 0% | 1,667 | 1,559 | -6% | 0 | 0 | — |
case-08 | fail→pass | 8,218 | 4,606 | -44% | 1 | 1 | 0% | 1,407 | 1,498 | +6% | 0 | 0 | — |
case-09 | fail→pass | 9,686 | 5,505 | -43% | 1 | 1 | 0% | 1,645 | 1,681 | +2% | 0 | 0 | — |
case-10 | pass→pass | 11,090 | 7,880 | -29% | 1 | 1 | 0% | 1,826 | 1,686 | -8% | 0 | 0 | — |
case-11 | fail→pass | 10,455 | 2,215 | -79% | 1 | 1 | 0% | 1,805 | 1,086 | -40% | 0 | 0 | — |
case-12 | pass→pass | 8,452 | 1,059 | -87% | 1 | 1 | 0% | 1,544 | 859 | -44% | 0 | 0 | — |
case-13 | pass→pass | 13,153 | 7,200 | -45% | 1 | 1 | 0% | 2,332 | 2,180 | -7% | 0 | 0 | — |
case-14 | fail→pass | 6,161 | 1,972 | -68% | 1 | 1 | 0% | 1,107 | 1,018 | -8% | 0 | 0 | — |
case-15 | fail→pass | 5,459 | 2,670 | -51% | 1 | 1 | 0% | 992 | 1,196 | +21% | 0 | 0 | — |
case-16 | fail→pass | 8,885 | 2,408 | -73% | 1 | 1 | 0% | 1,475 | 1,174 | -20% | 0 | 0 | — |
case-17 | fail→pass | 11,406 | 2,740 | -76% | 1 | 1 | 0% | 2,212 | 1,172 | -47% | 0 | 0 | — |
case-18 | fail→fail | 6,379 | 2,374 | -63% | 1 | 1 | 0% | 1,026 | 1,167 | +14% | 0 | 0 | — |
case-19 | fail→pass | 8,805 | 4,141 | -53% | 1 | 1 | 0% | 1,633 | 1,511 | -7% | 0 | 0 | — |
case-20 | pass→pass | 15,713 | 14,669 | -7% | 1 | 1 | 0% | 2,715 | 3,405 | +25% | 0 | 0 | — |
case-21 | pass→pass | 12,140 | 11,434 | -6% | 1 | 1 | 0% | 2,178 | 2,782 | +28% | 0 | 0 | — |
case-22 | fail→fail | 1,698 | 1,586 | -7% | 1 | 1 | 0% | 267 | 926 | +247% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +55 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.