JordanGunn/nunchuck / skills/plan/plan-exec
plan-exec
VerifiedExecute tasks in the active plan under `.plan/active/`. Writes concrete Output and Handoff for each task and archives the plan once terminal.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 820 B |
| assets/plan-archive-receipt-schema.json | config | 1.1 KB |
| assets/plan-root-schema.json | config | 1.8 KB |
| assets/plan-subplan-schema.json | config | 1.4 KB |
| assets/plan-task-schema.json | config | 3.0 KB |
| references/00_ROUTER.md | markdown | 528 B |
| references/01_SUMMARY.md | markdown | 476 B |
| references/02_TRIGGERS.md | markdown | 543 B |
| references/03_ALWAYS.md | markdown | 393 B |
| references/04_NEVER.md | markdown | 268 B |
| references/05_PROCEDURE.md | markdown | 989 B |
| references/06_FAILURES.md | markdown | 506 B |
| references/07_INSTRUCTIONS.md | markdown | 1.4 KB |
| references/08_PROCEDURE.md | markdown | 185 B |
| references/09_PROCEDURE.md | markdown | 1.8 KB |
| scripts/include/plan_exec_cli.py | script | 2.8 KB |
| scripts/include/plan_exec_parse.py | script | 15.1 KB |
| scripts/skill.ps1 | script | 1.7 KB |
| scripts/skill.shexecutable | script | 1.5 KB |
references/07_INSTRUCTIONS.md
View on GitHub---
description: Reference file for Instructions.
index:
- Initialize
- Critical: Execution Means Implementation
- Policies
---
# Instructions
## Initialize
1. Read all reference files listed in `metadata.references` in order before taking action.
2. Determine the target plan using `./skill.sh status` or user specification.
## Critical: Execution Means Implementation
**This skill performs actual work.** When executing a task:
- Write real code, not pseudocode
- Create real files, not descriptions of files
- Make real changes, not plans for changes
- Produce real outputs, not placeholders
If a task's Work section says "Create a Python script", you must write and save that script. If it says "Update the configuration", you must edit that file. **Filling in Output with descriptions of what could be done is a failure mode.**
## Policies
### Always
1. **Actually perform** each step in the Work section.
2. Execute in order: sub-plans a → b → c, tasks i → ii → iii.
3. Each completed task must have:
- **Output** with concrete, verifiable results
- **Handoff** with explicit next step
4. Verify your work exists on disk before marking complete.
### Never
1. Never fill Output with descriptions instead of results.
2. Never mark a task complete without performing the Work.
3. Never work ahead on later sub-plans.
4. Never skip the wrap-up phase.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |