JordanGunn/nunchuck / skills/prompt/prompt-compile
prompt-compile
VerifiedCompile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, conciseness, and correctness.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 939 B |
| assets/observability-template.md | markdown | 1.8 KB |
| assets/prompt-artifact-schema.json | config | 2.3 KB |
| assets/prompt-artifact-schema.md | markdown | 1.3 KB |
| assets/receipt-schema.json | config | 1.1 KB |
| references/00_ROUTER.md | markdown | 476 B |
| references/01_SUMMARY.md | markdown | 672 B |
| references/02_CONTRACTS.md | markdown | 683 B |
| references/03_TRIGGERS.md | markdown | 352 B |
| references/04_NEVER.md | markdown | 303 B |
| references/05_ALWAYS.md | markdown | 365 B |
| references/06_PROCEDURE.md | markdown | 910 B |
| references/07_FAILURES.md | markdown | 528 B |
| scripts/compile.ps1executable | script | 365 B |
| scripts/compile.shexecutable | script | 323 B |
| scripts/help.shexecutable | script | 437 B |
| scripts/include/prompt_compile_cli.py | script | 2.7 KB |
| scripts/include/prompt_parse.py | script | 6.7 KB |
| scripts/validate.shexecutable | script | 667 B |
references/07_FAILURES.md
View on GitHub---
description: What to do when things go wrong.
index:
- Failure Modes
- Recovery
---
# Failures
## Failure Modes
1. **No artifact** — `.prompt/active.yaml` does not exist
2. **Compile fails** — script execution fails or produces invalid output
3. **Artifact not ready** — `status` is not `ready`
4. **Polish introduces errors** — markdown no longer matches the artifact intent
## Recovery
- Prefer re-running deterministic compilation over manual patching
- Preserve `.prompt/active.yaml` for re-compilation
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |