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 |
scripts/include/prompt_compile_cli.py
View on GitHub#!/usr/bin/env python3
import argparse
import importlib.util
import sys
from prompt_parse import ACTIVE_PATH, artifact_exists, compile_to_markdown, load_artifact, validate_artifact, write_compiled
def cmd_help() -> int:
print(
"""prompt-compile - Compile .prompt/active.yaml into .prompt/PROMPT.md
Usage:
prompt-compile [--dry-run]
prompt-compile help
prompt-compile validate
Deterministic behavior:
- Verifies active artifact exists
- Validates artifact (schema)
- Writes .prompt/PROMPT.md (unless --dry-run)
- Preserves active artifact
"""
)
return 0
def cmd_validate() -> int:
errors: list[str] = []
if importlib.util.find_spec("yaml") is None:
errors.append("missing dependency: pyyaml")
if importlib.util.find_spec("jsonschema") is None:
errors.append("missing dependency: jsonschema")
if errors:
for e in errors:
print(f"error: {e}", file=sys.stderr)
return 1
print("ok: prompt-compile CLI is runnable")
return 0
def cmd_compile(dry_run: bool) -> int:
if not artifact_exists():
print("error: no active prompt", file=sys.stderr)
print(f"path: {ACTIVE_PATH} (does not exist)", file=sys.stderr)
print("use prompt-forge to create one first", file=sys.stderr)
return 1
artifact = load_artifact() or {}
errors = validate_artifact(artifact)
if errors:
print("error: artifact has validation errors", file=sys.stderr)
for e in errors:
print(f" - {e}", file=sys.stderr)
return 1
if artifact.get("status") != "ready":
print(f"error: prompt status is '{artifact.get('status')}', not 'ready'", file=sys.stderr)
print("use prompt-forge to finish refinement first", file=sys.stderr)
return 1
content = compile_to_markdown(artifact)
if dry_run:
print("--- PROMPT.md (dry-run) ---")
print(content)
return 0
output_path = write_compiled(content)
print(f"compiled: {output_path}")
print(f"artifact: {ACTIVE_PATH} (preserved)")
return 0
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(prog="prompt-compile", add_help=False)
parser.add_argument("command", nargs="?", help="help or validate")
parser.add_argument("--dry-run", action="store_true")
return parser
def main() -> int:
parser = build_parser()
args = parser.parse_args()
if args.command == "help":
return cmd_help()
if args.command == "validate":
return cmd_validate()
if args.command not in (None, ""):
print(f"error: unknown command '{args.command}'", file=sys.stderr)
return 1
return cmd_compile(dry_run=args.dry_run)
if __name__ == "__main__":
sys.exit(main())
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 |