Echo-aloha/asphalt-codex-skills-5 / skills/pfc-skill-pack
pfc-skill-pack
VerifiedGovern Asphalt-Codex-Skills-5 as a PFC 5.0-only asphalt-mixture package, enforcing version purity, external fistPkg boundaries, portable assets, validation, and release hygiene.
| File | Kind | Size |
|---|---|---|
| LICENSE | other | 1.1 KB |
| NOTICE.md | markdown | 675 B |
| README.md | markdown | 285 B |
| SKILL.md | skill md | 3.9 KB |
| agents/openai.yaml | config | 290 B |
| references/asset-inventory.md | markdown | 924 B |
| references/migration-coverage.md | markdown | 2.7 KB |
| references/pfc5-help-audit.md | markdown | 5.2 KB |
| references/pfc5-skill-set.json | config | 533 B |
| references/skill-index.md | markdown | 5.6 KB |
| scripts/README.md | markdown | 1.8 KB |
| scripts/build_skill_index.py | script | 316 B |
| templates/case-intake.md | markdown | 280 B |
scripts/README.md
View on GitHub# Scripts
Scripts in this folder support package-level maintenance. They should stay small, deterministic, and independent of private local project layouts.
## Current Scripts
### `build_skill_index.py`
Lists sibling directories that contain `SKILL.md`. Use it to check which skills in a pack are valid entrypoints.
Run from the skill-pack root or repository root:
```bash
python scripts/build_skill_index.py
```
## Suggested Future Helpers
### `check_portability.py`
Purpose: scan a skill pack for machine-local references and non-portable path conventions.
Expected behavior:
- Search markdown, YAML, JSON, and script files.
- Report drive-letter paths, home-directory paths, private download-folder names, and project-only folder names.
- Allow an ignore list for intentionally documented examples.
### `check_skill_tree.py`
Purpose: validate the PFC5 asphalt parent/specialist relationships.
Expected behavior:
- Confirm `pfc5-asphalt-workflow` lists the retained specialist skills.
- Confirm dependency manifests resolve only to retained skills.
- Confirm every skill has a `SKILL.md` with required frontmatter.
### `check_assets.py`
Purpose: verify that bundled source assets follow the asset inventory policy.
Expected behavior:
- Flag generated plots, videos, save files, and private project metadata.
- Confirm large source bundles have a manifest.
- Report executable files so maintainers can decide whether to exclude or document them.
## Rules For New Scripts
- Use explicit CLI arguments.
- Do not assume a particular drive, user name, download folder, or project directory.
- Do not mutate files unless a `--write` flag is provided.
- Print clear next steps when checks fail.
- Keep helper scripts optional; skills should remain understandable from markdown and bundled templates.
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: 471k | 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 |