Arnie016/codex-prompt-templates / skills/skill-pack-factory
skill-pack-factory
VerifiedCreate non-overlapping Codex skills or a local plugin from repos, workflows, PDFs, APIs, or repeated tasks. Use when the user asks to make many skills, convert GitHub learnings into skills, build a skill catalog, or package a workflow into reusable Codex instructions.
Skill Pack Factory
Make fewer, sharper skills. Use references for breadth.
Creation Flow
- Cluster source material into workflow patterns.
- For multiple local source clones, run
$auto-skill-build-source-pattern-synthesisbefore creating skill files. - Remove duplicates and generic advice.
- For each skill, define one job and skip conditions.
- Keep
SKILL.mdshort; move examples and catalogs to references. - Add scripts only for repeated deterministic mechanics.
- Validate with
$skill-quality-gate.
When source material is an external skill pack, slash-command pack, hook plugin,
or upstream prompt catalogue, run $auto-skill-safety-external-skill-intake
before creating or installing local skills from it.
Candidate Skill Card
Name:
Trigger:
Inputs:
Workflow:
Tools:
References:
Skip when:
Validation:
Quality Bar
A skill is worth creating only if it changes Codex behavior in one of these ways:
- chooses better files/tools
- prevents a risky action
- saves repeated tokens
- preserves durable project knowledge
- turns a domain workflow into a checklist
- makes validation more reliable
Read references/skill-patterns.md before generating large batches.
Validation
- Each skill has one job, trigger language, skip conditions, and validation.
- Long catalogs/examples live in references, not
SKILL.md. - Run
$skill-quality-gatebefore installing or relying on the pack.
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: 470k | 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 |