Cassiiopeia/projectops / skills/pro-skill-creator
pro-skill-creator
VerifiedCreate, review or improve a standard skill. Classifies intent as create/review/improve, then runs the matching phases. Use for 'make a skill', 'review this skill', 'improve this skill'.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.8 KB |
| references/anti_patterns.md | markdown | 4.4 KB |
| references/meta_principles.md | markdown | 5.1 KB |
| references/phase0_brainstorming.md | markdown | 8.6 KB |
| references/phase1_slots.md | markdown | 3.4 KB |
| references/phase2_question_format.md | markdown | 1.8 KB |
| references/phase4_checklist.md | markdown | 3.1 KB |
| references/phase6_report_format.md | markdown | 2.2 KB |
| references/review_improve.md | markdown | 4.0 KB |
| references/trigger_optimization.md | markdown | 2.6 KB |
| templates/config.json.example | other | 495 B |
| templates/python_cli_script.py | script | 3.9 KB |
references/phase2_question_format.md
View on GitHub# Phase 2 — One-question-at-a-time format
Use only when empty slots remain after Phase 1. One message = one slot. Ask in the user's language.
## Standard format
```
[Question] {slot name in user-friendly words}
Options:
1) {option A} — {one line on when it fits}
2) {option B} — {one line on when it fits}
3) Enter it directly
Recommended: {default} ({why this is the default})
```
## Rules
- **One message = one slot.** Never ask about 2 or more slots in one message.
- If a technical term appears, add a **one-line explanation** with it (H5).
- When you get an answer, fill the slot and move **to the next empty slot**.
- If the user answers several slots at once, accept them all and re-check only the empty slots (H2).
- The AskUserQuestion tool shows options as a nice UI — prefer it when the environment supports it.
## Good / Bad examples
**Bad (3 questions in one message):**
> "Tell me the domain, the DNS service and your email."
→ Users usually answer only 1~2, or think "ugh, complicated" and answer carelessly. Once the agent starts guessing the missing information, things go off the rails.
**Good (one message = one slot):**
> "Which domain will you use? (e.g. `example.com`)"
> (after the answer)
> "Thanks. Where is your DNS managed?
> 1) Cloudflare
> 2) AWS Route53
> 3) Other (enter it directly)
>
> Recommended: Cloudflare (company default)"
---
**Bad (no explanation of a technical term):**
> "Enter your Let's Encrypt email."
**Good:**
> "Which email should receive Let's Encrypt certificate expiry notices? (No sign-up is needed; you only get a notice when expiry is near.)"
---
**Bad (asking again for information the user already gave):**
> User: "docker-compose has the port set to 3000"
> Agent: "Which port will you use?"
**Good:** stay silent and move to the next empty slot. (`port=3000` is already extracted)
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 |