skill-creatorlisted

Author, audit and iterate on Claude skills - write a new SKILL.md from scratch, restructure or trim an existing one, and measure whether it actually works. Use when the user wants to create a skill, turn a workflow they just did into a skill, edit or improve an existing skill, fix a skill's frontmatter or description, run evals against a skill, benchmark a skill against a no-skill baseline, or optimize a description so it fires at the right time and not the wrong one. Also use when a skill needs validating before it ships - frontmatter key allowlist, the 1024-character description cap, ASCII, referenced-path existence. Not for acquiring or installing a skill from a repo or URL, or porting an already-authored skill between platforms - that is install-skill.
M4NUSH7/Niche-Claude-Code · ★ 1 · AI & Automation · score 74

Install: claude install-skill M4NUSH7/Niche-Claude-Code

# Skill Creator **Edition:** CLI (Claude Code). The Cowork/Linux edition is `skill-creator-cowork`. Platform differences live in `references/platforms.md` - read it before assuming a browser, a subagent pool, or `~/.claude/` exists. The loop: 1. Decide what the skill should do and roughly how. 2. Write a draft. 3. Write 2-3 realistic test prompts and run claude-with-the-skill on them, plus a baseline. 4. Show the user the results (`eval-viewer/generate_review.py`) and read their feedback. 5. Rewrite based on that feedback. Repeat. 6. Optimize the description for triggering, then package. Your job is to work out where the user already is in that loop and jump in there. If they say "I want a skill for X", start at 1. If they hand you a draft, start at 3. If they say "skip the evals, just vibe with me", do that - the loop is a default, not a gate. ## Talking to the user Skill authors range from career engineers to people who opened a terminal last week. Read the context cues. "Evaluation" and "benchmark" are usually fine; "JSON" and "assertion" need a signal that the user knows those words before you use them bare. A one-clause definition in passing costs nothing and never insults anyone. ## Interop  **Edition:** CLI (Claude Code). **Precedence:** - Yields to `install-skill` on packaging, platform adaptation and installation (`verify_skill.py --package` is canonical; `package_skill.py` defers). - Yields to `playwright-tester` on browser-tes