Individual skill
prompt-to-skill
Converts a prompt a user runs repeatedly into a reusable, paid-quality SKILL.md. Use when someone says "I keep pasting this prompt", "turn this prompt into a skill", "package this workflow", or has a recurring task pattern they want portable across projects and sessions. Do NOT use to author a skill from a capability idea with no existing prompt (use skill-creator) or to restructure an existing SKILL.md (use skill-author).
skills/prompt-to-skill/SKILL.md
Source commit 97a13607d669157a4a16d5ba79b77f208319f7b9
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 24
- Repository last updated
- Oct 13, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- claude Repository topic
- claude-skills Repository topic
- skill-me Repository topic
- operations Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 4,232 bytes
Read excerpt
# Prompt to Skill
Takes a prompt someone runs over and over and packages it into a skill any agent can load, discover, and execute consistently. The costly mistake this prevents: transcribing the prompt verbatim into frontmatter, which preserves its padding and loses its triggers - producing a skill that neither fires nor performs.
## Inputs to collect
1. The prompt itself, verbatim - the real text they paste, not a summary of it.
2. Two or three example runs: the input they gave and the output they liked. Real runs reveal what the prompt actually does versus what it says.
3. What the prompt gets wrong today - the edits they make to its output every time. Those corrections become skill rules.
If the user cannot produce an example run, treat the request as a capability idea and hand off to skill-creator.
## Operating procedure