skill-info
Skill28 starsChanged 58 days agoApache-2.0View on GitHub
Show one skill in full — its team record or Library folder, versions, installs, health, and its eval report when it is a team skill — as Markdown boards from the terum-skills CLI. Use when the user names a skill and asks what it is, who installed it, how it scored, or what its receipt says.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- desktop/AGENTS.mdAGENTS.md
- eval-reportSkill
- evalSkill
- list-skillsSkill
- search-skillsSkill
- skill-statusSkill
- sync-skillsSkill
- terum-skillsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 33
No TTY: never pipe y, never drive the CLI with expect, never add --frames to dodge a question.
- Very specific: line 34
Never use the skill-file
!commandinjection. - Very specific: line 35
Do not cd; run from the current working directory and pass absolute paths.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Show one skill: the detail board, then its eval report when the skill is shared with the team.
Arguments: everything after the command (in Claude Code this arrives as "$ARGUMENTS"): the skill's name, a unique prefix of it, or nothing when the working directory is inside a Library skill folder; --team <name> is passed through.
Command
npx -y terum-skills@latest ls skill <name> --format mdThen, only when that board's Next: line offers eval-report, also run
npx -y terum-skills@latest eval-report <name> --format mdand show both boards, detail first. A failure naming several candidates (Ambiguous skill name …) is a result: show it and ask which one.
Before
Nothing to confirm: both commands only read.
After
Show the boards verbatim; do not re-summarise unless asked. Offer the Next: line. No skill named … is a result, not something to retry: offer the list-skills skill so the user can find the name. An italic _Resolved: …_ line says which folder or record answered a prefix or a bare invocation; keep it.
Rules
- No TTY: never pipe
y, never drive the CLI withexpect, never add--framesto dodge a question. A question the CLI asks means the verb belongs in a terminal: say so and hand over the command. - Never use the skill-file
!`command`injection; run every command with your shell tool and read its output. - Do not
cd; run from the current working directory and pass absolute paths. - Exit 1 is a result, not a retry: show the failure block, do not re-run, and do not claim earlier steps were rolled back.
Sandbox
When CODEX_SANDBOX_NETWORK_DISABLED=1 is set and the command starts with npx, add --prefer-offline after npx so a cached package resolves without the registry; if npx still reports a network error, ask the user to run the command in a terminal. In that sandbox the verbs that need the network — sync, install, publish, invite, eval, and update's release probe — are handed to a terminal with the reason.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

