skills-gateway
Gateway and router to a catalog of skills that are not registered directly. Use it before any task a specialized skill could handle, such as text, JSON or git chores. It finds the right skill and loads its instructions.
- License 许可
- Unlicense
- 最近更新
- 2026-11-15
- Stars
- ★ 21
- Forks
- 9
01 前言 Front Matter
- name
- skills-gateway
- description
- Gateway and router to a catalog of skills that are not registered directly. Use it before any task a specialized skill could handle, such as text, JSON or git chores. It finds the right skill and loads its instructions.
- allowed-tools
- Bash(node:*)
03 SKILL.md 正文
Skills Gateway
The skills behind this gateway are not registered with you. This gateway is the only way to reach them.
Every command runs as:
node ${CLAUDE_SKILL_DIR}/../../../gateway.js <command>
- Find candidates with
route "<the request in a few words>". It prints the best matching skills, best first, named<source>__<skill>. - If no candidate fits, run
listto see the whole catalog. If nothing fits there either, tell the user no skill covers it and do the task without the gateway. - Load the chosen skill with
load <source>__<skill> <arguments>. It prints the skill instructions and its base directory. - Follow the loaded instructions exactly as if that skill had been invoked directly. Load only the skills the task needs.
- If a command exits non-zero, tell the user the stderr message. Exit 2 is an unknown skill or a bad request, exit 3 is an unreachable skill source.
04 同仓库更多 Skills
word-count
Counts the words, lines and characters of a text or a file.
slugify
Turns a title or a sentence into a URL slug, lowercase words joined by hyphens with accents removed.
json-format
Validates a JSON file and pretty prints it with two space indentation, or reports where the JSON is invalid.
commit-message
Writes a conventional commit message for the staged git changes.
decision-log
Record, list, show and supersede architecture decisions that persist across sessions in the shared agent infra state store. Use when the user says "record this decision", "log an ADR", "what did we decide about", "list decisions", or "supersede decision".
answer-grader
Grade a written answer (release notes, summaries, commit messages, JSON payloads) against checks using the shared evaluators of the agent infra, store every run in the evals UI and track the score trend per suite. Use when the user says "grade this answer", "check this output", "does this meet the criteria", "score the release notes" or "show grading history".