Manage local SKILL.md files with commands for listing, searching, creating, editing, removing, and comparing skills. A guided setup helps organize user and project skills, while validation checks file structure and required metadata.
中文简介正在准备中。当前显示英语简介。
Manage local skills - list, add, remove, search, edit, setup wizard
安装前可以查看交给 AI 代理的指令内容。
Manage local SKILL.md files with /skill commands. Shared execution, delegation,
state, hook, team, cancellation, verification, and escalation invariants live in
templates/AGENTS.md; follow that contract instead of repeating it here.
<Use_When>
<Do_Not_Use_When>
/learner to extract a skill from a conversation and /note for a short note.Canonical roots are ${CODEX_HOME:-$HOME/.codex}/skills/ (user) and .codex/skills/
(project). A skill lives at <root>/<name>/SKILL.md.
| Command | Contract |
|---|---|
/skill list | Scan both roots, parse frontmatter, and show name, description, triggers, scope, and quality/usage (N/A when unavailable). |
/skill add [name] | Run the authoring wizard, validate the name, choose scope, create SKILL.md, and report its path. |
/skill edit <name> | Find one scope, show metadata, then update description, triggers, argument hint, body, or rename and report the change. |
/skill remove <name> | Find the skill, show scope and metadata, confirm explicitly, then remove its directory. |
/skill search <query> | Case-insensitively search name, description, triggers, and body; rank name/trigger matches first and show context. |
/skill info <name> | Show parsed metadata, scope, path, and full body; suggest /skill search when absent. |
/skill sync | Compare user/project skills, show user-only/project-only/common entries, and confirm every copy or overwrite. |
/skill setup | Ensure both roots exist, scan them, then offer add, list, pattern scan, import, or done. |
/skill scan | Run setup's scan/inventory without its interactive menu. |
/skill validate | Validate every skill in both roots and report each path's pass/fail result; never rewrite files. |
With an argument, use direct command mode; without one, use the guided setup menu.
Ask for any missing values:
name: lowercase letters/digits separated by single hyphens ([a-z0-9]+(?:-[a-z0-9]+)*).description: a concise, non-empty one-line purpose.triggers: comma-separated recognition terms.argument-hint: optional invocation arguments.scope: user or project.Write this frontmatter at the start of every skill; optional metadata may add id,
source, and quality without replacing required fields:
---
name: <name>
description: <one-line purpose>
triggers: [<trigger1>, <trigger2>]
argument-hint: "<args>"
# optional: id, source, quality
---
Use an actionable body. The minimum recommended shape is:
# <Skill title>
## Purpose
What durable, codebase-specific outcome does this skill provide?
## When to Activate
Recognition signals, scope, and explicit non-goals.
## Workflow
1. Inspect the named files or inputs.
2. Apply the precise approach and record important assumptions.
3. Verify observable behavior and report evidence.
## Examples / Gotchas
Concrete invocation, edge cases, and failure recovery.
Prefer hard-won, non-obvious knowledge over generic programming advice. Include exact paths, commands, error text, and expected evidence when they materially help.
Before reporting success, check that the file exists, starts with --- frontmatter,
has non-empty name and description, uses a valid name, and has a non-empty body.
Reject malformed or unterminated YAML, multiline required scalar values, duplicate
names in one scope, missing directories/files, permission failures, and invalid
arguments. Report errors consistently:
✗ Error: <clear message>
→ Suggestion: <specific next step>
Every command ends with one concise result: ✓ plus the affected skill/path and
next action, or ✗ plus the error and suggestion. Preserve files on cancel or
validation-only runs. For add/edit/sync, report changed scope and metadata; for
list/search/info/scan/validate, report counts or matched paths and any failures.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Clean up working code by identifying duplication, dead code, unnecessary layers, and error paths that hide failures. Preserve behavior with targeted tests, simplify the requested files in stages, and report verification results and remaining risks.
中文简介正在准备中。当前显示英语简介。
Investigate repository behavior, architecture, or possible causes without changing files. Trace relevant code and supporting material, then rank explanations by evidence and confidence, with concrete file references and clear distinctions between observations, conclusions, and unresolved questions.
中文简介正在准备中。当前显示英语简介。
Ask Claude or Gemini through a locally installed command-line tool for focused questions, reviews, brainstorming, or second opinions. Save the prompt, original response, summary, and next steps in a reusable Markdown file.
中文简介正在准备中。当前显示英语简介。
Take an idea or issue through requirements clarification, reviewed planning, implementation, and verification. Supervise all stages in one recoverable OMX workflow, preserving artifacts and progress so work can resume or return to planning when findings require changes.
中文简介正在准备中。当前显示英语简介。
Run a persistent research workflow with a defined goal and explicit acceptance checks. It saves progress and finishes only when a recorded result passes either a validation script or an architect review of the research output.
中文简介正在准备中。当前显示英语简介。
Find the replacement for a research command removed in OMX 0.21. This migration notice directs existing autoresearch-goal usage to $autoresearch, the canonical research loop that requires validation before proceeding.
中文简介正在准备中。当前显示英语简介。