Menu
Scaffold a new custom SKILL.md file interactively. Use when asked to create a new skill or slash command.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Generate a changelog or release notes from recent git history. Use when asked to write a changelog, summarize recent commits, or produce release notes.
Create or switch to a feature branch, typically tied to a GitHub issue. Use when asked to create a branch or start work on an issue.
Create, view, list, or comment on GitHub issues. Use when asked to file, open, or manage GitHub issues.
Create, review, or manage GitHub pull requests. Use when asked to open, check, or merge a PR.
Run the linter, auto-fix what's fixable, and report the rest. Use when asked to lint or fix lint errors.
Run the project test suite and surface failures. Use when asked to run tests or check test status.
| name | new-skill |
| description | Scaffold a new custom SKILL.md file interactively. Use when asked to create a new skill or slash command. |
| allowed-tools | Write |
| disable-agent-invocation | true |
Create a new custom skill for this project.
What to build: $ARGUMENTS
Gather requirements — If $ARGUMENTS is empty, ask the user:
deploy, summarise-pr)?Design the skill:
Read, Write, Edit, Glob, Grep, Bash)true for side-effectful or destructive skills (deploy, commit, send messages); omit for general-purpose skills$ARGUMENTS for the user-supplied target!{cmd || echo "fallback"} only when useful context should be captured at activation time (e.g. current git branch, project config); always include a fallbackShow the complete draft SKILL.md to the user and ask for approval or edits before writing anything.
Write the file to .opencli/skills/<name>/SKILL.md using the write tool — it will prompt for confirmation before touching the filesystem.
Confirm success:
/<name> [args])---
name: <kebab-case-name>
description: <one sentence — verb-led, specific enough for auto-activation>
allowed-tools: <space-separated: Read Write Edit Glob Grep Bash>
# disable-agent-invocation: true # uncomment for user-only or dangerous skills
---
<Step-by-step instructions. Use $ARGUMENTS for the user's input.>
<Optional: !{cmd || echo "fallback"} for context injected at activation time.>
Skills land in .opencli/skills/<name>/SKILL.md (project-scoped, highest priority).
They override same-named built-ins and are discovered at the next session start.