菜单
Create and maintain repository skills for adonis-skills. Use when users ask to scaffold a new skill under skills/, generate agents/openai.yaml, run skill validation, refresh web index data, or standardize the skill authoring workflow.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate emoji-prefixed Conventional Commit messages and focused local commits from staged changes or a single clear unstaged change.
Commit a focused local change set with an emoji Conventional Commit message, safely stage a clear unstaged scope when needed, then push the current branch to its remote. Use when the user asks to "commit and push", "commit push", "submit and push", "push my committed change", or wants a local commit finalized on the remote. Do not create pull requests, merge requests, releases, tags, rebases, or deployment changes.
Use this skill when the user wants to decide, set, write, or use a durable coding-agent goal or /goal prompt that keeps Codex, Claude Code, or another agent working until a verifiable done condition is met. It gates autonomy, handles runtime differences, and writes copy-ready goal contracts with outcome, verification, constraints, write boundaries, iteration policy, completion evidence, and pause/ask conditions. Trigger on requests like 'should I set a goal?', 'set up a durable goal', 'give me a /goal prompt', 'turn this vague app idea into a goal', 'keep refactoring until tests pass', 'I am stepping away, have the agent finish this', migrations, refactors, ports, spec implementations, eval loops, backlog cleanup, or multi-checkpoint work. Do not use for single quick edits, running tests once, OKR/scrum goal questions, recurring reminders, or token-budget settings.
Create safe Git feature or hotfix branches with concise names. Use this whenever the user asks to create a branch, start work on a new feature or fix, wants a `feat/...` or `hotfix/...` branch name, asks for a short branch slug from a task description, or wants help before beginning local Git work. Default to recommending the branch name and command first, then create only after user confirmation. Do not push, commit, rebase, or create PRs.
Use when the user's pain is "adding/removing one more X means editing N files" and X is a recurring variant kind: popup, banner, modal, ad slot, payment method, AI model/tool, form field type, connector, sub-site, command, menu item, agent, extension point, or data source. Use when they want to design, refactor, review, name, or explain a pluggable mechanism using registry, interface/trait contract, runtime core, and convention folders; mention pluginize, pluggable, plugin architecture, extension point, registry pattern, or extensibility. Use when explaining the first-principles rationale, DDD/SOLID/OCP mapping, or industry analogies behind that structure. Use for cross-stack mapping to VSCode contributes, Webpack/Vite plugins, Rust/Tauri connectors, Python entry_points, or cargo features. Skip one variant's internals/styles/hooks/copy/bugs, and skip register/registry meaning DI container, user signup, or package registry.
Use BEFORE heavier workflow skills when route choice matters. Route creative work without a design doc/spec to Brainstorm; destructive or hard-to-reverse work to Discuss; unresolved decisions, Plan/Full fan-out, ship checks, unclear bugs, and fresh-eyes fix-then-re-review need this gate. Skip single-line read-only lookups, pure typo/formatting edits, trivial safe one-line fixes, and clearly safe named-skill requests. Outputs Route, Runtime skill, Fallback alias, and Execution path.
| name | repo-skill-creator |
| description | Create and maintain repository skills for adonis-skills. Use when users ask to scaffold a new skill under skills/, generate agents/openai.yaml, run skill validation, refresh web index data, or standardize the skill authoring workflow. |
Create and maintain repository skills with a triple workflow: creation mode, path-finalize mode, and auto-discover finalize mode.
skills/* path and indicates the skill is already generated/copied, run path-finalize mode directly without additional confirmation.skills:finalize:new) first.skills:new) and then continue finalize.Primary command (recommended):
pnpm skills:new
Manual creation commands:
pnpm skills:init <skill-name> --path skills --resources scripts,references
pnpm skills:finalize -- skills/<skill-name>
When the user pastes a path under skills/*, run:
pnpm skills:finalize -- <skill-path>
Examples:
pnpm skills:finalize -- skills/code-inspector-init
pnpm skills:finalize -- /Users/adonis/coding/adonis-skills2/skills/code-inspector-init/
Finalize pipeline is fixed and must run in order:
pnpm skills:quick-validate skills/<skill-slug>pnpm skills:validatepnpm skills:indexWhen user does not pass a skills/* path, run:
pnpm skills:finalize:new
Behavior contract:
git status --short --untracked-files=all:
A (index-added) and ?? (untracked)skills/<slug>/SKILL.md itself is in A or ??pnpm skills:finalize -- skills/<slug>git add skills/<slug> for each processed sluggit add apps/web/src/generated/skills-index.json when changedpnpm skills:newpnpm skills:openai-yaml unless explicitly requested.skills:install:local, skills:test:local) unless explicitly requested.git add -A; only stage skill-related files from this workflow.When executing this skill, always return:
pnpm skills:test:local).SKILL.md frontmatter valid with non-empty name and description.frontmatter.description must be English-only (ASCII characters only), and should clearly include when to use the skill.scripts/, references/, assets/) only when needed.