AGENT SKILL

setup

Verify actionlint's prerequisites and configuration here, and register its git pre-commit entry. Use when: 'set up actionlint', 'configure actionlint', 'is actionlint working', workflow lint silently isn't happening, or a hook reported a missing prerequisite or drifted git hook. Actions: check (read-only, default) | apply [install-git-hooks [scope=local|shared]]. Re-runnable and safe.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 30
Forks
7

01 前言 Front Matter

shell
bash
description
Verify actionlint's prerequisites and configuration here, and register its git pre-commit entry. Use when: 'set up actionlint', 'configure actionlint', 'is actionlint working', workflow lint silently isn't happening, or a hook reported a missing prerequisite or drifted git hook. Actions: check (read-only, default) | apply [install-git-hooks [scope=local|shared]]. Re-runnable and safe.
allowed-tools
[ "Bash(command -v node*)", "Bash(command -v actionlint*)", "Bash(node \"${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs\" verify:*)", "Bash(node ${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs verify:*)", "Bash(node \"${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs\" plan:*)", "Bash(node ${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs plan:*)" ]
argument-hint
[check|apply [install-git-hooks [scope=local|shared]]]
user-invocable
true
disable-model-invocation
true

02 资源文件 1

03 SKILL.md 正文

Pre-computed context

check's tool probes ran at load time. Read these rows instead of re-issuing them; each shows the tool's path when present, or absent when missing:

  • node: !command -v node 2>/dev/null || echo absent
  • actionlint: !command -v actionlint 2>/dev/null || echo absent

A row reading [shell command execution disabled by policy] carries no result: run that tool's command -v probe via Bash instead.

  • Pointer: for the placeholder a skipped load-time command leaves, fetch skills § Inject dynamic context live.
  • As of: 2026-11-11
  • Recheck trigger: the placeholder text changes.

Purpose

Thin check-centric setup per the uniform setup contract (docs/plugin-philosophy.md "Setup is explicit and repeatable" in the marketplace repository): check inspects and reports, apply resolves. The only consumer-project files this plugin owns are its git-hook entry copies, which apply install-git-hooks writes. actionlint auto-discovers its own optional config from the repository, and the tunables are the native userConfig options (actionlint_enabled and actionlint_end_of_turn). Every prerequisite is a PATH binary the plugin never bundles, and the plugin never installs system packages, so apply is guidance-and-verify with that one write path. It never modifies user settings or the plugin cache.

Action routing: no argument or check runs the check; apply runs the check first, then offers remediation guidance; apply install-git-hooks registers the git-hook entry. All are non-interactive. Never prompt when the action is given. apply install-git-hooks asks only where its section says to.

check (read-only)

The git-hook script (${CLAUDE_PLUGIN_ROOT}/git-hooks/actionlint-check.sh) is the single source of truth for what it requires and how it resolves things.

Read it first. Probe what it actually does, don't recite this file. Then read the pre-computed tool rows, run the remaining probes via Bash, and report a PASS/FAIL/INFO table with one remediation line per FAIL. Do not modify anything. Read each option value from this text; never put a ${user_config.*} string in a shell command. Open plugin files by the ${CLAUDE_PLUGIN_ROOT} paths this skill names; never Glob or Grep the plugin directory.

When the plugin's toggle is disabled, every prerequisite absence except node downgrades from FAIL to INFO. The Claude Code hooks exit through their enabled-gate before probing anything, so a deliberately disabled plugin is not broken. Report those probes informationally and note that re-enabling restores the FAIL semantics. A missing node stays FAIL: the launcher runs before the enabled-gate. A tool the git pre-commit entry needs keeps the grade it gets with the toggle on while that entry is installed (step 7 reports it as a tool line beside an ok, stale or modified entry): the entry runs at commit outside Claude Code and reads no toggle.

  1. Bash version. Check against the floor, Bash 3.2 or newer (README Requirements).
  2. node. The pre-computed node row. FAIL if absent, even when the toggle is off: every hook row launches through node hooks/exec-bash.mjs, so the hooks do not launch and the session-start probe does not run. The hooks cannot report this themselves. Probed here through Bash, which works without the launcher.
  3. actionlint. The pre-computed actionlint row. FAIL if absent: the pre-commit entry then fails the commit of an agent with the install command and gives a person a notice, and the end-of-turn check does nothing.
  4. actionlint config. INFO: actionlint auto-discovers an optional .github/actionlint.yaml from the repository when present. It is not required. actionlint runs with its built-in defaults without one. Report whether one exists for the reader's awareness; its absence is not a FAIL.
  5. Hook toggles. Report the effective actionlint_enabled value: ${user_config.actionlint_enabled} (unexpanded or empty means default true; any value other than true disables the Claude Code hooks). Also report actionlint_end_of_turn: ${user_config.actionlint_end_of_turn} (unexpanded or empty means the shipped default false), as INFO: on, the Stop row checks the uncommitted workflow changes once per turn; off, only the git pre-commit entry lints.
  6. Hook registration. INFO: confirm the plugin is enabled for this project (/plugin → Installed) rather than parsing settings files.
  7. Git pre-commit entry. Run node "${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs" verify from the repository. Each line is <state>\t<entry>[\t<detail>]: ok is PASS, declined is INFO (this clone said no; silent at session start), and missing, stale, modified or superseded is a FAIL whose remediation is apply install-git-hooks; a superseded detail lists what an install under an earlier plugin name left, which that action removes on the user's yes. A tool\t<tool>\tmissing line means the installed entry cannot run here: list every such tool with its install method from the ${CLAUDE_PLUGIN_ROOT}/prerequisites.json (Read that path), so a lane or cloud setup script can provision it before an auto-mode session commits. Outside a git repository, report INFO and skip the step.

apply install-git-hooks [scope=local|shared]

Run this section only when the user typed /actionlint:setup apply install-git-hooks as a command; that typed command is the only go-ahead this flow takes, plan included. The user's answers to this section's own questions continue a run it started. On any other request, including a plain-language "run the apply step" or "register the hook" and a hook notice, never run install.mjs plan, copy, decline or config-hook, and reply that the user should type /actionlint:setup apply install-git-hooks themselves.

Registers the plugin's git-hook entries (git-hooks/entries.json) with the repository's hook manager. The installer script only detects, renders and writes files the plugin owns; every step that needs judgment comes back to you as a decisions[] item, which you reason about and apply with your own edit tools.

  1. Scope. Use the argument when given. Otherwise, when the user is present, ask: local (this clone only, nothing committed) or shared (committed under .githooks/actionlint/, so every teammate and agent gets it). When nobody can answer, use local.
  2. Plan. Run node "${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs" plan --scope <scope> and read the JSON: manager, actions[], decisions[].
  3. Manager conflict. A manager-conflict decision lists the evidence (two managers, or one this installer does not drive, such as the pre-commit framework). Show it and ask which manager should carry the entry; rerun plan with --manager lefthook|husky|plain. Without an answer, stop here and report.
  4. Actions. When actions[] holds copy items, run node "${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs" copy --scope <scope> (plus the same --manager when you passed one). It prints installed, refreshed, unchanged, refused, blocked, unsafe-path or stage-failed per entry; refused means a locally edited copy or dispatcher, which the modified decision covers, blocked that another tool owns the local hooks directory, which the hooks-path-owned decision covers, unsafe-path the decision of that name, and stage-failed that git add failed on a shared install: report it, since the team would not receive the files.
  5. Decisions. Read reference/git-hook-decisions.md for what each kind asks of you, apply each one, then rerun plan until only the decisions you chose to leave remain.
  6. Verify. Run verify and report its lines as check step 7 does.

The entry only reports: at commit it lints the staged workflow files and blocks the commit on a finding actionlint reports on a line the commit adds. It rewrites nothing.

When the user does not want an entry in this clone, run node "${CLAUDE_PLUGIN_ROOT}/lib/git-hooks/install.mjs" decline --entry actionlint-check; the session-start drift line then stays silent until verify runs by hand, and --undo reverses it. Add --global (with or without --undo) to decline the entry in every clone; git config --global checks.git-hooks.declined true declines every entry of every plugin, and an entry's own key set to false in a clone opts that entry back in. The adoption path explains each install scope to the user.

apply (idempotent)

Run check, then for each FAIL point at the resolution. This skill installs nothing:

  • missing actionlint: platform install guidance from the README Requirements section (the kjanat/actionlint install guide).

  • missing node / Bash: platform install instructions from the README Requirements section.

  • toggle off: set actionlint_enabled to true through Claude Code's native flow, interactively with /plugin configure actionlint@<marketplace> or by a headless route, as the marketplace's plugin-reconfiguration convention gives them in § The routes (it owns the verified-version record). Apply the scope and failure-signal caveats in its § Caveats every setup skill's short form carries. Read both sections and print what they give, the fallback route, its behavior on an already-installed plugin and the scope to pass included, rather than only naming them, and leave out the verified-version record. Never uninstall to reconfigure; that section links what an uninstall deletes. This skill never writes user settings or pluginConfigs. Afterwards rerun check in a fresh session, since a same-session check can still show the old value, and report the observed effective value, never an unobserved change.

After pointing at a remediation, re-run the relevant check probe live via Bash (a pre-computed row predates the remediation, so never re-read it) and report its actual result. Never claim resolved on the reader's report that they installed something.

Re-running apply after everything passes changes nothing and reports "already configured".

Gotchas

  • A userConfig knob is reachable natively only if the manifest declares it. An undeclared key silently cannot be set through native plugin configuration (a raw settings env block still works). Pointer: the --config row in plugin install.
  • What each headless route does to stored options is the convention's to state. Read it in § The routes, which also holds the verified-version record: which CLI release each behavior was observed on, and under which conditions.
  • -shellcheck= / -pyflakes= are deliberate, and the deadlock claim is a local observation. The entry disables actionlint's external run-block linters because each spawns a subprocess per run: block; the additional "ShellCheck deadlocks on large blocks under the Windows subprocess IPC path in actionlint 1.7.x" rationale is the author's own reproduction. No matching upstream rhysd/actionlint issue as of 2026-07-23; recheck when a rhysd/actionlint issue or release note reports ShellCheck hanging or deadlocking under the Windows subprocess path, which would replace the local reproduction with an upstream-confirmed cause and a fixed version to pin against. Deep run-block linting belongs in CI.

What this skill does NOT do

  • Run the linter. git commit exercises the installed pre-commit entry.
  • Write the plugin cache, Claude Code user settings, or pluginConfigs.
  • Install actionlint, node or Bash.
  • Download or execute tools during check beyond the read-only command -v presence probes and the installer's read-only verify.

04 同仓库更多 Skills

melodic-software
melodic-software/claude-code-plugins

track

Backlog reads through the bound tracker: search open and closed items, view one item with its comments and state history. Use when another skill searches or reads tracker items.

★ 30
melodic-software
melodic-software/claude-code-plugins

reviewer-media

Reviewer media for one pull request: decides whether it needs a narrated walkthrough, builds the storyboard from /review:explain-change's digest, has /explainer-video:produce render it and hands the manifest to /source-control:pull-request media. Use when asked for 'reviewer media', 'a walkthrough video for this PR', 'a produced video of this change', or when pull-request ready or monitor hands a PR over.

★ 30
melodic-software
melodic-software/claude-code-plugins

route

Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.

★ 30
melodic-software
melodic-software/claude-code-plugins

route

Model and effort per agent role (orchestrator, worker, verifier, retrieval) for a multi-agent run, resolved through the bundled defaults and the user, team and personal override config layers into fenced JSON with single-agent and fan-out variants and the layer behind each value. Use when asked 'which model for the subagents', 'route the roles' or 'model routing', or before a skill passes a role's model on a spawn.

★ 30
melodic-software
melodic-software/claude-code-plugins

principles

Module-design vocabulary for architecture findings, and the checks built on it. Use when: 'what is a deep module', 'what is a seam', 'deep vs shallow module', 'what is the deletion test', 'leverage and locality', 'module design vocabulary', 'which word do we use for X in architecture findings'. Scanning a codebase for friction is /architecture:improve.

★ 30
melodic-software
melodic-software/claude-code-plugins

write

Structured five-field bug report (title, steps to reproduce, expected vs actual, justified severity, suggested fix location) from an informal description, read-only. Use when the user names a defect they observed, or asks for one written up ('report a bug', 'file a bug', 'write this up as a bug').

★ 30