4,668 件 ・ 関連度順
概要と使いどころ
Execute a swarm plan wave by wave with filesystem isolation via git worktrees. For each wave, main context decides the scenario recipe + implementation contract for every task, then spawns one swarm-worker per task in parallel. Each worker executes its recipe and reports JSON status. Worktree merge-audit verifies write-set discipline before changes land on main. Aborts remaining waves on any audit or task failure.
日本語の概要は準備中です。原文の説明を表示しています。
Read-only release + backlog recap. Reports the last release, commits-since-tag classified by conventional-commit type with the semver bump they trigger and pushed-vs-origin state, the backlog bucketed (open/picked-up/dropped with epic parent→child nesting), the roadmap epics with their per-task tallies, and condensed open questions — then recommends the next pickup. One `cli.mjs recap` call returns all six recap keys. Invoke any time (on demand) to plan a release or choose the next thing to build; a compact form is also surfaced at session start. Not a workflow phase; never writes CHANGELOG; never starts or commits work.
日本語の概要は準備中です。原文の説明を表示しています。
EXPERIMENTAL. Join or leave an org-team coordination channel as a session peer. `/companion on <channel_id> [peer_id]` registers this Claude Code session as a `pclass:"session"` peer and works the claim → execute → signal loop, escalating un-decidable forks to the lead (never deciding). `/companion off` deregisters. `/companion status` reports the current peer. Part of org mode (Article X), which is opt-in via `velocity.org_mode.enabled` and OFF by default. Use when a human launches a second session to act as a peer alongside a lead.
日本語の概要は準備中です。原文の説明を表示しています。
Phase 10.5 — move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to docs/archive/<YYYY-MM-DD>/<slug>/. Runs before /commit so the committed tree is clean of work-in-flight files. workflow.json stays live and gets archived as the first step of /commit.
日本語の概要は準備中です。原文の説明を表示しています。
Workflow Phase 8 (optional) — OWASP-aligned security review of pending code changes. Produces a prioritized findings report (Critical/High/Medium/Low) mapped to OWASP Top 10 and CWE IDs. Output at `docs/security/<slug>-<date>.md`. Read-only.
日本語の概要は準備中です。原文の説明を表示しています。
Generate or repair a project's .gitignore. Composes the baseline must-ignore set (the single source of truth in baseline-ignores.json) with optional gitignore.io enrichment, and merges add-only so existing entries are never lost. Use when a repo has no .gitignore, when the commit-leak guard reports a gap, or when onboarding a new stack. Trigger: "set up gitignore", "fix my gitignore", "ignore node_modules/secrets", "gitignore for <stack>".
日本語の概要は準備中です。原文の説明を表示しています。
Derive an execution roadmap from a project's vision/spec docs by first principles, then diff that fresh derivation against the existing roadmap to prove the task ORDER is correct. Use this whenever the user wants to review, validate, re-derive, or sanity-check an execution roadmap or delivery plan; asks whether the tasks/epics are "in the right order"; suspects a task is scheduled before its prerequisite (a producer-after-consumer / dependency-inversion error like "OpenAPI after the web client that consumes it", OR a cross-cutting inherited default like observability/auth/tenancy scheduled after the feature work that inherits it — a seam-after-consumer error); wants to find missing tasks, circular dependencies, or over-fragmented epics; or wants to compact a plan to raise velocity. Also trigger on "review the roadmap", "re-derive the plan from the spec", "is this the right build order", "check the dependency graph of our epics", "which task should come first". It reads the vision + spec corpus, decomposes actors → use-cases → modules → epics → typed tasks, identifies cross-cutting inherited-default seams, builds a real dependency graph with hard + soft (seam) edges (deterministic helper), breaks cycles, topologically orders, compacts, and emits a derived roadmap PLUS a delta report against the current one — it never blindly overwrites a hand-crafted roadmap.
日本語の概要は準備中です。原文の説明を表示しています。
Orchestrates `impeccable` for every design task inside a workflow phase. Captures intent in natural language, classifies it (design / development / copy), translates design intents into a sequence of impeccable subcommand invocations, runs them in main context with state persistence at `.claude/state/design/<slug>.json`, and returns a structured report. ALWAYS invokes `impeccable` under the hood for the underlying design move; never picks aesthetic direction itself; never writes product code directly. Per CLAUDE.md Article X.2, all design tasks in workflow phases route through this skill.
日本語の概要は準備中です。原文の説明を表示しています。
Cycle-end retrospective converting recurring judgment failures into durable enforcement. Reviews the cycle's friction — repeated user corrections, guard trips, RCA themes, integrate failures — and turns each recurring one into a landmines.md entry, then proposes graduation candidates up the enforcement funnel (landmine → advisory hook → hard gate). Pairs with standup: standup says what shipped and what's next; retrospective says what kept going wrong and how to stop it structurally. Writes only memory entries and a report — graduation proposals are advisory and require the normal seed.md amendment path to become enforcement. Invoke at the end of a release cycle, an epic, or any stretch of work with repeated friction.
日本語の概要は準備中です。原文の説明を表示しています。
Review the auto-extracted candidates in `.claude/memory/_pending.md` and commit keepers to the canonical memory files (`landmarks.md`, `libraries.md`, `decisions.md`, `landmines.md`, `conventions.md`, `pending-questions.md`, `backlog.md`). Invoke at session start when the SessionStart hook reports pending candidates, or any time `_pending.md` has accumulated entries you want to curate. Reset the pending body after flushing.
日本語の概要は準備中です。原文の説明を表示しています。
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
日本語の概要は準備中です。原文の説明を表示しています。
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
日本語の概要は準備中です。原文の説明を表示しています。
Exploratory QA of web apps: find bugs, evidence, reports.
日本語の概要は準備中です。原文の説明を表示しています。
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
日本語の概要は準備中です。原文の説明を表示しています。
Send SMS messages with Azure Communication Services SMS Java SDK. Use when implementing SMS notifications, alerts, OTP delivery, bulk messaging, or delivery reports.
日本語の概要は準備中です。原文の説明を表示しています。
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
日本語の概要は準備中です。原文の説明を表示しています。
Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
日本語の概要は準備中です。原文の説明を表示しています。
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
日本語の概要は準備中です。原文の説明を表示しています。
End-of-week reflection report. Mines your Claude Code transcripts from the last 7 days to produce a self-contained HTML file with (1) the topics/areas you explored, (2) distilled key learnings with live-searched further-reading links, and (3) a token/command/skill/ctx-stack usage summary. Use when the user says "week in review", "weekly review", "what did I learn this week", "my week", or runs /week-in-review.
日本語の概要は準備中です。原文の説明を表示しています。
Run or resume a deliverable active-outreach workflow across lead discovery, screening, customer intel, and outreach email. Use when an operator or system pipeline needs durable run state, visible intermediate artifacts, evidence gates, report-bound human approval, and a final editable email draft that is never auto-sent.
日本語の概要は準備中です。原文の説明を表示しています。
OpenClaw-native SIEGER-aligned customer intelligence. Use a structured evidence bundle to produce a bilingual report with claim-level evidence, decision gates, industry-specific analysis, and proposed sales angles that require explicit approval before email drafting.
日本語の概要は準備中です。原文の説明を表示しています。
Build bilingual, evidence-backed, SIEGER v2 customer intelligence reports for foreign-trade leads. Use when OpenClaw or a sales operator needs claim-level citations, decision gates, an industry-specific analysis lens, a non-fabricated verdict card, and sales angles that require approval before downstream outreach drafting.
日本語の概要は準備中です。原文の説明を表示しています。
Run all project linters (ruff, mypy, sqlfluff) and report results. Invoke with /lint.
日本語の概要は準備中です。原文の説明を表示しています。
Validate trained models and analytical claims against their intended decision, independent evidence, and human-reviewed ground truth. Use when reviewing model performance, analysis conclusions, launch claims, or evaluation reports; use failure diagnosis instead when the main task is locating a known defect.
日本語の概要は準備中です。原文の説明を表示しています。