Use when auditing and fixing reliability or resilience in a scope — timeouts, retries, idempotency, partial failure, dependency outages, overload, failover, recovery,…
Read a plan-completion-audit report, plan the fixes, and execute them with safety gates per finding. Verifies between batches; optionally re-runs the audit to confirm closure.
Audit ResumeSourceFolder for structural completeness and layout conformance; interactively fill gaps and write edits back to source markdown
Use when auditing repo topology in a scope — code grouped by type where the repo groups by feature, god-modules, misplaced files, leaky or missing module boundaries,…
审计配合主流程 — 整合资料收集 + 调整审核 + 函证管理的全流程审计配合。 适用情形：年度审计配合报告时执行，整合 audit-evidence-collection、 audit-adjustment-review 和 confirmation-management，输出完整的审计配合报告。 核心：资料完整 → 调整合规 → 函证充分 → 报告出具。
Audit tools/ directory for structure compliance, test coverage, CLI quality, and documentation completeness.
Reads the execution trail the `audit` hook writes into `.claude/audit-usage/` and consolidates it across runs — spend per skill and agent, duration, failure rate, permissions…
Consulta a trilha de auditoria de uma feature. Mostra rastreabilidade completa de decisões, modelos, assertions e commits.
Generate full documentation from source code with the 3-stage AI pipeline (outline, write, review). Triggers on: write docs, generate API reference, create README, AI doc…
Generate concept, task, and reference templates for one feature using Jinja2 meta templates. Triggers on: generate template, regenerate feature, write help for, create docs for…
Initialize a .help/ documentation system in a project. Scans source directories for features and creates features.yaml.
Author DeLP/McCarthy context lifting rules between existing context YAMLs so cross-context claim reasoning can proceed. Collection-level, runs after all papers are ingested.
Report which feature templates are stale by comparing source file hashes. Triggers on: stale templates, what's outdated, doc status, check help freshness, what changed.
Analyzes authorization and access-control logic across routes and resources for privilege and enforcement flaws. Use when auditing authorization, RBAC, or access control.
Create CloudWatch alarms and SNS subscription for AI automation monitoring. Creates 4 alarms (DLQ depth, WI-Router errors, PR-Router errors, throttles) and subscribes an email…
Start autonomous execution with stop hook feedback loop. Works until all tasks complete or max iterations reached. Use when you want continuous unattended execution.
Deploy Lambda code for AI automation agents (wi-router and/or pr-router). Packages agent steps + shared libs into a zip and uploads to AWS Lambda.
Autonomous development workflow - understand an issue, plan changes, implement with change notes, and run an iterative verify-fix loop until passing.
Run the AI automation evaluation framework against test fixtures. Verifies agent quality without hitting ADO or LLM APIs. Use after changing prompts, rules, or agent steps.
Enable parallel agent execution for multi-domain features with git worktree isolation
Prepare a team's certified backlog for a fleet of parallel /loop /auto sessions — audit `specified` labels for unattended-shippability (mark human-dependent issues `needs…
Analisa um projeto de forma read-only e gera um README_GENERATED.md de alta qualidade.
Automatically analyze and tag untagged [Gorgias](https://composio.dev/toolkits/gorgias) tickets based on content.
Detecta a stack do alvo, gera testes com o runner nativo dela (pytest, Jest/Vitest, go test...), roda, e auto-corrige testes mal escritos (parando se achar bug real no código).
Generate BDD test scenarios or full build specs from a product usage video using AutoGherk
Set up, view, and manage automations on monday CRM boards using natural language — no block IDs or technical knowledge required.
Run an automated smoke test using the godot-mcp server. Launches the project, captures debug output, and checks for errors or crashes.
Volledige autonome ontwikkelcyclus — PR's mergen, branches opruimen, lokaal/online synchen, open issues uitvoeren, iteratie-branch aanmaken, debug starten.
Agent 또는 skill의 프로덕션 배포를 canary 1% → 10% → 50% → 100% 4단계로 자동 진행한다. 각 단계는 continuous-eval 통과와 SLO 준수를 gate로 하며 circuit breaker가 SLO 위반을 감지하면 즉시 이전 단계로 자동 롤백한다. 100% 승격은 사람 승인이 필수다.
Orchestrate a bounded round of automated issue processing: reclaim orphaned in-progress issues, discover eligible `autoship:ready` issues, and invoke `/ship` sequentially for each…
Every Auvik endpoint as a command, plus the cross-client answers the Auvik UI and API cannot give you.
Scan a release on VirusTotal and generate false positive submission instructions for flagged AV vendors.
Avvertenze legali, limiti, deontologia, GDPR AI, segreto professionale. Blocchi output obbligatori. Nessuna consulenza legale. — from pixari/claude-per-il-diritto-italiano
Guided Oracle birth and awakening ritual. Default is Soul Sync (~20min), or --fast (~5min). Use when creating a new Oracle in a fresh repo, when user says 'awaken', 'birth…
Build award-winning websites (Awwwards SOTD 7.5+, FWA, CSSDA). Recommends the best design archetype for the brief, calibrates atmosphere, and produces a complete DESIGN.md.
Set or clear the away status on this airc identity. IRC /away analog — exchanged at handshake so peers see the status in airc whois. Run with no args (or use 'airc back') to clear.
Triage new issues and PRs on awesome-list repos by applying curation criteria distilled from past decisions.
Use when approved BA/project truth needs to be communicated as a professional, plain-language FRD report that mixed business and technical readers can understand without changing…
Run one repository's pull-request queue as the merge lane of the loop-lane three-session topology: a self-paced standing or drain loop that invokes /source-control:babysit-prs…
Cleanly stop an active /babysit-pr watcher for a PR. Sets the watcher's stop flag in session-state so its next tick terminates, cancels the recurring poll (CronDelete in durable…
Babysit your own open GitHub pull requests as a tiered fleet loop. The safe default discovers YOUR PRs under the current repo's owner, checks readiness, fixes clear branch-owned…
Verify backend/API releases with tests, migrations, queues, integrations, and endpoint smoke checks.
Use this skill when applying home-manager or darwin configurations that require long-running builds. Automatically runs builds in background, monitors progress with appropriate…
Audit a domain's backlink profile via Ahrefs, Moz, or a free-tier fallback — producing a referring-domain register, anchor histogram, and a toxic-link disavow plan.
Scan the System Backlog for stale items, enforce lifecycle timeouts, auto-archive completed items, and produce a hygiene report. Use as a scheduled maintenance task or on demand.
Auto-classify a new or existing System Backlog item as NOVEL, DUPLICATE, OVERLAP, or DEFERRED. Use when a new idea is added to the backlog or when the user asks to triage an…
Re-trigger the bake-off mindset whenever you are about to brief several agents/models to produce competing designs, mockups, drafts, or approaches for the human to judge…
Apply the Buddhist Five Powers (Bala 5) as a practical subagent balance check before planning, coding, review, or recovery work.
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances.
银行关系评估 — 评估公司与银行的关系健康度，包括授信额度使用、 利率水平、服务质量和战略合作潜力。 适用情形：年度银行关系审视、半年度评估时，或用户要求"评估银行关系"时执行。 核心：授信分析 + 关系健康度评分 + 策略建议。
银行关系评估 — 评估公司与银行的关系健康度，包括授信额度使用、 利率水平、关系紧密度和维护策略。 适用情形：年度银行关系审视、再融资前、或用户要求"评估银行关系"时执行。 核心：授信分析 + 关系健康度评分 + 维护策略。
Change the colors of the usage and context bars in Claude Code's status line. Usage: /bar-colors --usage #RRGGBB --ctx #RRGGBB
Examensvorbereitungs-Fragen für das 1. und 2. Juristische Staatsexamen, bundeslandspezifisch nach JAG.
Overnight batch execution of queued analysis designs. Generates marimo notebooks (8-cell contract), executes headlessly, self-reviews results, records journal events, and produces…
Group several small GitHub issues into one durable, assignable batch — mint a parent "batch" epic issue, wire the small issues as native sub-issues (+ optional dependency order),…
Process multiple content pieces in parallel with queue management, priority scheduling, and progress tracking
Bazi chart calculation & reading (八字排盘与命理解读 / 四柱推命鑑定 / 사주팔자 감정). Triggers on: \"算八字\" \"bazi reading\" \"四柱推命\" \"사주 봐주세요\".
Execute the implementation planning workflow using the plan template to generate design artifacts. — from buildbetter-app/skills
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts. — from buildbetter-app/skills
Synchronise work with Beads (bd). Ensure current work is tracked, linked, and committed as evidence.