Generate TODO-Today queue from BACKLOG Ready items. Use when populating the execution queue, starting a new batch of work, or converting Ready backlog items into actionable queue…
Discover and document existing systems with 10-phase brownfield analysis and drift detection workflows.
Executes an approved agentmaster-plan plan and chains straight into the full code review. Use when the user has accepted a plan and wants it built — "execute the plan", "run the…
Cost-tiered adversarial code review. Use after implementer subagents complete a agentmaster-plan plan (the plan's review gate invokes this), or whenever the user wants a rigorous…
Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files.
Discover, search, and manage Claude Code agents. Use when you want to find available agents, list installed agents, or refresh the agent catalog.
Aggiorna STATE.json di TITANIUM_OS con un nuovo milestone verificato. Usa dopo aver completato un pezzo fisico, un feature del software, o una fase del progetto.
应收账款账龄分析 — 生成全公司应收账款账龄分析报告，识别高风险逾期客户。 适用情形：每周固定时间（如周一）执行，从 ERP 获取应收账款数据， 按账龄/客户/信用等级多维度分析，输出逾期清单和催款优先级。 核心：账龄分层 + 逾期天数计算 + 坏账概率评估 + TOP N 高风险客户。
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.
Add a note to a specific idea. Notes are lightweight observations, feature ideas, considerations, proposals, or risks that should be captured without triggering a debate session.
Lock minimal API contracts for stub-mode systems in the active epic. Writes Contracts section in EPIC.md and pre-registers stubs in stubs.md.
Complete launch readiness validation covering every department: code, content, store, marketing, community, infrastructure, legal, and go/no-go sign-offs.
Render rich, interactive UIs in the browser. Use when displaying data tables, lists, or any structured data with more than 3 items.
用于【都市悬疑】题材下的去 AI 味重写。作为题材包装层、兼容入口与路由层，负责保留都市悬疑标准入口名、补充程序 / 证据口径、数值双轨与冷压迫来源保护边界，并明确要求加载并使用 `通用-去AI味重写`。关键词：都市悬疑去AI味、模板腔、证据口径、冷压迫。
用于【AI科幻】题材下的 My Fiction 平台输出任务。作为题材包装层、兼容入口与路由层，负责保留AI科幻入口、补充关系黏性与调查驱动边界，并明确要求优先强制加载并使用 `通用-输出My Fiction版`。关键词：AI科幻My Fiction版、英文追更、关系张力。
用于【AI科幻】题材下的去 AI 味重写。作为题材包装层、兼容入口与路由层，负责保留AI科幻标准入口名、补充程序 / 数据痕迹径、数值双轨与冷压迫来源保护边界，并明确要求优先强制加载并使用 `通用-去AI味重写`。关键词：AI科幻去AI味、模板腔、数据痕迹径、冷压迫。
Stage and commit changes using the team's standard commit message format. Only invoke when the user explicitly types /ai-assist-git-commit.
Generate a plain-language project overview, comprehensive engineer status update, and surgical documentation enhancement. Reads project docs, specs, dependencies, and git history.
Runs the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes.
Automates GPTZero AI detection pipeline for a given file. OPT-IN and external: it uploads the draft text to a third-party site (gptzero.me) and requires the user's GPTZero login,…
AI-driven health analysis system including comprehensive analysis, risk prediction, intelligent Q&A, and report generation.
KI-System-Inventar nach EU-KI-VO (VO 2024/1689) – erfasst je KI-System Rolle (Anbieter, Betreiber, Einführer, Händler, Bevollmächtigter, Produkthersteller) und Risikoklas — from…
Use when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumulated learnings to context files.
Access Travis Gertz's personal knowledge graph with ~5,850 entities tracking projects, people, finances, and relationships.
Maintenance skill for the ai-mentor plugin. Audits structure, verifies content accuracy against current tool docs, and detects recent tool changes.
Use when optimizing prompts, skill descriptions, or agent instructions for clarity, specificity, and behavioral effectiveness. — from majiayu000/claude-skill-registry
Command-invoked AI-SDLC readiness audit. Runs the deterministic scoring engine across all dimensions in one pass and compiles a report.
Utility: Detect and remove AI-generated code slop. Finds unnecessary comments, over-engineering, verbose error handling, premature abstractions. Solo operation, no team needed.
Tune typical shapes from scratch (baseline .co kernels) for >=150 iterations each. Covers shapes far from the reference that need full optimization.
Review recorded AI coding-tool usage and recommend concrete optimizations. Reads real token, cost, session and harness-configuration data from the AI Insights MCP server, then…
KI-Folgenabschätzung (FRIA nach Art. 27 KI-VO + DSFA nach Art. 35 DSGVO) erstellen – strukturierte Aufnahme, Risikoanalyse, Regulierungsklassifizierung nach KI-VO und DSG — from…
Direct-entry Lite-path shortcut (Author new tests (unit/integration/e2e); each test traces to an acceptance criterion; framework inferred from the KB.) -- skips the aid-describe…
Direct-entry Lite-path shortcut (Remove or delete a code artifact, endpoint, dependency, feature, or dead code; update dependents, tests, and docs.) -- skips the aid-describe…
Direct-entry Lite-path shortcut (Alias of aid-change-api.) -- skips the aid-describe interview/triage.
AI-DLC（AI-Driven Development Lifecycle）の統合オーケストレーター。 フェーズ（inception/construction/operations）の開始・継続、セットアップ、エクスプレスモード、フィードバック送信を統一的に実行する。 Use when the user says "インセプション進めて", "start…
Analyze project and generate or enhance build automation file (Makefile, Taskfile.yml, Justfile, Magefile.go).
Create conventional commit messages by analyzing staged changes. Generates semantic commit messages following the Conventional Commits specification.
Generate and maintain project documentation. Creates a lean README as a landing page with detailed docs pages split by topic in the configured docs directory.
Self-improve AI Factory skills based on project context, accumulated patches, and codebase patterns. Analyzes what went wrong, what works, and enhances skills to prevent future…
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements.
Fix a specific bug or problem in the codebase. Supports two modes - immediate fix or plan-first. Without arguments executes existing FIX_PLAN.md.
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses.
Execute implementation tasks from the current plan. Works through tasks sequentially, marks completion, and preserves progress for continuation across sessions.
Refine and enhance an existing implementation plan with a second iteration. Re-analyzes the codebase, checks for gaps, missing tasks, wrong dependencies, and improves the plan…
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are…
Plan implementation for a feature or task. Two modes — fast (single quick plan) or full (richer plan with optional git branch/worktree flow).
Create knowledge references from URLs, documents, or files for use by AI agents. Fetch, process, and store structured references in the configured references directory (default:…
Add project-specific rules and conventions to the configured RULES.md artifact. Each invocation appends new rules.
Run a standalone read-only rules compliance gate against changed files or a git ref. Use when you need a dedicated project-rules check without a full review or verify pass.
Verify completed implementation against the plan. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met.
Generate Airwallex Drop-in Element integration code. Use when user mentions Drop-in, dropIn element, embedded payment UI, createElement('dropIn'), multi-method checkout, Apple…
Generate Airwallex Hosted Payment Page (HPP) integration code. Use when user mentions HPP, hosted payment page, redirectToCheckout, PaymentIntent, guest checkout, save card,…
Generate Airwallex Connected Account KYC onboarding integration code. Use when user mentions KYC, embedded KYC element, createElement('kyc'), hosted KYC flow, connected account…
Generate Airwallex Split Card Element integration code. Use when user mentions Split Card, cardNumber element, expiry/cvc element, individual card inputs, custom card form, 拆分卡元素,…
Генерация 5 привлекательных B2B-сегментов по методологии Advanced Jobs To Be Done. Используй когда пользователь хочет найти сегменты для B2B-продукта, провести сегментацию или…
Генерация 5 привлекательных B2C-сегментов по методологии Advanced Jobs To Be Done. Используй когда пользователь хочет найти сегменты для B2C-продукта, провести сегментацию…
Генерация графа работ ниже уровнем к Core Job для конкретного сегмента по методологии Advanced Jobs To Be Done.
Генерация текста лендинга для продукта на основе сегмента и его работ по методологии Advanced Jobs To Be Done.
Генерация Top-5 рискованных предположений (RAT — Risky Assumption Test) для продукта по методологии Advanced Jobs To Be Done.
Генерация способов рекрута респондентов для AJTBD-исследования. Используй когда пользователь хочет найти респондентов для интервью, организовать рекрут для исследования или…