В каталоге 183 730 навыков в 14 категориях.
Experimental workflow for reviewing configured repositories' pull requests. Use for manual or scheduled PR triage, appro...
Review configured PR queues under independent reply, approval, and merge gates. Use for PR triage.
Pipeline complet requirements → release
Use when a factory run must post its changes — check out the run branch, commit a step's allowlisted paths, push only th...
Security conventions for builds that touch sensitive data, regulated industries, or AI-generated code paths. Covers KMS...
Use to threat-model a feature, audit AI-generated code, design sensitive-data handling, or review auth/authz boundaries....
Use when configuring the factory tracker provider for a repo (first factory run, missing .adlc/issues-provider.yml), ver...
Configure portable Linear workflow settings in `.factory-kit/linear.json`, migrating legacy `.claude/linear.json` settin...
Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled f...
Complete authorized delivery work under explicit publish, merge, deployment, closure, and notification gates.
Dark Factory two-phase spec workflow (/factory-spec, /fs): create a main spec (spec.md) AND an attractor spec (attractor...
Phase MODEL - Génère specs + ADR + rules
Cross-build locked stack decisions and decision criteria for divergent choices. Read at the start of any new project. Co...
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog
How to reason about state in an interface codebase before writing any component. Interfaces are functions from state to...
Get comprehensive factory status - research progress, drill status, inventory, production overview. Use when checking pr...
Live Auto-Factory status audit — inspects real coding CLI conversations on jeff-ubuntu (/linux), captures tmux panes, au...
Show what the claude-factory is doing in this repo and what waits on the user. Use when the user asks "what is the facto...
Move the current branch's Linear issue to "In Review"
Testing conventions across builds. Vitest + Playwright as the locked stack; tests co-located in `__tests__` next to the...
Use when the user asks for their active worklist — open PRs with next actionable move, merged work not yet closed, takab...
생성된 컴포넌트 검증 및 품질 보증 스킬
How we know the software the factory produces is correct, and how we know the kit's own conventions are followed. Define...
Use to design the verification strategy for a change — what would prove it correct, given its blast radius, and what is...
Communication voice for Claude Code — senior software architect, first-principles framing, crisp English. Governs how Cl...
Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled...
Monitor authorized delivery work for verified stalls. Use for policy-gated scheduled follow-through.
Factoryが生成する日本語の文章(要件定義書、監査レポートと改善提案、PR本文、レビューの指摘、修正の返信、Issue化の提案、コミットメッセージ)を書くときに使う。すべての生成フローのheadless Claude実行に注入され、成果...
Read-only consistency check of any live site, on any stack. FACTS: one approved facts list (value, source, owner); scrip...
Restate content as a flat list of atomic facts in the style of av/facts fact sheets. Use when the user says "just facts"...
Ensure the library has collected all publications by faculty in a department - a collection completeness requirement
Route a learning request to the smallest useful set of Academy professors or instructors based on subject, level, and go...
Combine teaching from multiple Academy specialists into one coherent explanation or learning plan while preserving domai...
Never fade a `backdrop-filter` layer with `opacity` or a uniform-alpha `mask` — animate its geometry, or the blur radius...
Builds a WebGL fragment-shader effect in which a word in a bitmap pixel face trails away into light like a long exposure...
Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows w...
Build Fae's house scenes (3D low-poly) consistent with Cloverhollow style lock
Generates a complete FAERS comparative pharmacovigilance study design from a user-provided drug set, comparator logic, a...
Query the FDA Adverse Event Reporting System (FAERS) via openFDA API. Use whenever the user asks about adverse drug reac...
Get your project to 100% ✪ AI-readiness, fast — the AI auto-detects your stack and only asks for what it can't know (you...
Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scori...
Guided interview to Gold Code (100% AI-Readiness). Use when helping users improve their .faf file through questions. Lev...
Done-for-you .faf generator. One-click AI context for any project - new, legacy, or famous. Auto-detects stack, scores r...
查询法海风控企业司法数据。通过法海风控 API 查询企业司法风险数据列表(裁判文书、执行公告、失信被执行人、司法拍卖等)并获取案件详情。适用于企业背调、司法风险评估、风控审查等场景。触发词:法海、法海风控、企业司法数据、裁判文书查询、执行公...
Check preconditions at the start of functions and fail immediately if they aren't met Use when enforcing code quality st...
Use when the user needs to restore service from a specific known failure by applying a single prescribed recovery operat...
Protect servers from brute force attacks with Fail2Ban. Use when a user asks to block repeated failed login attempts, pr...
识别突破失败、冲高回落与关键位失守后的撤退信号,并给出减仓、止损与重新观察的动作顺序。适用于突破交易纠错、假突破处理与强势股失速后的快速修正场景。
Deterministically fail through the cli-tool adapter.
Use this skill when you need evidence-bounded failover-testing analysis and validation preparation; triggers include 故障切...
Activate emergency failsafe chassis when primary systems fail.
Execute emergency protocol reset when critical system integrity is compromised.
Conditions that fail a /create-module or /add-operation task on contact. Use when scoping work, reviewing a PR, or refus...
Puts a number on what the failing placements consumed, in impressions and in money, so the cost of the problem can be we...
Immediate failure conditions that stop work
Terminate on unrecoverable external blockers and report precise error details.
当遭遇挫折、失败或结果不如预期时,用于将负面经验转化为成长燃料
Hata senaryolarını önceden planlamayı ve kodda hataları düzgün yönetmeyi öğretir.
Read the wreckage before rebuilding. Use for incident post-mortems, "what happens when everything goes wrong at once?",...
This skill should be used when handling failures in go-class command flows — Soyo blocking with NEEDS_CHANGES / BLOCKED,...
This skill should be used when the user asks to "log a failure", "remember this mistake", "add to failure log", "what mi...
Identify potential failure modes and assess system vulnerabilities for pilot workflows and integrations. Use when antici...
Systematically enumerate how code can break — boundaries, concurrency, partial failure, malicious input, time, resource...
Comprehensive guide to identifying, analyzing, and documenting failure modes in distributed systems
Analyze likely cascade paths and propagation semantics in DSDS architectures. Use when estimating blast radius, diagnosi...
Recovery protocols for stuck agents, context exhaustion, build failures, and confusion. Use when agent is looping, respo...
Failure simulator on code level: inventories every external touchpoint (HTTP clients, DB access, filesystem, queues, cac...
当需要在多个领域积累独特竞争优势,避免单一技能风险时
Accessibility: WCAG compliance, assistive technologies, inclusive design.
Communication: User's language. Docs/code: English.
API development: REST, GraphQL, OpenAPI, versioning, auth, rate limiting.
Build Production-Ready APIs with Modern Best Practices (2025-2026)
Comprehensive guide for text-to-speech, speech-to-text, voice cloning, and voice agent development
Automation & tooling specialist: browser automation, CI/CD, monorepo, performance testing, feature flags. 23 methodologi...
BA Core: Planning, elicitation, requirements lifecycle, strategy analysis, solution evaluation. 21 methodologies.
BA Modeling: Use cases, user stories, process models (BPMN), data models, decision tables, interfaces, acceptance criter...
Backend orchestrator: coordinates systems (Go, Rust, DB) and enterprise (Java, C#, PHP, Ruby).
Enterprise backends: Java, C#, PHP, Ruby.
Multi-language backend patterns for production-grade applications.
Systems backends: Go, Rust, databases, caching.
SDD Backlog Grooming - prioritize features, refine specs, create designs and tasks
BA Domain Skill: IIBA BABOK v3 orchestrator. 6 Knowledge Areas (Planning, Elicitation, Analysis, Traceability, Evaluatio...
CI/CD: GitHub Actions, GitLab CI, Jenkins, ArgoCD, GitOps, monitoring.
Complete Guide to Anthropic Claude API (2025-2026)
Claude Code: skills, agents, hooks, commands, MCP servers, IDE integrations.
Code quality specialist: architecture patterns, refactoring, code review, development practices. 23 methodologies.
Communication: stakeholder dialogue, Mom Test, conflict resolution, feedback, storytelling.
Pre-execution confidence assessment. Validates readiness before spec, design, or implementation. Prevents wrong-directio...
Content marketing: strategy, copywriting, SEO, email campaigns, social media.
Conversion optimization: landing pages, CRO, funnels, PLG, onboarding flows.
Universal Django coding guidelines and architecture patterns. Use when writing Django code, creating models, services, A...
Creates or updates CLAUDE.md documentation for any module/folder. Use when user asks to create docs, document module, ad...
UI design: brainstorming, prototyping, Storybook. Triggers: ui design, component library.
DevOps Engineer role: Docker, Kubernetes, Terraform, AWS/GCP/Azure, CI/CD (GitHub Actions, GitLab CI), infrastructure as...
DevTools orchestrator: code quality and automation.
Execute all SDD tasks for a feature sequentially. Handles task ordering, continues on minor failures, stops on critical...
You are an expert on text embeddings - numerical vector representations of text that capture semantic meaning. Help user...
Execute specific SDD task via faion-task-executor-agent agent. Loads context, runs agent, moves task through lifecycle.
SDD feature executor: sequential task execution with quality gates. Runs tests/coverage validation after each task, perf...
Customize Language Models for Domain-Specific Tasks (2025-2026)