精选 Skills 索引（第 43 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- ln-71-system-design-baseline-builder
Creates a project baseline of architecture drivers and constraints. Use before design or planning; not for target design, plan review, implementation, or architecture audit.
- ln-72-current-architecture-documenter
Documents implemented current-state architecture from repository evidence. Use for onboarding or migration baselines; not for target design, audit verdicts, or code changes.
- ln-73-system-design-proposal-builder
Creates a decision-complete target system design from requirements and constraints. Use before implementation planning; not for requirements baselines, reviews, audits, or code changes.
- ln-74-architecture-decision-recorder
Records one architecture decision with context, alternatives, tradeoffs, and consequences. Use for a significant choice; not for broad design, audit, or implementation.
- ln-75-architecture-diagram-builder
Creates evidence-backed current or target architecture diagrams when the diagram is the primary deliverable. Not for UI design, architecture audit, or invented structure.
- ln-76-architecture-migration-planner
Plans a reversible architecture migration with compatibility, data movement, rollout, and rollback. Use for current-to-target transitions; not execution, generic planning, or delivery review.
- create-game-assets
Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset briefs.
- sponsio
Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails…
- 021-problem-framing
Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing po…
- 022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis…
- 023-assumption-analysis
Use when a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view n…
- 024-context-mapping
Use when a problem under exploration needs its surrounding system context identified before design begins — Existing systems, Integrations, Ownership, and External dependencies. This should trigger when an issue's Context Mapping point of…
- 025-quality-attribute-discovery
Use when a problem under exploration needs its quality attributes (non-functional requirements) identified and prioritized before architecture and design begin. This should trigger when an issue's Quality Attribute Discovery point of view…
- 058-design-bdd
Use when a Java change needs independent Behavior-Driven Development guidance from trusted behavior facts through concrete examples and observable scenarios, with focused clarification when behavior is pending or ambiguous. This should tri…
- 059-design-atdd
Use when reviewing whether an OpenSpec change's execution goal, acceptance criteria, and implementation or verification tasks are aligned. This should trigger for requests such as Review this OpenSpec change with ATDD; Check acceptance cri…
- discuss-change
Align on the shape of a change through an interview, then implement it. Escalates open product decisions and settles the implementation shape in conversation. Use when the user asks to \"discuss this change\", \"align on this change first\…
- explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to \"explain this\", \"what am I b…
- simplify-all
Run the code and documentation simplification passes together over one scope, launching every review agent concurrently before applying a single round of fixes. Use when the user asks to \"simplify all\", \"simplify everything\", \"simplif…
- adapt
Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested across viewports, or when the user says "…
- bolder
Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or "template-y", or when the user says "bolder", "more personality", "more…
- clarify
UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says "fix the labels", "improve error messages", or "…
- craft
One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "hazme un dashboard") an…
- critique
Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says "what's wrong with this UI", or needs a second opinion b…
- delight
Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says "mak…
- distill
Reduction pass — cuts content, structure, visuals, and dead code that doesn't answer a user question or drive an action, respecting CRAFT_LEVEL. Use when the UI feels cluttered, has too many CTAs, walls of text, or decorative noise, or whe…
- harden
Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for productio…
- polish
Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover states, and a signature detail — directly to code. Use when the surface is functionally complete but feels unfinished, or wh…
- quieter
Tone down visual noise — lowers variance and motion, simplifies layout and color weight, keeps hierarchy clear. Use when the UI feels loud, busy, or over-designed, or when the user says "quieter", "more restrained", "simpler", or "tone it…
- redesign
Redesign an existing site or app without losing what already works — audits the current surface first, classifies what to preserve (brand, IA, SEO, content), picks a refresh/reskin/rebuild scope, then modernizes deliberately. Use when the…
- typeset
Typography pass covering font choice, modular scale, tracking, leading, weight hierarchy, and micro-typography details. Use when fonts feel generic (default Inter with no reason), the scale is ad hoc, hierarchy is flat, or the user says "f…
- unhappy
State-first design pass — inventories and implements all non-happy states (loading, empty, error, partial, conflict, offline) before the happy path, and refactors impossible boolean state to proper state machines. Use when starting a new s…
- claude-code-reverse
对用户拥有或明确获授权的本机可执行文件、应用二进制和版本产物做只读静态逆向，包括 Claude Code 及其他 CLI、Mach-O、ELF、PE、Wasm 或打包应用。仅在用户明确要求“逆向、扒实现、查二进制字符串/符号/依赖、验证内部行为、比较两个版本”时使用；不要因普通提及软件而触发，也不要用于执行未知样本、绕过授权/计费、破解或再分发。
- ip-check
检测一个 IP 或住宅/机房代理节点的质量——注册库、地理库一致性、ASN/org、风控信誉、黑名单、住宅真实性、BGP 宣告、目标服务(Grok/Claude/ChatGPT)解锁与延迟三角测量。判定该 IP 能否安全用于 AI 服务(避免被地理库误判到别国导致区域锁)。当用户说"查这个 IP"、"这个节点在哪"、"这个代理能用吗"、"IP 质量检测"、"验收住宅 IP"、"为什么被判定在 X 国"、"check ip"、给出 socks5 代理凭证问归属或解锁时使用。
- multi-ai-research
Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), gener…
- npm-supply-chain-check
Detect known malicious npm package versions and install-time supply-chain indicators in repositories, lockfiles, and node_modules. Use when a user mentions an npm compromise, Shai-Hulud, the Keyv/cacheable incident, suspicious preinstall s…
- review-agent-harness
Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hook…
- sol-luna-router
Route coding work so GPT-5.6 Sol remains the commander and reviewer while a separate GPT-5.6 Luna Max Codex CLI session performs concrete implementation. Use when the user asks for Sol to direct, plan, supervise, or review work done by Lun…
- Frozen fixture — the REAL defect (self-review Phase 2 as it shipped at a36c79e).
Run the manuscript through each applicable category below. For each item, assess whether a reviewer would raise it as a Major or Minor comment.
- obsidian-paper-vault
Turn a folder of research PDFs into an Obsidian knowledge vault — consistently formatted literature notes with frontmatter, PDF embed links, and cross-referenced atomic concept notes. Use whenever the user wants PDFs converted to Obsidian…
- github-fix-issue
Analyze and fix GitHub issues in the current repository, including issue research, scoped implementation, and testing. Use when the user asks to fix, investigate, or work on a GitHub issue by number or URL. Create branches, commits, pushes…