精选 Skills 索引（第 37 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。
- rss-writing-style
Use when revising an RSS (Robotics: Science and Systems) draft to meet the science-first bar — a falsifiable claim about robotics up front, evidence sized to claim scope, honest failure reporting, concision under an 8-page ceiling that rew…
- rt-desk-reject-risk
Use before submitting to score a manuscript against a specific venue's own desk-reject triggers and return a ranked, fixable risk report. Venue-conditional — it reads the target's documented triggers rather than applying generic advice. Ru…
- rt-ladder-ev
Use when choosing between submission sequences rather than between single venues — "should I try the top journal first, or start one rung down?", or when a tenure/job-market clock makes time-to-print the binding constraint. Costs a resubmi…
- rt-submission-readiness
Use when an author is one revision away from submission and needs a venue-parameterized go/no-go scorecard on the actual manuscript: fit, identification, robustness, exhibits, exposition, venue mechanics, data/code, and pre-empted objectio…
- rt-venue-integrity
Use before submitting to a venue this repository does not cover, one that arrived by email solicitation, or one whose indexing status matters for a tenure or degree requirement. Runs a source-by-source verification protocol — indexing, pub…
- rt-venue-reframe
Use after a rejection, or when switching target journals, to turn a manuscript framed for one venue into one framed for another. Produces a concrete reframing diff — introduction arc, contribution claim, evidence to add or cut, house style…
- ssc-fit-positioning
Use when judging whether a manuscript is on-target for 《中国社会科学》 (Social Sciences in China) before investing in revision — screening for 思想分量 over technical sophistication, big-question level, cross-disciplinary reach, and original theory —…
- asc-ad-hoc-distribution
Prepare, publish, resume, and verify private iOS release-testing installs with asc distribute. Use when distributing an IPA to registered devices outside TestFlight, reconciling ad hoc profiles, publishing through caller-owned S3-compatibl…
- asc-analytics-reports
Collect, download, and verify App Store Connect Analytics reports with asc. Use when users need to discover analytics report requests, select report instances by processing date or granularity, download every segment, or verify downloaded…
- ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks Style…
- ss-resolve
Compile a small, deterministic StyleSeed rule bundle for one agent, output grammar, surface adapter, domain, page type, and optional profile. Use before setup or build, when STYLESEED.md changes, when updating StyleSeed, or whenever an age…
- ss-studio
Turn a product brief and optional references into three distinct creative directions, a human-selected StyleSeed interaction plan, generated image/video asset jobs, a working UI prototype, and a verified prototype-first showcase reel. Use…
- styleseed
Route a StyleSeed request to exactly one first workflow after resolving the current artifact boundary. Use when the user asks generally for StyleSeed help rather than invoking one specific ss-* skill.
- goal-filter
Lock ONE primary marketing goal per brand, then judge any idea, draft, campaign, or plan against it — on-goal, partially, or off — with the fix that would make it pull harder. Use when: setting the quarter's focus, gut-checking whether wor…
- lead-magnet-ideas
Turn a content topic, campaign, or existing piece into specific lead-magnet ideas tied to the brand's real assets and expertise, each graded on lead-gen power × build effort. Use when: a piece needs an opt-in offer, a campaign needs a conv…
- signal-mine
Turn a raw dump of external material — news articles, social threads, community discussions, competitor moves, research, sales-call notes — into content angles mapped to the brand's pillars, with what didn't map listed and why. Use when: t…
- story-mine
Turn a real experience — a client win, a failed launch, a support ticket, a founder moment — into 3-5 distinct content angles, each with a format and a draft opening. Use when: something just happened worth telling, a case study feels too…
- video-packaging
Generate or critique video packaging — title + thumbnail-text pairs where each does a different job, tagged by discovery intent (search vs browse). Use when: a video needs its title and thumbnail decided, an existing video underperforms on…
- app-builder
(Preview) Builds and edits a model-driven Power Apps app from a natural-language intent — tables, columns, relationships, adaptive forms with sub-grids, views, Choice-column charts, generative page intents for overview/dashboard surfaces (…
- krea2-identity-edit
Swap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background — use for "put this jacket on her", "change his shirt", "clothes swap", "try on", "outfit transfer", "virtual try-on", "dress her in", "wear…
- panel-node-pack-sync
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (self_update, npm i -g comfyui-mcp, a new version in the ENVIRONMEN…
- report-bug
Self-heal + report bugs to make the ecosystem better. When you hit ANY defect in comfyui-mcp / the sidebar panel, OR in a third-party custom node / ComfyUI core, use this: diagnose it, attempt a local fix so the user can keep working, and…
- rgthree
Configure and author rgthree-comfy nodes — Fast Groups Bypasser/Muter (group toggles), Power Lora Loader, Context/Context Big, Seed, Any Switch. Use when a workflow contains rgthree nodes, when asked to add stage/section toggles or an A/B…
- wan-scail-replacement
SCAIL-2 in-video character replacement on WAN 2.1 — WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls
- maker-council
When you want multiple expert perspectives on a founder/operator question — a simulated personal board of advisors staffed by legendary founders, CEOs, and operators (Jason Fried, Elon Musk, Jeff Bezos, Jensen Huang, Bob Iger, Paul Graham,…
- Custom Engine e2e fixture
This directory is a minimal skill-up fixture that exercises the **Custom Engine** local and http transports end-to-end. It is consumed by `e2e/custom_engine_test.go`.
- ac-handoff-creator
Create handoff packages for session transitions. Use when ending sessions, preparing for continuation, saving session state, or creating resumable context.
- ac-knowledge-graph
Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.
- ac-master-controller
Master controller for complete autonomous operation. Use when starting full autonomous projects, managing end-to-end workflow, controlling autonomous lifecycle, or running complete implementations.
- ac-memory-manager
Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.
- ac-stop-hook-analyzer
Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation decisions, or implementing the Two-Claude pattern.
- Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance o…
- agent-assistant
You are an **Agent Assistant AI**. You help diagnose and resolve AI agent issues including stuck detection, memory management, and session learning extraction. You utilize the MUSUBI OpenHands-inspired modules to provide advanced agent ass…
- agent-builder
Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices for building specialized AI assistants.
- agent-context-generator
Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, README expectations, and convent…
- agent-cross-review
Structured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware feedback. Use when one agent reviews another's work, during handoffs, or when validating cross-cutting concerns.
- agent-error-coordinator
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across multi-agent systems with focus on minimiz…
- agent-factory
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
- agent-generator
Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions.
- agent-implementer
Implementation guidance for creating individual agents in the Arcanea system with proper structure, capabilities, and integration.