Skills worth trusting.
Agent skills from Anthropic, OpenAI, skills.sh, ClawHub, SkillsMP and other reputable sources. Savant assesses them for security risks and evaluates model-generated test cases using independent scoring. Workspaces import any skill into their own repositories through a reviewed pull request. Every listing on each hub is enumerated; packages are fetched, scanned and evaluated most-popular first as daily capacity allows.
gsap
Expert guidelines for building high-performance animations with GSAP (GreenSock Animation Platform)
surrealql
Generate and modify SurrealQL queries to interact with SurrealDB databases. This includes creating and retrieving records, designing and managing schemas, establishing and querying graph relationships, performing live (real-time) queries, and leveraging all unique SurrealQL features for advanced database workflows. Use this skill whenever users need to write, adapt, or troubleshoot SurrealQL statements.
seed-design
SEED Design을 사용하는 프로젝트의 공식 문서·CLI 안내나 설치·업그레이드 진단이 필요할 때 사용한다.
error-analysis
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.
cmux-workspace
Work inside the current cmux workspace and terminal. Use for cmux workspace, current workspace, caller surface, panes, surfaces, tagged reloads, socket targeting, and non-interfering cmux automation.
firetiger
Use when the user mentions Firetiger or wants to work with their observability data — setting up Firetiger, instrumenting an app with OpenTelemetry, querying traces/logs/metrics with SQL, investigating an incident, monitoring a PR or deployment, or creating a monitoring agent. Always use this skill when the user says "Firetiger", even for simple asks — it routes to the specialized skill that carries the critical gotchas (Basic-auth ingest, DuckDB SQL over per-service tables, the @firetiger comment flow) that prevent common mistakes.
fusion-issue-author-user-story
DEPRECATED: Use fusion-issue-authoring instead. Previously: Draft and update user-story issues with role-action-value framing and workflow scenarios.
gsap-greensock
Use when implementing Disney's 12 animation principles with GSAP (GreenSock Animation Platform)
revenuecat-migrate
Migrate to RevenueCat from raw StoreKit or Google Play Billing, or upgrade the RevenueCat SDK across a major version. Use when the user says migrate to RevenueCat, switch from StoreKit to RC, upgrade RevenueCat SDK, from v4 to v5, observer mode, RevenueCat major version upgrade, or already have in app purchases and want to add RevenueCat on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.
write-docs
Write, author, edit, and format GitBook documentation pages in Git-synced repos, IDEs, or any text editor. Use whenever a task involves creating or editing a GitBook markdown page, writing or updating a README.md or SUMMARY.md, inserting a hint, tab, stepper, card, or other GitBook block, configuring page frontmatter or layout options, setting up variables or expressions, or formatting content for GitBook outside the GitBook UI.
ads-setup
Set up a paid-media client, brand, account, data-source, privacy, and mutation-guardrail profile for Claude Ads. Use for onboarding, initial configuration, brand DNA, API tokens or credential profiles, environment-variable or keychain setup, connecting exports or read adapters, safe native or verified-local installation, curl-pipe-bash install requests, declaring KPIs, or preparing a new advertising project.
chief-of-staff
C-suite orchestration layer. Routes founder questions to the right advisor role(s), triggers multi-role board meetings for complex decisions, synthesizes outputs, and tracks decisions. Every C-suite interaction starts here. Loads company context automatically. Use when a founder question needs routing to the right advisor — e.g. 'should we raise now or cut burn?' — or when a multi-domain decision needs a board meeting convened.
syncfusion-react-gantt-chart
Implement, configure, and customize the Syncfusion React Gantt Chart component. Use this when building project scheduling applications with task timelines, dependencies, resource management, and calendar-driven scheduling. Covers GanttComponent setup, task constraints, taskbar customization, filtering, sorting, Excel/PDF export, critical path analysis, milestones, predecessors, resource view, baseline tracking, and task calendar configuration.
plan-writing
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
device-interaction
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
experience-cms-content-generate
Creates, edits, and publishes Salesforce CMS content of any kind — any domain, any topic. Single and bulk: create many in parallel, edit one or many, publish all or a subset. Use this skill ANY TIME a user asks to create, generate, write, draft, author, or add content, OR to update, edit, or revise a content record, OR to publish it, OR to delete/remove a content record. Triggers like "create a <thing> about X", "create 5 <things>", "update content <id>", "publish content <id>", "publish the record <id>", "make <id> live", "delete content <id>" — where <thing> is any user-named content type. Activates FIRST whenever content authoring, editing, publishing, or deletion is mentioned, regardless of subject. Handles the full workflow: finding the content type, resolving the workspace, creating content, editing or publishing it — including a record identified by its variantId. Does not apply to defining a content type / schema (use experience-cms-content-type-generate), cloning, versioning, workspaces, or media.
seedance-submitter
Use when preparing, submitting, polling, or debugging Seedance 2.0 or 2.5 video generation jobs from prompts, opening/ending frames, multimodal references, storyboard images, UGC scripts, or voiceover copy. Use for selecting an unambiguous scene endpoint, uploading references, composing submit flags, submitting through PostPlus Cloud, polling predictions, and handing off local render paths.
foundation-okr-writer
Drafts, reviews, rewrites, and coaches outcome-based OKR sets across team, department, product, or company scopes. Supports five entry modes (Guided default, One-Shot via --oneshot, Sustained Coach, Audit Only, Rewrite). Diagnoses empowered-team context and adjusts framing; refuses to fabricate baselines or targets; refuses to use OKR scores for compensation; reframes feature-delivery KRs into outcome KRs. Use when planning quarterly OKRs, translating strategy into team outcomes, reviewing draft OKRs for quality, or converting roadmap-as-OKR drafts into proper OKR sets.
discover-stakeholder-summary
Maps the people and groups with a stake in a project, documenting their needs, concerns, influence, and engagement approach. Use at project kickoff, when taking over from another PM, or when resistance signals misalignment. For the update you send to those stakeholders, use foundation-stakeholder-update instead; this skill maps them, that one talks to them.
hig-platforms
Apple Human Interface Guidelines for platform-specific design. Use this skill when the user asks about "designing for iOS", "iPad app design", "macOS design", "tvOS", "visionOS", "watchOS", "Apple platform", "which platform", platform differences, platform-specific conventions, or multi-platform app design. Also use when the user says "should I design differently for iPad vs iPhone", "how does my app work on visionOS", "what's different about macOS apps", "porting my app to another platform", "universal app design", or "what input methods does this platform use". Cross-references: hig-foundations for shared design foundations, hig-patterns for interaction patterns, hig-components-layout for navigation structures, hig-components-content for content display.
cook
Implement an approved spec or focused task through stale-safe source edits. Use this skill when the user says "implement this", "cook this spec", or "fix this bug". Use it for `/cook .cheese/specs/<slug>.md`. Also use it when the user says "go" with clear acceptance criteria. Run it alone for an unambiguous task. Use `--prototype` when the user says "prototype this", "go prototype it", or "spike this out" and wants to refine the result round by round. A spec helps but is not required. Do not use it for fuzzy planning (`/mold`). Do not use it for no-write discussion (`/culture`) or review-only work (`/age`).
neo4j-aura-agent-skill
Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, invoking agents with natural language queries, or generating evaluation datasets (max 50 questions) for the Aura Agent evaluation feature. Covers OAuth2 auth, organization/project scoping, tool parameter schemas, and InvokeAgentResponse format. Does NOT cover AuraDB instance provisioning — use neo4j-aura-provisioning-skill. Does NOT cover vector index creation — use neo4j-vector-index-skill.
attack-path-analysis
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
frontend-security-coder
Expert in secure frontend coding practices specializing in XSS prevention, output sanitization, and client-side security patterns.
healthkit
API reference: HealthKit. Query for HKHealthStore, HKQuantitySample, workouts, health data read/write.
oura
Connect to your Oura Ring and view health data. Use when the user mentions Oura, sleep score, readiness score, activity score, step count, steps, heart rate, HRV, SpO2, blood oxygen, stress data, workout tracking, recovery cost, workout recovery, or asks about their health metrics, sleep quality, recovery, or ring data. Also trigger on phrases like "how did I sleep", "show my health data", "check my ring", "what's my readiness", "how many steps", "how does pickleball affect my recovery", "should I work out today", "if I play tomorrow", "recovery time", or any question about biometric, wellness, or wearable ring data.
app-store-screenshots-generator
Generate production-ready App Store screenshots for iOS apps using AI agents, Next.js, and html-to-image
domain-expert-configuration
Settings for experts who are not developers — domain language, sane defaults, grouping by professional concept. Use when designing settings panels, solver configuration or constraint editors.
tanstack-router
Build type-safe, file-based React routing with TanStack Router. Supports client-side navigation, route loaders, and TanStack Query integration. Prevents 20 documented errors including validation structure loss, param parsing bugs, and SSR streaming crashes. Use when implementing file-based routing patterns, building SPAs with TypeScript routing, or troubleshooting devtools dependency errors, type safety issues, Vite bundling problems, or Docker deployment issues.
reflex-process-management
Manage Reflex application processes: compile to test, run the server in production mode, reload a running app by finding and restarting the app process, and manage logs for debugging. Use when the user wants to test, run, restart, or reload a Reflex app, when troubleshooting a running Reflex server, or when investigating errors.
malware-distribution-awareness
Recognize and report malicious software distribution repositories masquerading as legitimate security tools
douban-skill
Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files via Frodo API. Supports full export (all history) and RSS incremental sync (recent items). Use when the user wants to export Douban reading/watching/listening/gaming history, back up their Douban data, set up incremental sync, or mentions 豆瓣/douban collections. Triggers on: 豆瓣, douban, 读书记录, 观影记录, 书影音, 导出豆瓣.
ios-dev
Start here for any iOS or SwiftUI task. Coordinates best-practice guides, correctness checks, and full Apple API references. Use before navigating to other Apple skills — for building, reviewing, refactoring, or debugging iOS apps.
metabase-data-app-routing
Add client-side routing (multiple pages) to an existing Metabase data-app project using the host-provided `DataAppRouter`, `DataAppLink`, and `useDataAppLocation` primitives. Use when the user has an existing data-app project and wants more than one page.
stitch-design-taste
Classic skill for Google Stitch, opt-in: it runs only when called by name. Writes an agent-friendly DESIGN.md with strict type, colour and layout rules.
detailed-pr-description
Assess test coverage or draft/update GitHub PR descriptions with self-contained context, risks, follow-up work, focused code references, and validation results.
user-story-writing
Write effective user stories that capture requirements from the user's perspective. Create clear stories with detailed acceptance criteria to guide development and define done.
capgo-cli-usage
Guides the agent through the Capgo CLI command surface and routes requests to more specific Capgo skills. Use when the user asks generally about the Capgo CLI, app setup, diagnostics, OTA operations, native builds, or organization commands. Do not use when a more specific Capgo skill already clearly matches the request.
hig-components-controls
Apple HIG guidance for selection and input controls including pickers, toggles, sliders, steppers, segmented controls, combo boxes, text fields, text views, labels, token fields, virtual keyboards, rating indicators, and gauges. Use this skill when the user says "picker or segmented control," "how should my form look," "what keyboard type should I use," "toggle vs checkbox," or asks about picker design, toggle, switch, slider, stepper, text field, text input, segmented control, combo box, label, token field, virtual keyboard, rating indicator, gauge, form design, input validation, or control state management. Cross-references: hig-components-menus, hig-components-dialogs, hig-components-search.
develop-spike-summary
Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommendation so the team does not re-litigate the exploration. Use once a time-boxed investigation has concluded. For the architecture decision the spike informs, use develop-adr instead; for research-based exploration, use discover-interview-synthesis.
neo4j-snowflake-graph-analytics-skill
Run Neo4j Graph Analytics algorithms (PageRank, Louvain, WCC, Dijkstra, KNN, Node2Vec, FastRP, GraphSAGE) directly inside Snowflake without moving data. Use when running graph algorithms against Snowflake tables via the Neo4j Snowflake Native App ("GDS Snowflake", "graph algorithms in Snowflake", "Neo4j Graph Analytics"). Covers the explore → prepare projection views → project-compute-write flow, the strict view/column type rules the graph engine requires, exact SQL CALL syntax, and privilege setup in both modes — app-identity grants and execute-as-user / per-user PAT auth (programmatic access token, set_enable_custom_credentials, register_user_role, caller grants). Does NOT cover Cypher or Neo4j DBMS queries — use neo4j-cypher-skill. Does NOT cover Aura Graph Analytics — use neo4j-aura-graph-analytics-skill. Does NOT cover self-managed GDS — use neo4j-gds-skill.
tribev2-brain-encoding
Use TRIBE v2, Meta's multimodal foundation model for predicting fMRI brain responses to video, audio, and text stimuli
capacitor-plugin-upgrades
Guides the agent through upgrading a Capacitor plugin to a newer major version. Covers dependency alignment, native platform changes, example app verification, and multi-version jumps. Do not use for app project upgrades or non-Capacitor plugin frameworks.
threejs-r3f
Build or fix React Three Fiber scenes, Drei helpers, Suspense loading, events, and React lifecycle integration.
webflow-mcp:site-activity
Query and summarize site activity logs for a Webflow enterprise site. Surfaces recent changes, identifies who made them, and generates human-readable activity reports. Use for site monitoring, change tracking, publish preparation, or weekly activity summaries. Enterprise plans only.
diversification
Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification. Use when the user asks about portfolio variance, correlation effects, the efficient frontier, minimum variance portfolios, diversification ratios, or factor diversification. Also trigger when users mention 'don't put all eggs in one basket', 'how many stocks do I need', 'correlation breakdown in a crisis', 'are my holdings really diversified', 'risk contributions', or ask why diversification fails during market crashes.
lean-startup
Applies Eric Ries's Lean Startup methodology for building products under extreme uncertainty. Use when iterating toward product/market fit, designing MVPs, deciding whether to pivot or persevere, setting up actionable metrics, or accelerating the Build-Measure-Learn loop. Triggers include 'how do we test this idea fast', 'what should our MVP look like', 'our metrics look good but we're not growing', 'should we pivot', 'we're building features no one uses', 'how do we measure validated learning', 'vanity metrics vs real metrics', 'how to do innovation accounting'. NOT for companies with proven product/market fit scaling a known playbook (use Crossing the Chasm), not for determining Market Type (use Four Steps), not for sales methodology (use SPIN Selling), not for pricing strategy (use Monetizing Innovation).
sales-engineer
Analyzes RFP/RFI responses for coverage gaps, builds competitive feature comparison matrices, and plans proof-of-concept (POC) engagements for pre-sales engineering. Use when responding to RFPs, bids, or proposal requests; comparing product features against competitors; planning or scoring a customer POC or sales demo; preparing a technical proposal; or performing win/loss competitor analysis. Handles tasks described as 'RFP response', 'bid response', 'proposal response', 'competitor comparison', 'feature matrix', 'POC planning', 'sales demo prep', or 'pre-sales engineering'.