SkillsCat
An open platform for discovering, sharing, and installing AI Agent Skills.
Browse 74,630 community skills to extend agent capabilities.
Trending Skills
View allhyperframes-cli
by heygen-com
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
pr-comments
by ccch1mneyyy
Read and triage existing pull request review comments, or address them when requested. Use for PR comment requests or /pr-comments; use review to inspect code without existing reviewer feedback.
audit
by ccch1mneyyy
Audit the repository or a broad subsystem for security, correctness, and maintainability risks. Use for audit requests or /audit; use review for a specific change and vuln-check for a security-only assessment.
email-shortlist
by tin-computer
Build a bounded outreach shortlist from connected Gmail and Calendar evidence.
phpcheck-server
by openai
Check PHP2Shell patch status with local or server access.
small-reviewable-site-health-fix
by tin-computer
Diagnose and propose one low-risk mechanical website improvement as a reviewable PR.
key-state-attribute
by sno-ai
Choose one offered state attribute for a stored statement about a named thing.
resolve-relative-time
by sno-ai
Understand temporal meaning in context without performing calendar arithmetic.
scenario-maya-pipeline-scripting
by scenario-labs
"Use when writing or fixing Maya pipeline code in Python: mayapy batch jobs over many scenes, validating and auto-fixing scenes, FBX export for Unreal or Unity (static, skeletal, animation clips, Game Exporter), Alembic or GPU caches, USD export, stages and layers, references and namespaces, PySide6 tool windows, OpenMaya 2.0 plug-ins, or slow playback. Also when an FBX lands with wrong scale, normals, tangents or extra takes, a USD export has one frame or smoothed meshes, or one bad file kills a batch."
phpcheck-url
by openai
Check the advertised PHP version from a URL or hostname.
figma
by heygen-com
Bring Figma into a HyperFrames video - rendered assets, brand tokens, components, storyboard frames as reconstructed motion (frames read as states, not slides), shaders and connector-assisted motion. Use when the person pastes a figma.com link or asks to use a Figma design, frame, logo or brand.
hallmark
by Nutlope
"Design skill for websites and new pages that look designed, not generated. Use when the user asks to build or design something new, or names Hallmark. Never use it on an existing design unless the user names Hallmark, as in /hallmark redesign <path>."
Recently Added
View allautocad-dwg-redraw
by pengxiaoan
Rebuild and validate AutoCAD drawings from a source DWG, a PDF-derived intermediate DWG, or a raster reference image paired with authoritative dimensions and drawing requirements. Use when Codex must profile and exactly reproduce a .dwg, convert a PDF into a validated intermediate DWG before exact redraw, or convert an image plus metrics into parameter-driven AutoLISP/AutoCAD geometry and optional 3D solids.
refinery-project
by skanehira1126
Knowledge Refineryの導入・設定変更・状態確認・診断、仕組みの説明に使う。ナレッジ検索・記録やvault内の品質監査は対象外。
refinery-memory
by skanehira1126
Knowledge Refineryのexperienceから再利用できる原則を抽出し、project・shared memoryを提案・記録・改善するときに使う。検索だけ、または単一試行の記録はrefinery-experienceを使う。
refinery-maintenance
by skanehira1126
Knowledge Refinery vaultの定期棚卸し、品質監査、指定したナレッジ・metadata・taxonomyの修復に使う。通常の開発レビューや単発の保存確認、repo設定診断は対象外。
refinery-handoff
by skanehira1126
特定の作業の引き継ぎを保存し、新しいチャットで再開・整理する。明示呼び出し専用。
refinery-experience
by skanehira1126
Knowledge Refineryのナレッジ検索、または再利用できる試行・比較・失敗のexperience記録に使う。原則の抽出・改善はrefinery-memory、設定操作はrefinery-projectを使う。
upgrade
by stayfixed
Upgrade the stayfixed scaffold in a repository after a plugin update, keeping every hand edit. Use when the user asks to upgrade, update or refresh stayfixed's files, or after the plugin version changed.
uninstall
by stayfixed
Remove stayfixed's scaffold from a repository, leaving hand-edited files in place and listed. Use when the user asks to uninstall or remove stayfixed from a project.
sweep-defect-class
by stayfixed
Turn one defect into its class and close every instance — enumerate the shape across the tree, prove which tests take the branch, fix or file each hit, and declare the mutation that reddens each fix. Use after a bug fix whose shape could recur.
setup
by stayfixed
Configure the machine for stayfixed — the preset, the personal parameters, and the per-repository git hook. Use on a new computer, when the user asks to install stayfixed's defaults, or when a commit-message hook is wanted.
run-correctness-audit
by stayfixed
Audit a repository for correctness defects by component — candidates first, then each one executed to a verdict, then the survivors filed. Use before a release, after a large merge, or when the owner asks whether the code does what its documents say.
review-plan-three-lenses
by stayfixed
Review an implementation plan through three lenses before it is executed — whether each task's premise holds in the tree, whether each assertion can fail, and whether each trust ruling names its anchor. Use on any plan longer than one task, before the first dispatch.
Top Rated
View allrea-analysis-optimization
by morluto
Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.
reverse-engineer-anything
by morluto
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.
rea-changelog-update
by morluto
Prepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.
rea-ci-tests-audit
by morluto
Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.
rea-tool-design
by morluto
Design or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.
api-design
by affaan-m
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when designing or reviewing REST endpoints, resource names, status codes, pagination, or versioning.
mcp-server-patterns
by affaan-m
Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.
unified-memory
by affaan-m
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
backend-patterns
by affaan-m
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when building or reviewing Node.js, Express, or Next.js API routes and their data access.
homelab-vlan-segmentation
by affaan-m
Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik — including switch trunk config, firewall rules, and wireless SSID mapping. Use when splitting a home network into IoT, guest, trusted, and server VLANs on UniFi, pfSense/OPNsense, or MikroTik.
grill-me
by mattpocock
A relentless interview to sharpen a plan or design.
ai-regression-testing
by affaan-m
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.