| Name | Contains | Score |
|---|---|---|
Rego is the declarative policy language used by Open Policy Agent (OPA). This tile covers writing and testing Rego policies for Kubernetes admission control, Terraform and infrastructure-as-code plan validation, Docker container authorization, HTTP API authorization, RBAC and role-based access control, data filtering, metadata annotations with opa inspect, and OPA policy testing with opa test. | DocsRules | 99 1.19x Agent success vs baseline Impact 99% 1.19xAverage score across 31 eval scenarios Reviewed: Version: 1.17.0 |
Hygiene patterns for any OpenCV + dlib vision pipeline: camera index probing + macOS init quirks, warmup that verifies real frames, frame-skip policy for expensive inference. | SkillsRules | 94 1.36x Agent success vs baseline Impact 100% 1.36xAverage score across 6 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.2 |
dl-team-1/my-first-tile v0.1.1 now | SkillsRules | 15 Impact — No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.1.1 |
jbaruch/speaker-toolkit v0.18.5 Six-skill presentation system: ingest talks into a rhetoric vault, run interactive clarification, generate a speaker profile, create presentations that match your documented patterns, produce the deck illustrations + thumbnail visual layer, and publish talk pages to a Jekyll shownotes site. Includes a 102-entry Presentation Patterns taxonomy (91 observable, 11 unobservable go-live items) for scoring, brainstorming, and go-live preparation. | SkillsRules | 88 1.30x Agent success vs baseline Impact 89% 1.30xAverage score across 25 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.18.5 |
himank-test/tessl-llvm v0.5.1 LLVM 22.x tile for building compilers, language runtimes, and out-of-tree tooling | SkillsDocsRules | 85 1.23x Agent success vs baseline Impact 96% 1.23xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.5.1 |
jbaruch/nanoclaw-host v0.1.34 Skills and rules for the NanoClaw host agent (Claude Code on Mac). Tile promotion, container management, staging checks, repo chain safety, and public sync. | SkillsRules | 72 Impact — No eval scenarios have been run Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.1.34 |
tessl-labs/good-oss-citizen v1.1.10 Rules and skills that teach AI agents how to contribute to open source projects without being the villain. | SkillsRules | 95 3.55x Agent success vs baseline Impact 96% 3.55xAverage score across 20 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 1.1.10 |
jbaruch/govee-h6056 v0.1.5 Ground truth for Govee Flow Plus Light Bars (H6056): phantom segments, bar-to-segment mapping, API auth and rate limits. Language-agnostic facts; Kotlin/Ktor reference example. | SkillsRules | 93 3.84x Agent success vs baseline Impact 100% 3.84xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.5 |
Database architecture skills, docs, and rules for high-demand multi-tenant commerce platforms (PostgreSQL source of truth, Neo4j as derived GraphRAG projection, transactional outbox, RLS-based tenant isolation). Includes live schema introspection workflow via Postgres MCP. | SkillsDocsRules | 77 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 1.1.1 |
Flight notifications via byAir: delay, gate, connection risk, inbound aircraft delay, time-to-leave, arrival logistics. NanoClaw per-chat overlay tile. | SkillsRules | 77 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 0.1.12 |
g14wxz/pkce-auth-flow v0.1.0 Enforces PKCE-based OAuth code flow replacing implicit auth flows for modern Supabase auth. | SkillsDocsRules | 80 Impact — No eval scenarios have been run Securityby Passed No known issues Reviewed: Version: 0.1.0 |
Hygiene for JavaCV + DJL vision pipelines on Kotlin/JVM: camera discovery and probing, frame-skip policy for heavy inference, downscale-before-detection. Replaces the Python jbaruch/vision-pipeline-foundations tile. | SkillsRules | 91 1.86x Agent success vs baseline Impact 99% 1.86xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.1 |
vitron-ai/alethia v0.8.4 Agent-native E2E runtime with verifiable safety. 16 MCP tools including alethia_propose_tests (agent generates tests from a URL), alethia_assert_safety (proves destructive actions are blocked), and the expect block: NLP primitive unique to Alethia. Zero-IPC; 2-5x faster than Playwright MCP per flow; signed evidence packs. Works with Claude Code, Cursor, Cline. | SkillsDocsRules | 95 2.80x Agent success vs baseline Impact 98% 2.80xAverage score across 5 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.8.4 |
tessl/cli-setup-beta v0.71.0 Tessl CLI MCP tool usage guidelines | Rules | — |
tessl/cli-setup v0.71.0 Tessl CLI MCP tool usage guidelines | Rules | — |
Standards and workflows for building secure, well-structured Terraform modules, including planning gates, validation steps, and implementation guidance. | SkillsDocsRules | 74 1.77x Agent success vs baseline Impact 80% 1.77xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.8 |
vitron-ai/themis v1.2.2 Reference tile for Themis, a Node.js and TypeScript unit test framework designed for AI coding agents. Covers unit-test authoring, Jest/Vitest migration, agent-readable failure output with repair hints, and first-class integrations for Claude Code, Cursor, and generic agents. | SkillsDocsRules | 98 2.91x Agent success vs baseline Impact 99% 2.91xAverage score across 20 eval scenarios Securityby Passed No known issues Reviewed: Version: 1.2.2 |
Meta-skill: how to pass skills/context to Claude sub-agents that start with fresh context, with documented SDK gotchas. | SkillsRules | 93 1.43x Agent success vs baseline Impact 92% 1.43xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.7 |
Syncs TripIt travel itineraries to Reclaim.ai timezone segments and Google Calendar OOO blocks. | SkillsDocsRules | 97 1.70x Agent success vs baseline Impact 97% 1.70xAverage score across 4 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.3.0 |
Evidence-first pull request review with independent critique, selective challenger review, and human handoff. | SkillsRules | 92 1.43x Agent success vs baseline Impact 93% 1.43xAverage score across 43 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.8 |
Can't find what you're looking for? Evaluate a missing skill.