A software factory for AI coding agents: opinionated plan -> build -> review -> test -> ship -> reflect workflows, shipped as portable Agent Skills that run identically on Claude Code and pi.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Agent skills from the team behind Cavuno and Himalayas — evidence-first performance optimization and a PR review loop that only fixes what it can demonstrate.
★not rated 2 21d agoA
tokens not measured
originalMIT
Builds a progressive YouTube learning path on any topic. Fans out 8+ search angles with yt-dlp and web search, then reads the transcript and the top comments of every shortlisted video before recommending it. Broad topics are anchored to the field's canonical textbook and delivered with an honest coverage table.…
★not rated 2 1mo agoA
tokens not measured
originalMIT
An Early Value Proposition is a ≤22-word line matched to a Schwartz awareness tier. Same product, five lines, because the unaware buyer and the vendor-comparing buyer are not the same reader.
★not rated 2
changed 10d agoA
tokens not measured
originalMIT
A career-planning add-on that studies a résumé against current artificial-intelligence and related job opportunities, then creates a tailored learning route.
Code-quality reviewers: the ai-code-tells skill scans a diff for the tells of unreviewed AI-generated code, and the code-review agent runs a pre-push review of local changes (Claude Code agent + Codex CLI variant included).
★not rated 2 11d agoA
tokens not measured
originalMIT
Audit and fix performance on live WordPress sites across whatever stack they actually run — page builders, caching layers, CDNs and managed hosts. Fingerprints the stack, separates origin from edge TTFB, and applies fixes only under a guarded write loop with a rollback for every change.
Intelligent Agent-Skill dependency butler: discover, security-audit, and install Agent Skills into your project. Scans tech stack, plans a vetted combination, audits each skill, and installs per-agent.
★not rated 2 3mo agoA
tokens not measured
originalMIT
Explain a concept, feature, ticket, or implementation in plain language, grounded in verified source — separating how it works today from what it's meant to become, and flagging assumptions instead of guessing.
★not rated 2 25d agoA
tokens not measured
originalMIT
Hybrid prompt linter — deterministic Node detector for 18 of 20 rules plus an LLM model layer for PR003, PR009, and semantic cases of PR002, PR005, and PR010. Lint, don't rewrite. Markdown or JSON output, suppression comments, baseline mode, conformance corpus (25 cases), CI recipes. Never imposes a framework, never…
★not rated 2 4mo agoA
tokens not measured
originalMIT
Let Claude watch a video -- fully local. Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, ALWAYS transcribes with faster-whisper and compares against creator-provided captions. Auto-detects your NVIDIA GPU: uses it for video decode (NVDEC) and whisper when present, falls back to a fully working CPU-only.
Superpowers for data analytics, causal inference, and econometrics: discipline skills that make the silent failures of data work loud — data contracts, data preparation, join-cardinality checks, wrong-number debugging, result verification, pre-analysis plans, descriptive evidence (stylized facts, trends, summary-stats.
★not rated 2
changed 9d agoA
tokens not measured
originalMIT
Fail-fast quality gate (Typecheck → Lint → Test → Security Audit) that runs before any task is declared done or code is committed. Auto-detects Node.js and Python projects.
★not rated 2 3mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: