16,155 mods tagged anthropic that install into Claude Code, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
The distributed-correctness lens: design or audit anything that spans machines. Use when the user designs or reviews RPC, queues, replication, consensus, sharding, fault tolerance, or distributed transactions — or asks whether a design is correct. Triggers on "is this retry safe / exactly-once / idempotency"…
Turn a user's idea, scene description, or mood into ONE production-grade cinematic still-image prompt in English for text-to-image models (Seedream, Midjourney, Flux, DALL-E, or any image generator). Use this skill whenever the user asks for an image prompt, a cinematic frame, a "movie still" look, a photorealistic…
Scores a potential date against the user's stated preferences (traits, dealbreakers, age range, distance, intent) and returns a like/pass decision with reasons.
Take a fuzzy idea (or an existing thing you want to improve) through a disciplined funnel — explore → pressure-test → converge — and produce one living CONCEPTBRIEF.md: a locked concept + phased roadmap. Acts as a blunt, honest co-founder (permission to overrule you), forces a success metric and a kill criterion…
Writes, rewrites, reviews, and audits prompts and system prompts using Anthropic's current official guidance, and selects the right model and effort level for the task before drafting. Use when the user asks to write a prompt, improve or fix a prompt, design a system prompt, or check a prompt before running a task …
Score your own Claude Code and Codex CLI sessions on YC Paxel's exact 5-axis rubric, locally, with Claude as the scorer (no upload, no backend). Use when the user wants to see how Paxel would evaluate their work, run a self-assessment on Execution Leverage / Steering / Engineering Quality / Product Thinking /…
Audit Claude Code configuration for issues, overlaps, unused components, update status, and misconfigurations. Use when the user (1) asks to check or audit their setup, (2) wants to find duplicate or conflicting skills, hooks, plugins, or rules, (3) asks what is broken or needs cleanup, (4) wants to check Claude Code…
Tutoring skill (teach) for learning a topic interactively — calibration, syllabus planning, and a Socratic/Feynman/drill teach loop. Named after Richard Hamming.
★not rated 2 4mo agoA
tokens not measured
originalMIT
End-to-end help filing an Indian ITR-2 for AY 2026-27 (FY 2025-26) for a salaried person with capital gains from shares and mutual funds, plus interest from RD/FD/savings. Parses Form 16, AIS, TIS, Form 26AS and broker/RTA capital-gains statements, reconciles them, classifies every gain under the current…
Finds where a Claude Code session wasted tokens (uncached context, context bloat, oversized tool output, redundant reads, wrong-tier routing) and coaches the fix. Adds a live cost/context statusline and a non-blocking end-of-session coach.
★not rated 2 2mo 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
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.
Scan a codebase and generate a new-developer onboarding guide as HTML, then publish to uselink. Use when the user wants to create a getting-started guide, onboard a new team member, or share 'how to work in this repo' docs.
Project bootstrap wizard — turns any codebase into a fully planned, agent-ready project with coordination docs, debugging guidelines, and parallel execution infrastructure. Use when starting work on a new or unfamiliar project that needs structure.
Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal. Preserves manually resumable state and uses oh-my-claudecode for autonomous continuation. Use only when the user explicitly invokes goal-loop.
First Claude Code plugin that generates brand-aligned visual assets from your terminal. 9 providers, cost-optimized (one call, many derivatives), security-first (auto-gitignore, chmod 600, pre-commit hook).
★not rated 2 5mo agoA
tokens not measured
originalMIT
Skill that makes your coding agent stop and ask instead of silently resolving spec ambiguity, picking up workarounds, or shipping 'close enough'. Accuracy over autonomy.
★not rated 2 yesterdayA
tokens not measured
originalMIT
Spec-driven development for existing codebases. Reads your repo's conventions, interviews you about a change, and writes spec, design and tasks to disk, with blast-radius analysis. Regulatory policy profiles are optional and off by default.
★not rated 2 16d agoA
tokens not measured
originalMIT
Autonomous Project Manager for Claude Code. Orchestrates parallel worker sessions to execute Linear tasks through a structured lifecycle: fetch, assign, implement, verify, review, merge.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Greenfield Labs Claude Code plugin marketplace — ramp (adaptive learning) and tools (session lifecycle management).
★not rated 2 1mo 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: