Explore

Mounts Cloud Storage buckets on Google Cloud as a POSIX file system using Cloud Storage FUSE (and the gcsfuse CLI tool). Use when interacting with the gcsfuse CLI or Cloud Storage FUSE mounts: decide

in the skill textrunbook for slow mounts and bill spikes — enabling and reading gcsfuse metrics, mapping cache-hit and request-mix signatures to misconfigurations, the coherency-tuned defaults, tuned

Official·Skill·Apache-2.0·★ 21k in collection·No key

Produces API reference documentation for Next.js APIs: functions, components, file conventions, directives, and config options. **Auto-activation:** User asks to write, create, or draft an API referen

in the skill textcode showing the convention, props, behavior, examples 4. **Directive** (`use client`, `use cache`): definition, usage, serialization/boundary rules, reference 5. **Config option** (`basePath`, `images`, etc.): definition, config

Official·Skill·MIT·★ 143k in collection·No key

Convert text, markdown, or a summary produced by another skill into a listenable MP3 using local CPU-only neural text-to-speech. Rewrites written prose for the ear before synthesising. Use when the us

in the skill textrun on CPUs. The bundled script installs it automatically into a cached virtualenv on first use, so usually you need do nothing. To install it explicitly

Official·Skill·MIT·★ 40k in collection·No key

Creates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Modeling Tool v7.3+. Use this skill whenever asked to create, generate, or modify a .tm7 threat model fil

in the skill textthe elements: - **Processes** (web apps, services, functions) → `StencilEllipse`, `GE.P` - **Data stores** (databases, caches, queues, blobs) → `StencilParallelLines`, `GE.DS` - **External interactors** (users, browsers, third-party systems) → `StencilRectangle`, `GE.EI

Official·Skill·MIT·★ 40k in collection·No key

Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal

in the skill textMarkdown, JSON, and source files. It is not hidden in a plugin cache, locked in a cloud database, or silently uploaded to a model. ## From source

Skill·MIT·★ 16k·No key

CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity.

in the skill textcalculated from unrounded averages per six-task run, then rounded to whole percentages. ¹ Cache-weighted input proxy, not dollar cost. ² Includes estimates where final token usage

Skill·MIT·★ 222·No key

洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.

in the skill textapply --move-root` to park untracked process Markdown under `.agent_tmp/` | | 2 | **Cache sprawl** | `node_modules`, `.venv`, build caches, WSL/Docker VHDX grow silently | `audit_workspace_hygiene

Skill·MIT·★ 18·No key

A vision backend for AI Agents — self-healing Claude Code Agent Skill. Routes images to Mimo/OpenAI/Ollama vision API.

in the skill textjson # 结构化输出 unblind.mjs --health # 连通性诊断 unblind.mjs --config # 查看配置 unblind.mjs --set-model # 切换模型 unblind.mjs --cache-stats # 缓存统计 unblind.mjs --clear-cache # 清空缓存 ``` ## 🏗️ 架构 协议驱动——把 LLM API 的

Skill·MIT·★ 24·No key

Skill for Claude Code & Codex: describe your system architecture in text → get an editable PowerPoint diagram (native shapes, not a flat image).

in the skill textServing (PagedAttention) Six-layer request pipeline (client → API server → engine → paged KV cache → execution → optimizations). Solid edges = data flow; dashed = cache/block management. *Scheme S1 Monochrome Blue

Skill·MIT·★ 44·No key

An open-source Agent Skill for problem framing and assumption testing across coding, debugging, architecture, scientific research, and product decisions.

in the skill textP99 rose from 300 ms to 2.8 s. Add Redis." -> design a cache | Attribute the reported latency, test whether database time actually dominates the slow tail

Skill·MIT·★ 102·No key

Test coverage for your docs: anchors doc sections to the code they describe, deterministically flags drift with receipts, proposes reviewable patches.

in the skill textthe repo; no deletion record in reachable history [env-claim] README.md:9 "ITEMS_CACHE_URL" receipt: read nowhere in code (scanned 3 files for process.env.ITEMS_CACHE_URL

Skill·Apache-2.0·Few stars·No key

AI Skills Bank is a unified, multi-tool platform designed to aggregate, manage, and route AI skills across various workflows and AI assistants (such as Antigravity, Claude Code, Cursor, and Copilot).

in the skill textagent platforms (Claude, Copilot, Cursor, Hermes, etc.). 5. **Maintains** a canonical cache in `lib/` with automatic updates via file watcher. **Result:** Agents access 3,600+ curated

Skill·MIT·★ 13·No key

Give Claude a smarter video input. Scene-aware frame extraction, per-frame OCR, auto-chunked Whisper transcripts. Skill for Claude Code, claude.ai, and Codex.

in the skill textimprovements: only reads `.env` from `~/.config/scenelens/`, validates `--out-dir` against system paths, caches request bodies between Whisper retries. ``` /scenelens what hook did they open with? ``` ## Install

Skill·MIT·★ 3·Few stars·No key

Turn public X posts, profiles, and search into compact Markdown or JSON for agents. Hosted at x.pcstyle.dev.

in the skill textoff`, `author`, `all` | | `nocache` | false | `true`, `1`, or `yes` bypasses the application cache | `thread=off` returns only the requested post. The default conversation result is ordered

Skill·MIT·★ 161·No key

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing,

in the skill textCHAR_LIST, } ``` **deploy/gen_trt_engine (mandatory data sources):** ```python { "gen_trt_engine.onnx_file": " ", "gen_trt_engine.trt_engine": " ", "gen_trt_engine.tensorrt.calibration.cal_cache_file": " ", "gen_trt_engine.tensorrt.data_type": "fp16", "gen_trt_engine.tensorrt.calibration.cal_image

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

in the skill textConformer-RNNT | `decoder=nemo` | `parakeet-rnnt-*` | | **Conformer-TDT (default)** | `decoder=nemo` | `parakeet-tdt-*` | | Cache-Aware RNNT (Nemotron streaming) | `decoder=nemo` | `nemotron-streaming-*` ⚠ SFT broken on this

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

in the skill textduring editing loops nearly instantaneous. Pass `--no-cache` to bypass the cache, or `--cache-dir ` to customize its location. See `docs/CACHE.md` for technical details on storage

Skill·MIT·★ 33·No key

Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. Sends user-provided PDB files and design parameters to NVIDIA's hosted API, authenticated with an envi

in the skill textAPI_KEY`. Local inference requests use no auth header after readiness. Warm-cache key-free startup varies by image/version and should not be assumed. ## Data Transfer

Official·Skill·Apache-2.0 AND CC-BY-4.0·★ 3.6k in collection·No key

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop

in the skill textAgent: .foundry Workspace Standard Every agent source folder can keep Foundry-specific cache and overlay state under `.foundry/`: ```text / .foundry/ agent-metadata.yaml agent-metadata.prod.yaml suites/ datasets/ evaluators/ results

Official·Skill·MIT·★ 1.6k in collection·No key

A multi-agent application-security review harness for Claude Code (and, later, other AI agents). One router skill dispatches to a full offensive-security pipeline that maps a codebase, hunts vulnerabi

in the skill textthat was written on the PR the whole time. This needs no cache: the state lives in the PR, so it works on a cold machine

Skill·MIT·★ 42·No key

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-

in the skill texttransitions via lint; immutable event log | | **Repeat ingest is expensive** | 3-layer cache (embedding, LLM, provider prompt) — repeat lint on unchanged pages costs near-zero tokens

Skill·AGPL-3.0·★ 1.6k·No key

A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.

in the skill textthe tool that opens a network connection for `check`. Answers are cached on disk so that a run interrupted by an outage does not pay for

Skill·MIT·★ 35·No key

Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

in the skill textCustom composition without `storageDomain` | Supported | Depends on Web services | Available | URL cache and Host calibration use in-process state | Before replacing `0.5.4`, read the Upgrade and

Skill·MIT·★ 59·No key

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents explore at query time, with document lookup instead of a serv

in the skill textthe paper). Per-query token accounting includes `input_tokens`, `output_tokens`, `cache_read_input_tokens`, and `cache_creation_input_tokens` (Anthropic prompt-cache fields), plus

Skill·MIT·★ 94·No key

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compress

in the skill textits tail never loads | | Disabled plugins | Installed but disabled plugins still in cache | | Stale projects | Project memory untouched for 90+ days | | Temp caches | Failed plugin install

Skill·MIT·★ 44·No key

HAR Skills — AI-native library for HAR file analysis. Access via: Skills (CLAUDE.md), Go SDK, CLI, MCP. 23 commands, 70+ methods, progressive disclosure docs.

in the skill textheaders, cookies, CORS, mixed content, leakage | | `cookie` | Cookie inventory and security posture | | `cache` | Cache-Control and cacheability analysis | | `performance` | Lighthouse-style scoring and recommendations | | `redact` | Sensitive

Skill·MIT·★ 38·No key

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a

in the skill textprompt cache, so the breadcrumb is kept small and standalone to stay cache-safe. ```markdown # ▸ NEXT **C003 · Build the signup API** `P1` `critical path` `5 pts

Skill·MIT·★ 68·No key

WaveSpeed CLI — run any image, video, audio or 3D model from your terminal or coding agent: live catalog search, per-model schema introspection, local-file upload, price quotes

in the skill textupload; a missing `@` file is an error. Identical bytes are content-hash cached for 24h, so repeated runs (and `price --upload`) reuse one upload and spare

Skill·MIT·★ 25·No key

Claude Code skill: one topic in, one ranked YouTube research workbook out. Searches YouTube Data API v3, ranks by views, engagement, momentum or breakout, and writes Videos, Channels, Summary, Comment

in the skill texthooks: yt-dlp -j per video, json3 captions, heatmap peaks (no quota, cached) | --transcribe: local Whisper on the downloaded file or fetched audio (no quota, cached

Skill·MIT·★ 61·No key

Research, Evolve, and Document for AI-assisted engineering

in the skill textchange might look like this: 1. **Research — investigate the cause.** “Does the cache survive a settings update?” Capture observations and investigate invalidation. Present the findings and

Skill·Apache-2.0·★ 11·No key

Mubu (幕布) outline CLI & AI Agent Skill — import/export Markdown with true round-trip fidelity, plus OPML/FreeMind export.

in the skill textand PR. - ✅ **Auto-refresh auth** — expired tokens re-login automatically using your cached credentials (env vars / `~/.workbuddy/.env.mubu`); no manual re-entry needed after initial setup. - ✅ **Pinned

Skill·MIT·★ 17·No key

Discover, read and maintain Notion skills with immutable task snapshots

in the skill textauthentication: "available"`, a positive `skill_count`, and `skill_read.available: true`. It reads and caches one Skill to verify the selected storage mode. `list` returns metadata and coverage

Skill·MIT·Few stars·No key

Give DeepSeek (text-only) models **vision** in Claude Code and Codex by routing image files to any OpenAI-compatible vision endpoint (OpenRouter, SiliconFlow, DashScope, Ollama, llama.cpp, vLLM, LM St

in the skill textname and publishes it to **both** npmjs and GitHub Packages. Your settings, cache, skill files, and the CLI command are **unchanged** — only the package reference moves

Skill·MIT·★ 3·Few stars·No key