AI & ML

efficientcontext Skill

Use when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g. "how much did ContextPilot save?", "show ContextPilot token savings", "ContextPilot status", "savings in the last 24h / all time", or "give me the raw savings JSON". This skill runs the metadata-only `scripts/contextpilot_savings.py` reporter and summarizes its output in plain language. It is read-only and observe-only — it never changes ContextPilot code or config, never enables routing/dropping/summarization, never creates cron jobs, branches, or pull requests, and never reads conversation messages, tool outputs, system prompts, reasoning, or raw session ids.

greatmark Skill

Delegate a coding task to Codex with write access via the codex CLI (no MCP). Use when the user wants Codex to investigate/fix/implement something, when Cursor is stuck after repeated attempts and a second implementation pass would help, or to continue a previous Codex task. Trigger words - delegate to codex, hand it to codex, codex rescue, let codex fix it, continue the codex task, 让 codex 修, 交给 codex, codex 接手, 继续上次 codex 任务.

hicywon Bundle

MasterGo Vibe MCP 集成。当用户要求在 MasterGo 画布上设计、绘制、 生成页面、读取图层代码、修改组件、管理变量时使用。自动检测 MCP 连接状态，未配置时引导一键安装，配置完成后提供完整的工具调用能力。 支持私域版 MasterGo（如 mastergo.private.example.com）。

kareemghorab Bundle

Builds production-ready full-stack apps with interactive product intake, contradiction checks, feature recommendations, TDD, modular-monolith architecture, i18n/locales, dark/light themes, responsive layouts, professional UI/UX, current stack defaults, verification loops, and AI-agent documentation. Use when the user asks to build, scaffold, create, or greenfield a web/app product, full-stack project, MVP, or SaaS — or explicitly names fullstack-prod.

lightharu Skill

Brain-inspired cognitive architecture. Self-evolving personality, memory, emotions, skill learning, and reward adaptation. Injects brain context into every prompt.

ptpavlotkachenko Skill

Design rules for building Spectacles lenses in Lens Studio 5.22 (CLAD/MCP workflow) so they downgrade to LS 5.15.4 for device testing in under an hour. Load when STARTING or architecting a new 5.22 Spectacles project that will later be tested on Spectacles (2024), when the user says "we will downgrade to 5.15" / "5.15-portable" / "we will test on device later", or before adding any shader/material/package to a 5.22 project that must survive the downgrade. Distilled from two full real-project migrations.

stefanozaghi1987 Skill

Re-validate the model-routing configuration (settings.json aliases, fallback chain, advisor, reviewer subagents, effort rules) against the current official Claude Code docs and propose updates. Manual maintenance task.

szewowsky Bundle

Skanuje skille, paczki MCP i agentów pod kątem zagrożeń (prompt injection, kradzież kluczy, złośliwy kod) przez Snyk agent-scan. Używaj gdy: „przeskanuj skilla", „sprawdź czy skill jest bezpieczny", „zeskanuj paczkę" — dla lokalnego folderu lub linku do repo ze skillem.

britt Skill

Use when a repo's agent setup may be broken, half-finished, or drifted - a setting-up-a-project run failed partway, CLAUDE.md or AGENTS.md is thin or missing sections, leftover {{PLACEHOLDER}} text, AGENTS.md is a symlink, the instruction files disagree, or agents behave inconsistently in the repo - audits the project against what setting-up-a-project would generate today and repairs only the gaps, preserving existing content

cbemister Skill

Enhance an existing project with Claude Code agents, teams, rules, hooks, plans, MCP servers, and CLAUDE.md. Scans what exists, installs what's missing. Links shared files (agents, plan templates) from ~/.claude/shared/enterprise/ instead of duplicating.

januarylabs Skill

Explain Zukhruf's purpose and durable background-agent model.

johnpuksta Skill

MCP Server Setup

ydnikolaev Bundle

Debugger 🔍

ydnikolaev Bundle

[object Object]

jiunbae Bundle

Synthetic AIR example with no private session content

doodledood Skill

Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.

u9401066-pubmed-search-mcp Skill

Codex workflow skill for building Foam-compatible LLM wikis from Zotero, PubMed, documents, and local Markdown notes.

akornmeier Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

spartanlabsxyz Bundle

Fixture Instruction-Only Skill

madappgang Skill

Provides Whisper transcription patterns — model selection, SRT/VTT/JSON, timing sync, diarization. Use when transcribing audio or video, or generating subtitles.

pumblus Bundle

OKF Harness

rerun-io Skill

Rerun data model

th0rgal Skill

Manage the Sandboxed.sh library (skills, agents, commands, tools, rules, MCPs) via Library API tools. Trigger terms: library, skill, agent, command, tool, rule, MCP, save skill, create skill.

slackapi Skill

Use when a developer wants to create, scaffold, or bootstrap a new Slack app or agent from scratch with the Slack CLI. Covers prerequisites, sandbox setup, authentication, and creating + running a project from a Bolt (JS or Python) template locally. Trigger on "create a Slack app", "new Bolt app", "start a Slack agent".

codealive-ai Bundle

Search X/Twitter posts with Exa, filtered to x.com/twitter.com. Use for finding tweets or threads on a topic. NOTE: Exa's X coverage is limited (the tweet category was retired and X blocks crawlers), so results are often sparse — the skill is honest about this and suggests fallbacks. Runs a local script against the Exa API; no MCP server required.

codealive-ai Bundle

Find people with Exa semantic search — by role, company, and location, LinkedIn-weighted. Use to map a company's team, find experts/decision-makers, locate a specific person, or build people lists. Runs a local script against the Exa API; no MCP server required.

codealive-ai Bundle

Research companies with Exa semantic search — find competitors, funding, headcount, news, and build company lists. Use for competitor analysis, market mapping, sourcing companies by category/stage/geo, or 'find companies like X'. Runs a local script against the Exa API; no MCP server required.

kostiantyn-matsebora Bundle

Canopy framework execution engine. Interprets canopy-flavored skills (any SKILL.md with a `## Tree` section) at runtime — platform detection, section semantics (`## Agent`/`## Tree`/`## Rules`/`## Response:`), tree notation (`<<`, `>>`, `|`), control-flow primitives (`IF`/`ELSE_IF`/`ELSE`/`SWITCH`/`CASE`/`DEFAULT`/`FOR_EACH`/`BREAK`/`END`), interaction primitives (`ASK`/`SHOW_PLAN`), execution primitives (`EXPLORE`/`VERIFY_EXPECTED`), op lookup chain, category directory semantics, subagent contract. Install this to execute existing canopy skills. Install `canopy` (the authoring agent) too if you need to create/edit/manage them.

mikker Bundle

Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.

ucsandman Bundle

Governance behavior for AI agents governed by DashClaw. Teaches the governance protocol: when to call guard (risk thresholds), how to interpret decisions (allow/warn/block/require_approval), when to record actions, how to wait for approvals, and session lifecycle management. Loads org-specific policies and capabilities from MCP resources at session start. Use with @dashclaw/mcp-server. Trigger on: governed agent, dashclaw governance, guard policy, approval wait, governed capability, risk threshold, action recording, session lifecycle.

bobmatnyc Skill

Core Rust toolchain conventions — ownership/borrowing patterns, error handling, async with tokio, and idiomatic project structure for the rust-engineer agent

tbsten Skill

PR の探索的検証で 5 並列 subagent を category 別に kick する際の運用規約。 PDCA / MCP / 設定ファイル拡張 / CI ログ / apiDump / ticket 起票 / PR コメント / gradle 隔離 / working tree / 時間管理 / 他 KCP 比較 / 各 cat 役割 / ループ終了処理 / メンテナ反応 latency trace / close 後 handshake を含む。 各探索 iter で subagent を kick する前に必読。

woocommerce Bundle

Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring. Runs live against the demo store + gpt-5.1 via the woo-mobile-ai backend wrapper, writes a JSONL run record, compares against stored baselines, and surfaces regressions. Always delegated to a subagent so the main context only sees the markdown report.

blink-new Skill

Knowledge base with vector search, document upload, collections, and AI-powered Q&A with citations. Semantic search over uploaded documents.

blink-new Skill

GitHub operations via the Blink GitHub App — clone repos, push code, open pull requests, create issues, check CI, and call the GitHub REST API. No PAT needed. Connect once at blink.new/settings?tab=connectors and every surface (CLI, MCP, Claw agents) works automatically.

dotnet Skill

Select and run .NET SDK tests through the repository's diagnostic-preserving test entry point. REQUIRED whenever an agent will select, run, or rerun local dotnet/sdk tests, including a project, class, method, targeted test, focused test, smallest relevant test, or completed-change validation. NEVER invoke when the user says not to run tests yet.