Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Skill Claude CodeCodex
Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checked with code. Do NOT use when the failure can be checked with regex, schema validation, or execution tests. Do NOT use…
claw-opus/proactive-self-improving-agent
Skill Claude CodeCodex
A skill that records failed actions, user corrections, missing capabilities, tool errors, outdated knowledge, and better approaches in separate files.
Skill Claude CodeCodex
Expert Chrome developer skill covering advanced browser APIs and capabilities. Use this skill whenever working on Chrome extensions (Manifest V3), WebAssembly (Wasm 3.0), WebGPU (graphics and compute), WebNN (neural network inference), Chrome Built-in AI (Gemini Nano Prompt API, Summarizer, Translator), local ML model…
Skill Claude CodeCodex
A protocol framework for long-horizon autonomous tasks. Targets three empirically-observed failure modes — cognitive loops, stalling, runtime fragility — by prescribing state management, stall detection, and watchdog mechanisms. Validated on multiple task types including paper writing (4 ICLR-format surveys…
Skill Claude CodeCodex
Audits a Claude Code / Agent SDK skill (or folder of skills) against 10 QA checks to verify it will trigger and execute correctly in any LLM (Claude, GPT, Gemini). Ativa quando o usuário diz "audit my skill", "roda skill-audit", "verifica se essa skill funciona", "check skill quality", "skill-audit ./my-skill", "minha…
Skill Claude CodeCodex
Agentic DFIR orchestrator that autonomously investigates security incidents by chaining forensic skills (IOC extraction, Windows artifact triage, timeline correlation, YARA generation) with an autonomous reasoning loop, persistent case state, and human-in-the-loop approvals. Use this skill whenever the user mentions…
Skill Claude CodeCodex
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
bahayonghang/my-ai-cli-toolkit
Skill Claude Code
Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion codemap.md navigation maps — against Claude 5 context-engineering rules (judgement over rules, progressive disclosure, no cross-layer conflicts). Asks whether to optimize the current repository…
Skill Claude Code
Icelandic personal-finance literacy (fjármálalæsi) — payslips and wage rights, union benefits, the three-pillar pension system, verðtryggð (CPI-indexed) mortgages — year-by-year projections, equity/LTV paths, and prepayment strategies — séreignarsparnaður trade-offs, savings and investment options, staðgreiðsla tax…
tracebit-com/tracebit-canary-honeytokens-skill
Skill Claude CodeCodex
Use when the user wants to protect their workspace from credential theft, prompt injection, or data exfiltration — even if they don't mention "canaries" or "honeytokens" directly. Covers deploying Tracebit security canaries (fake decoy credentials that alert on use), detecting when they're triggered via the user's…
Evaluris-Solutions/claude-active-directory
Skill Claude CodeCodex
Use when classifying or explaining authorized Active Directory attack techniques—Kerberos and NTLM paths, coercion awareness, delegation and RBCD, ACL and DCSync concepts, LAPS and shadow credentials, GPP, trust paths, AD-joined SQL pivots, and lateral movement by protocol. Use as a reference when writing findings or…
Skill Claude CodeCodex
Search for campgrounds, check availability and book campsites across the entire world.
Skill Claude Code
Read this before authoring or substantially changing a plugin, skill, or agent for Archie. It's the conceptual playbook for building plugins that fit Archie's one-agent-per-task model — what a plugin contributes, when a skill is the right answer (almost always), and the narrow cases where a worker earns a definition…
Carloslee96/vizagent-dashboard
Skill Codex
Compile CSV/XLSX tabular data and a DashboardSpec into a single validated offline HTML dashboard with KPIs, charts (line/bar/pie/scatter), China/world maps, theme tokens, and a data-coverage + validation report. Use when the user has a spreadsheet (CSV or XLSX) and wants a standalone HTML dashboard — for business…
yan-stone-computer/ModelVisionSkill
Skill Codex
Give text-only LLMs (DeepSeek, Xiaomi MiMo, GLM-4.5, MiniMax, Llama 3.x, etc.) eyes by analyzing images, screenshots, UI captures, diagrams, charts, and OCR documents through free multi-modal APIs with automatic engine fallback and caching. Images are handled by the browser-driven web engines FIRST (Doubao, Kimi…
Skill Claude Code needs its repo
Use the ng-blatui Angular UI library in an app — install, import components (bui-prefixed, signal-based, zoneless, SSR-safe), theme with Tailwind v4 + oklch tokens, localize dates/numbers/labels, and discover the full catalog via the registry, api.json, llms.txt or the ng-blatui-mcp MCP server. Invoke when building…
Skill Claude CodeCodex
A web crawler and scraper that searches with DuckDuckGo, fetches individual pages or whole sites, and returns clean Markdown intended for language models. It can also scrape pages that need JavaScript to display their content.
Skill Claude CodeCodex
Overview of all available Pinecone skills and what a user needs to get started. Invoke when a user asks what skills are available, how to get started with Pinecone, or what they need to set up before using any Pinecone skill.
Aaryan-Kapoor/video-production-skill
Skill Claude CodeCodex
End-to-end narrated video production with research, source extraction, storyboard/script, Manim/ffmpeg visuals, TTS voiceover, QC, archival backups, and optional local/Tailscale hosting. Use when the user asks to make, create, generate, render, or produce a video, explainer, paper walkthrough, product demo, briefing…
Skill Claude CodeCodex
Demonstrate basic injection payloads for training.
Skill Claude CodeCodex
Approval workflow skill. View pending approval tasks and approve or reject service requests.
Skill Claude Code
Delegate implementation to Codex or to a sandboxed Claude Code (claude -p), have a model from the other vendor review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex or a sandboxed Claude to write code, mentions handing off / delegating…
Skill Claude CodeCodex
A skill for deeply reading and analysing long technical blogs, product announcements, industry analysis, and case studies. It identifies the article’s type and writes the analysis in natural Chinese paragraphs.
Skill Claude CodeCodex
Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state…
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: