agentsclimarketplace

Context & AI engineering

25,729 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • OPTIC

    jord0-cmd/jord0.skills/skills/OPTIC Skill

    0★ repo

    INVOKE THIS SKILL when: generating AI images, editing existing images, writing prompts for Gemini image models, performing surgical inpainting, running multi-pass Sequential Grounding, colour matching composites, or any AI image generation pipeline work. Contains the generator tool, prompt engineering framework, and advanced compositing techniques.

  • RECON

    jord0-cmd/jord0.skills/skills/RECON Skill

    0★ repo

    Deep technical research that persists. Use when: exploring new technologies, investigating frameworks, comparative analysis of tools, understanding complex systems, or any research task that should be saved for future reference. Invokes Claude's built-in research agent and auto-saves results to a knowledge base for retrieval across sessions.

  • SPARK

    jord0-cmd/jord0.skills/skills/SPARK Skill

    0★ repo

    Break out of conventional thinking. Use when: brainstorming feels predictable, standard approaches have failed, creative challenges need unconventional solutions, or when exploring radical alternatives. Invokes Claude's built-in tail-sampler agent to explore low-probability solution spaces that standard reasoning avoids.

  • Auto improving agents md

    msewell/agent-stuff/skills/auto-improving-agents-md Skill

    0★ repo

    Sets up, structures, and auto-improves AGENTS.md files for coding agent projects. Bootstraps new AGENTS.md with self-improvement meta-rules, structures sections for clean rule placement, audits and prunes existing files against an instruction budget, performs end-of-session reflection to capture learnings, and proactively proposes AGENTS.md updates when corrections or conventions are discovered mid-session. Use when setting up AGENTS.md, adding auto-improvement to an existing AGENTS.md, pruning or auditing AGENTS.md, performing end-of-session reflection, or when the user mentions auto-improving, self-improving, or maintaining agent instructions.

  • Tdd with llm agents

    msewell/agent-stuff/skills/tdd-with-llm-agents Skill

    0★ repo

    Enforces strict red/green/refactor TDD discipline when writing code. Guides the agent through one-test-at-a-time cycles, prevents test subversion, and ensures minimal implementation. Use when writing code with TDD, doing test-driven development, implementing features test-first, or when the user mentions red/green TDD, failing tests first, or test-driven workflow.

  • Toon format

    msewell/agent-stuff/skills/toon-format Skill

    0★ repo

    Instructs an LLM agent when and how to use TOON (Token-Oriented Object Notation) for encoding and generating structured data. Use when injecting structured data into context, encoding tool results, preparing RAG documents, producing structured output, or advising on TOON integration.

  • Writing agent skills

    msewell/agent-stuff/skills/writing-agent-skills Skill

    0★ repo

    Creates, reviews, and iterates on Agent Skills (the open, cross-platform format for extending AI agents). Scaffolds new skill directories, writes SKILL.md files with proper frontmatter and body structure, applies progressive disclosure, reviews existing skills for anti-patterns, and guides testing workflows. Use when the user asks to create a skill, write a SKILL.md, review or improve an existing skill, or structure agent instructions.

  • Loop orchestration engineer

    papanito/ai-skills/skills/loop-orchestration-engineer Skill

    no license0★ repo

    specialized protocol for Loop Engineering — auditing a workspace for repeatable tasks, ranking them with the 4-Condition Test, and building self-verifying Loop Orchestration Skills with a done-rule, a separate verifier subagent, run memory, and a Loop Training Mode toggle.

  • Pushary

    Pushary/pushary-skill/skills/pushary Skill

    0★ repo

    Push notifications + human-in-the-loop for AI agents. Approve from your lock screen. Claude Code, Claude Cowork, Codex, Cursor, Gemini.

  • Agent integration

    Victoriakaey/build-reliable-agents/skills/agent-integration Skill

    0★ repo

    Use when connecting an LLM agent to a full-stack application, external API, or third-party platform. Covers four integration patterns (REST, WebSocket/SSE, Webhook, Message Queue), interface design, reliability, security, and observability. Framework-agnostic — guides you to the right pattern for your situation, then gives concrete implementation direction for your chosen stack.

  • Code review

    Victoriakaey/build-reliable-agents/skills/code-review Skill

    0★ repo

    Use when reviewing code — either Claude reviews your code and produces a structured report, or Claude guides you through reviewing someone else's code. Default mode: Claude performs the review and produces a report organized by severity. Second mode: guided self-review with a structured checklist and probing questions. Covers correctness, security, performance, maintainability, and AI-specific concerns for LLM applications.

  • Database design

    Victoriakaey/build-reliable-agents/skills/database-design Skill

    0★ repo

    Use when designing a database schema for a new system, or when an existing schema needs to be revised. Two modes: (1) general schema design for any application, (2) AI-specific schema design for systems with conversation history, embeddings, agent state, or LLM outputs. Guides through data modeling decisions, type choices, indexing, and AI-specific storage patterns.

  • Harness design

    Victoriakaey/build-reliable-agents/skills/harness-design Skill

    0★ repo

    Use when designing or improving the action space, observation format, tool boundaries, and evaluation signals of an LLM agent. Covers the five layers of harness design: what tools the agent has, what it sees after acting, how each tool is scoped, how behavior is evaluated, and how to iterate when the agent misbehaves. Prevents the most common harness failures — agents that pick wrong tools, ignore critical information, or loop without progress.

  • Memory system

    Victoriakaey/build-reliable-agents/skills/memory-system Skill

    0★ repo

    Use when designing how an agent remembers and uses information across turns, sessions, or runs. Covers the four types of agent memory (in-context, episodic, semantic, procedural), when to use each, how to manage context window limits, retrieval strategies, and memory decay. Cross-references database-design skill for storage schema patterns.

  • Model selection

    Victoriakaey/build-reliable-agents/skills/model-selection Skill

    0★ repo

    Use when choosing a model for an LLM application, deciding between API and local deployment, or evaluating whether fine-tuning is needed. Guides through deployment decision (API vs local), model selection based on task requirements and constraints, configuration setup, and the prompt engineering vs fine-tuning decision. Records user's setup for future reference.

  • Prompt change management

    Victoriakaey/build-reliable-agents/skills/prompt-change-management Skill

    0★ repo

    Use before making any prompt change in an LLM system. Covers the full cycle: pre-change documentation, change scoping, post-change validation, and rollback protocol. Prevents silent regressions caused by prompt changes with unexpected downstream effects.

  • Prompt design

    Victoriakaey/build-reliable-agents/skills/prompt-design Skill

    0★ repo

    Use before writing any new LLM component prompt, or when an existing prompt is producing unstable, inconsistent, or wrong outputs. Two modes: (1) design from scratch by defining component boundaries and structure before writing, (2) diagnose an existing prompt to find root cause of failure. Covers all dimensions of prompt quality: job definition, input structure, output schema, rules, few-shot examples, system/user split, token budget, and prompt decay over time.

  • Handoff

    RhythmMittal19/claude-config/skills/handoff Skill

    0★ repo

    Save session state for the next session. Creates structured handoff file.

  • Session memory

    RhythmMittal19/claude-config/skills/session-memory Skill

    0★ repo

    Bridges Code tab sessions with the Memory MCP server. Use at session start to load relevant project memories, and at session end to store new discoveries. Activates when working on any project to maintain continuity across sessions.

  • Handoff

    pedroberaldo87/pedro-plugins/plugins/handoff/skills/handoff Skill

    no license0★ repo

    Use pra preservar a sessão pra depois (antes de /clear, conversa longa, o usuário sinaliza uma pausa, depois de um marco) OU pra retomar o trabalho no começo de uma sessão nova/recém-limpa onde existe um .claude/HANDOFF*.md. Um comando, dois modos — detecta o estado do contexto (sessão cheia → salva, recém-limpa → retoma) e roteia. Workspace-aware: o handoff pertence ao projeto que a sessão tocou (resolve a fronteira .git dos arquivos editados), então funciona pra projeto avulso, monorepo (um HANDOFF-<módulo>.md por módulo) ou pasta guarda-chuva com projetos aninhados. Use também quando o usuário disser "handoff", "salva a sessão", "retoma de onde paramos", ou rodar /handoff com argumento opcional [salvar|retomar].

  • Orchestration policy enforcer

    alainlebret/claude-agents/higher-ed-teaching-agents/skills/orchestration-policy-enforcer Skill

    0★ repo

    Enforces workflow order, required artifacts, quality gates, and reproducibility rules for the orchestrator. Use when a workflow must be run in a disciplined, auditable, reproducible way.

  • Regression benchmark orchestrator

    alainlebret/claude-agents/higher-ed-teaching-agents/skills/regression-benchmark-orchestrator Skill

    0★ repo

    Runs repeatable cross-workflow benchmarks to detect drift in grading stability, artifact quality, and policy compliance across model or prompt revisions.

  • Task file generator

    scryptoginger/keith-claude-skills/skills/task-file-generator Skill

    no license0★ repo

    Use this skill whenever someone has a short idea — a sentence or two describing something they want built, scaffolded, configured, or automated — and needs it turned into a structured, multi-phase task file that an AI coding agent (Claude Code, Cursor, or similar) can execute autonomously. Trigger on phrases like "write a task file for," "scaffold this project," "break this into phases," "plan this build," "create an autonomous task," "overnight session plan," or any time someone describes a project idea and wants it decomposed into an executable plan with phases, deliverables, and validation steps. Not for writing code directly, executing the task, managing an existing project, or generating single-file scripts — this Skill produces the plan, not the implementation.

  • Tiktok hook writer

    Sayemnyc/claude-skills-for-writers/skills/social/tiktok-hook-writer Skill

    0★ repo

    Generate ten three-second hooks for a TikTok video. The hook is the first sentence the creator says on camera. Each hook is structured to stop the scroll within three seconds. Used when the user has a TikTok concept and needs hook options before recording.

  • Chat session briefing

    CaptCanadaMan/session-briefing/chat-skills/chat-session-briefing Skill

    0★ repo

    Maintain continuity across multi-session projects in a chat interface (claude.ai web or desktop) using a single structured markdown session briefing. Use this skill whenever the user is working on a project that spans multiple conversations, whenever they ask to create or update a session briefing, project status document, or context handoff note, or whenever they mention resuming work from a previous session. Also trigger when the user starts a new multi-step project and needs a system for tracking progress across sessions — even if they don't explicitly say "session briefing." If the user references prior sessions, version histories, or asks to "pick up where we left off," this skill applies. Covers both creating the first briefing for a new project and updating an existing one. For coding agents that run in a repo with a context file (AGENTS.md/CLAUDE.md) and git, use agent-session-briefing instead.

  • Memory vault

    HacQueen2025/Claude-Skills/memory-vault Skill

    0★ repo

    Cross-conversation memory and recall skill. Use this skill whenever the user asks Claude to remember, retrieve, or recall anything from past conversations — code Claude wrote, decisions made, designs created, topics discussed, problems solved, or any previous output. Triggers on: "remember that time we...", "what did we decide about...", "find the code you wrote for...", "what was that thing we built...", "recall our conversation about...", "what do you know about me from past chats", "find everything related to [topic]", "what did we work on last week". Uses Claude's conversation search tools to retrieve, reconstruct, and summarize any past context across all chats. Always trigger for memory or recall requests — even vague ones like "wasn't there something about X we talked about?"

  • Prompt engineer

    HacQueen2025/Claude-Skills/prompt-engineer Skill

    0★ repo

    Master prompt engineering skill for ALL major AI systems. Use this skill whenever the user asks to create, improve, or optimize a prompt for ANY AI — image generators (Midjourney, DALL-E, Stable Diffusion, Flux, Adobe Firefly, Ideogram), video generators (Kling AI, Runway, Pika, Higgsfield, Sora, Luma Dream Machine), audio/music AI (ElevenLabs, Suno, Udio), chatbots and LLMs (Claude, ChatGPT/GPT-4, Gemini, Llama, Mistral, Perplexity), code AI (GitHub Copilot, Cursor, Windsurf), or any other AI tool. Even triggers for: "write me a prompt for...", "how do I get better results from...", "make X do Y", "optimize this prompt", "why isn't my prompt working", "generate an image of...". Each AI gets its own optimized prompt strategy for maximum output quality.

  • Zk llm design

    tenki-labs/public-claude-skills/plugins/tenki-public-skills/skills/zk-llm-design Skill

    0★ repo

    Use when the user types /zk-llm-design or asks how to add zero-knowledge proofs to an LLM system, "prove model output without revealing weights", "ZK-ML", "verifiable inference", "trustless model serving", or wants help choosing between Halo2, Plonk, STARKs, or FHE for an LLM use case. Walks through threat model, what is being proved, scheme selection, and feasibility for a given model size.

  • Eval refine

    pagoda111king/claude-code-pack/template/.claude/skills/eval-refine Skill

    no license0★ repo

    Eval rubric refinement engine · Solo Founder edition harness-optimizer. Scans all historical eval results (idea-eval / skill eval / agent eval), identifies dimensions where rubrics are too loose or too strict, and drafts adjustment PR drafts to candidates/. Use when founder says "the evaluation feels off" or "5/6 all 100% PASS — is something wrong?"

  • Idea eval

    pagoda111king/claude-code-pack/template/.claude/skills/idea-eval Skill

    no license0★ repo

    6-dimension scoring for product ideas. Use when founder wants to launch a new product/tool. ≥22 = golden idea, 15-21 = workable, <15 = skip. Avoid burning runway on unvalidated ideas.

  • Loadout dev

    missionbuilt/loadout/skills/loadout-dev Skill

    0★ repo

    Expert development partner for The Loadout — the Mission Built MCP server (mcp.missionbuilt.io) that powers The Warmup and The Spotter skills. Use this skill any time you are working on the Loadout project: adding or editing a skill, modifying warmup-template.html or spotter-template.html, changing index.ts tools, bumping versions, editing SKILL.md files, running a tech lead review, or preparing a commit and deploy. Also use it when the user says things like "work on the warmup," "add a new loadout skill," "update the spotter," "edit the template," "bump the version," or "review before we ship." This skill carries the full project architecture, hard-won lessons from past sessions, and the exact collaboration model Mike and Claude use — including the rule that Mike runs all terminal commands and Claude writes all code. DO NOT invoke for end-user requests to RUN the skills — "spot my epic," "run my warmup," "run the approach for [company]" are handled by the MCP tools directly, not by this development skill.

  • Memory load

    ztnkv/personal-operating-system/.claude/skills/memory-load Skill

    0★ repo

    Loads relevant entries from memory/ into the conversation context. Use at the start of any non-trivial conversation, and any time the topic might overlap with what is stored in memory (personal facts, habits, goals, relationships, work, health, hobbies, etc.). Hybrid strategy — always read memory/index.md and memory/tags.md as the map first, then pull full entry bodies by tag match and by semantic match on titles. No artificial cap on how many entries can be loaded.

  • Memory retro

    ztnkv/personal-operating-system/.claude/skills/memory-retro Skill

    0★ repo

    Orchestrator for writes into memory. Analyzes the source (the current conversation OR an external file/text passed as an argument), decides which new facts, changes, contradictions, and deprecations should be recorded in memory/, builds a diff proposal, and confirms it with the user. Only after an explicit "yes" does it call memory-write to apply changes. Triggered four ways — (1) explicit user command ("sum it up", "write down what you learned", "update memory", "/memory-retro"); (2) the agent's own initiative when meaningful new facts or contradictions surface in the dialog; (3) **mandatory auto-run from grill-me** — after a grill session completes, memory-retro always runs without re-asking the user; (4) bootstrap mode for bulk import from an external file (chat history dump, personal notes, session transcript) — fully autonomous, no dialog confirmations, all edge cases resolved by deterministic heuristics with confidence demoted to low as a signal for later review. In normal mode, never writes to memory silently.

  • Memory write

    ztnkv/personal-operating-system/.claude/skills/memory-write Skill

    0★ repo

    Service skill that writes and modifies files in memory/. Invoked ONLY from memory-retro after the user confirmed the proposed diff. Never runs by itself and is not invoked by the user directly. Supports four operations — add (new entry), update (edit existing), supersede (soft delete via status), delete (hard delete, only by an explicit user command). When tags need to be created or updated, cascades into tag-pick.

  • Gemini prompt cache

    baronguyen001/ai-automation-skills/skills/gemini-prompt-cache Skill

    0★ repo

    Cache a long, stable Gemini system-prompt prefix once and reuse the handle across many calls so repeated instruction tokens bill at the cheaper cached rate instead of full input. Use for cache gemini system prompt, context caching, cut gemini input cost, cachedContent, or reuse a long prompt prefix.

  • Pipeline orchestrator

    baronguyen001/ai-automation-skills/skills/pipeline-orchestrator Skill

    0★ repo

    Chain a scrape -> AI -> alert pipeline where each stage is a plain callable, with exponential-backoff retry per stage and a JSON state checkpoint between stages so a crashed or rate-limited run resumes instead of restarting. Use for chain pipeline steps, scrape then summarize then notify, retry between stages, resumable pipeline, or orchestrate a job.

  • Session audit

    dylanmoo/workos-plugin/skills/session-audit Skill

    0★ repo

    Simple end-of-session audit that scans for uncaptured corrections, preferences, and decisions, then proposes saving them to the right workspace file. Use this skill whenever you say 'audit this session,' 'session audit,' 'what did we miss,' or 'end of session check.' Works with any Cowork workspace that has a CLAUDE.md and MEMORY.md in the root folder.

  • Uninit workos

    dylanmoo/workos-plugin/skills/uninit-workos Skill

    0★ repo

    Reverse what /init-workos did, removing only the scaffold files it created and leaving every other document and folder untouched. Use whenever the user says 'uninit workos,' 'undo init-workos,' 'remove the workos scaffold,' 'tear down workos,' 'reset this back,' 'revert init-workos,' or asks to clean up the CLAUDE.md / MEMORY.md / ARCHIVE.md scaffolding without losing their existing content. Identifies scaffold files by a sentinel marker (`workos-init-scaffold v1`) that init-workos writes at the top of every file it creates. Files without the sentinel — including any document the user wrote — are never deleted or modified. When a scaffold file has been edited since init, shows the user what changed and asks before removing.

  • Workspace audit

    dylanmoo/workos-plugin/skills/workspace-audit Skill

    0★ repo

    Audits a WorkOS workspace for drift — misplaced entries, size-ceiling violations, archive candidates, format violations, and engagement-specific content that should cascade to a project. Use when the user says 'workspace audit,' 'audit my workspace,' 'check my CLAUDE.md,' 'check my MEMORY.md,' 'is my workspace healthy,' or when periodically maintaining a WorkOS-style workspace. Distinct from session-audit, which only captures new learnings from the current conversation — this skill audits the workspace files themselves.

  • Luban skill

    PlevanTem/luban-skill/.claude/skills/luban-skill Skill

    0★ repo

    Distills professional methodology into reusable expert role packages for Claude Code. Generates a complete role directory (SOUL.md, SKILL.md, identity.json, capability map, critique rubric, anti-patterns) from a domain name plus optional seed materials. Activates only on explicit invocation by name — "luban" or "鲁班". Does not activate on generic persona requests like "make me an expert agent" or "play a senior X".

  • Motion handoff

    kennykankush/skillpack/plugins/videos/skills/motion-handoff Skill

    no license0★ repo

    Create AI-video motion handoff prompts and keyframe grouping plans from accepted storyboard frames. Use when the user has storyboard images and needs Higgsfield Canvas, Gemini/Omni, Runway, Krea, or another video model to understand frame order, motion intent, clip stitching, and UI stability constraints. Does not generate storyboard frames; pair with videos:storyboard only when new frames are still needed.

  • Max prompt

    kennykankush/skillpack/plugins/workbench/skills/max-prompt Skill

    no license0★ repo

    Turn vague feedback, screenshots, taste, frustration, or half-formed product intuition into an implementation-ready prompt for a coding agent. Use for UI/UX bugs, frontend polish, animation behavior, component architecture, and "it feels wrong but I don't know how to say it" moments.

  • Memory scriber

    kennykankush/skillpack/plugins/workbench/skills/memory-scriber Skill

    no license0★ repo

    Capture a conversation's essence into the active host's memory directory, and recall it back like a colleague - not a database. Use at the tail end of a substantive session ("log this", "memory-scribe this"), progressively during one ("scribe as we go", "checkpoint this"), or in reverse when the user asks "where did we leave off", "what do you remember about this project", "pick up the thread". Supports Codex with a Workbench project-memory convention and Claude Code project memory without assuming the two plugin runtimes share state.

  • Skill distiller

    kennykankush/skillpack/plugins/workbench/skills/skill-distiller Skill

    no license0★ repo

    Distill a successful chat, project workflow, repeated agent behavior, or a way of thinking into a reusable Codex or Claude skill. Use when the user wants to "skillify" a process, capture a reasoning/voice mode that just worked, create a new skill from what just worked, generalize a workflow without overfitting one project, or update a skillpack/plugin with reusable instructions.

  • Headless claude

    iansteitz1-eng/aria-skills/headless-claude Skill

    no license0★ repo

    Run the `claude` CLI fast, hook-free, and unattended for automation — wraps `claude -p` with --setting-sources project (skip your user hooks + heavy auto-memory, ~2s not ~15s), --permission-mode bypassPermissions (no interactive approval prompt that would block a script), and a neutral cwd. Uses your own plan, no API key. Use when the user says "run claude headless", "scriptable claude", "claude -p keeps hanging / prompting", "call claude from a cron/agent", or is automating Claude Code.

  • Kimiskill

    fergus/claude-kimi-delegate/kimiskill Skill

    no license0★ repo

    Triggered when Kimi is invoked via the Claude delegation bridge. Use when the task file indicates from: claude, the prompt mentions delegation mode, or the user is acting as a bridge from Claude Code. This skill sets output conventions, prevents clarifying questions, and ensures results are written to the declared output path.

  • Reactprinciples hook

    sindev08/react-principles-skills/skills/reactprinciples-hook Skill

    0★ repo

    Scaffold a custom React hook following React Principles custom-hooks recipe. Invoke when the user says "create a custom hook", "scaffold a hook", or asks for a hook to encapsulate logic. Generates the hook file with proper naming (use prefix), TypeScript types, a stable return shape, and a colocated test file. Places the hook in src/shared/hooks/ for cross-feature use or src/features/<x>/hooks/ for feature-specific.

  • Handoff outbound

    Build-Your-Sales/data_gouv_mcp_bys/skills/handoff-outbound Skill

    no license0★ repo

    Bridge the data-gouv-bys output to the BYS outbound engine — packages the client brief (CAB-P, recap, 10 ciblages), exports leads from data.gouv into leads.json, and produces the exact commands to run in the outbound engine repo for enrichment + Lemlist sequences. Use after /data-gouv-bys:ciblage when the brief is ready.

  • Ultra

    SashaMarchuk/claude-plugins/plugins/ultra/skills/ultra Skill

    0★ repo

    Backing skill for the /ultra:run and /ultra:resume slash commands — multi-agent swarm with adversarial validation, structured debates, devil's advocate, and anti-AI-slop checks. Users invoke this via /ultra:run (or /ultra:resume); never via a bare /ultra. Supports tiers (--small/--medium/--large/--xl), multi-terminal coordination, and wrapping other skills.

  • Skill budget

    dhruba-datta/claude-papercuts/skills/skill-budget Skill

    0★ repo

    Audit installed Claude Code skills against the system-prompt char budget and show which ones may have silently fallen out of the model's visible list. Use this skill when the user runs /claude-papercuts:skill-budget, asks why their skills stopped triggering, mentions installed-but-invisible skills, or wants a Monday-morning health check of their Claude setup. Runs the audit.py script in this skill's directory and presents the result.

  • Subagent broker

    dhruba-datta/claude-papercuts/skills/subagent-broker Skill

    0★ repo

    Battle-tested Task-tool delegation templates that survive the subagent-delegation pitfalls reported in issues #4182, #5528, and #19077. Use this skill when the user runs /claude-papercuts:subagent-broker, asks how to delegate work to subagents reliably, asks when to use the Task tool, says their subagents ignore configuration or CRITICAL directives, or wants a template for parallel search / independent review / cross-file audit. Runs templates.py to list named delegation patterns and prints the one matching the user's situation.

  • Claude edit

    luck1ncoder/agent-colleague-dashboard/.claude/skills/claude-edit Skill

    0★ repo

    Modify the project's `CLAUDE.md` (or `~/.claude/CLAUDE.md` user-level) based on a natural-language request. Triggered by /claude-edit. Backs up the file, uses the Edit tool (with built-in diff and permission prompt), and invalidates the dashboard cache. Use when the user wants to change the project charter — adding, removing, or rewording principles, rules, or constraints.

  • Dashboard

    luck1ncoder/agent-colleague-dashboard/.claude/skills/dashboard Skill

    0★ repo

    Render agent.md and CLAUDE.md as anthropomorphized HTML profiles. Triggered by /dashboard. Auto-detects layout (Focus for single agent, Team for multiple, CLAUDE.md-only when no agents). Use when user asks to visualize, view, or explain their Claude Code agents and project charter.

  • Claude code content validator

    mercedesperezcapilla-gif/claude-skills/skills/claude-code-content-validator Skill

    0★ repo

    Keeps Claude Code teaching content factually correct against Anthropic's live documentation. Claude Code changes fast, so any course, tutorial, lesson set, or internal guide about it drifts out of date: invented commands, renamed conventions, archived MCP packages, stale model ids. This skill reads your content, checks every Claude Code claim against the current official docs (never from memory), and returns a section-by-section validity report plus the safe fixes. Use before you publish or re-share any Claude Code training material. Works on any course or docs repo.

  • Agent introspection debugging

    bertbertov/claude-stack/skills/agent-introspection-debugging Skill

    0★ repo

    Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

    The same file is in 5 other repositories

  • Agentic actions auditor

    bertbertov/claude-stack/skills/agentic-actions-auditor Skill

    0★ repo

    Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

    The same file is in 3 other repositories

  • Deer flow

    bertbertov/claude-stack/skills/deer-flow Skill

    0★ repo

    Invoke DeerFlow — ByteDance's multi-agent research harness running Claude Sonnet 4.6. Use for deep research tasks, multi-step web research, document analysis, and report generation. Spins up a local LangGraph agent that decomposes the task into sub-agents in parallel. Requires the backend to be running first.

  • Gpt image 2

    bertbertov/claude-stack/skills/gpt-image-2 Skill

    0★ repo

    Generate and edit images using OpenAI's GPT Image 2 API. Interactive skill that guides users through image creation with style presets, cost-aware draft/final workflow, thinking mode, carousels, and photo editing. This skill should be used when the user requests image generation via OpenAI/GPT Image 2, wants to create social media carousels, edit photos into artistic styles, or needs images with readable text (infographics, diagrams, posters).

  • Mcp builder

    bertbertov/claude-stack/skills/mcp-builder Skill

    0★ repo

    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).

    The same file is in 42 other repositories

  • N8n mcp tools expert

    bertbertov/claude-stack/skills/n8n-mcp-tools-expert Skill

    0★ repo

    Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, managing credentials, auditing instance security, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns. IMPORTANT — Always consult this skill before calling any n8n-mcp tool — it prevents common mistakes like wrong nodeType formats, incorrect parameter structures, and inefficient tool usage. If the user mentions n8n, workflows, nodes, or automation and you have n8n MCP tools available, use this skill first.