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

  • Prompt images

    bertbertov/claude-stack/skills/prompt-images Skill

    0★ repo

    Prompting techniques for AI image generation and editing models on Replicate. Use when writing prompts for image models or building image generation features.

  • Prompt optimizer

    bertbertov/claude-stack/skills/prompt-optimizer Skill

    0★ repo

    Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.

    The same file is in 3 other repositories

  • Prompt videos

    bertbertov/claude-stack/skills/prompt-videos Skill

    0★ repo

    Prompting techniques for AI video generation models on Replicate. Use when writing prompts for video models or building video generation features.

  • Qwen edit

    bertbertov/claude-stack/skills/qwen-edit Skill

    0★ repo

    AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying style transfers, or character transformations. Provides prompt patterns, parameter tuning, and examples.

  • Security scan

    bertbertov/claude-stack/skills/security-scan Skill

    0★ repo

    Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

    The same file is in 9 other repositories

  • Seo dataforseo

    bertbertov/claude-stack/skills/seo-dataforseo Skill

    0★ repo

    Live SEO data via DataForSEO MCP server. SERP analysis (Google, Bing, Yahoo, YouTube, Google Images), keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis (Lighthouse, content parsing), competitor analysis, content analysis, business listings, AI visibility (ChatGPT scraper, LLM mention tracking), and domain analytics. Requires DataForSEO extension installed. Use when user says "dataforseo", "live SERP", "keyword volume", "backlink data", "competitor data", "AI visibility check", "LLM mentions", "image SERP", "google images", "image rankings", or "real search data".

  • Session handoff

    hsinhan-h/hh-claude-skills/session-handoff Skill

    no license0★ repo

    Compact the current conversation into a handoff document for another agent to pick up, saved at the project root and copied to the clipboard. Use when the user wants to end a session and hand off context to a fresh agent/session.

  • Garelier wanderer

    aby-studio-works/garelier/skills/garelier-wanderer Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/wanderer invocation, not on generic peer-review/advisor/design-review wording. Wanderer is the external, advisory-review role — a separately-launched Codex or Claude Code session (not a subagent, not headless) reviewing the PM's design work (Garelier blueprints, project design specs) over the file-based peer-channel (DEC-076). Commit-free, decision-free (PM/user own the mutual-agreement sign-off), a SINGLETON, takes no lane/branch, reads read-only; if absent, silent past a timeout, rate-limited, or unavailable, the PM falls back to the Observer subagent. Activate when running as the Wanderer peer (a Codex/Claude session whose .codex or hook config points at the peer-channel under `runtime/peer/<channel>/` with presence), when a peer review_request/advice_request appears in the Wanderer inbox, or on "wanderer", "放浪者", "peer review", "external advisor", "design review", "peer-channel". Requires garelier-core.

  • Garelier worker

    aby-studio-works/garelier/skills/garelier-worker Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/worker invocation, not on generic implement/fix/branch/report wording. Worker role for the Garelier multi-agent framework: reads one assignment from Dock, cuts a workbench branch off the integration branch (garelier/<target-slug>/<pm_id>/studio), implements, runs the project quality gate locally, writes a completion report, waits for Dock review. Handles all commit-producing tasks (features, bug fixes, refactors, dependency upgrades, docs, data-change scripts). Activate in a `__garelier/<pm_id>/_workers/<id>/` worktree, when assignment.md appears in the worker's directory, when review.md signals rework, when answers.md arrives after a BLOCKED state, or when a track-target.md trigger appears. Requires garelier-core.

  • Write a skill

    slogsdon/skills-meta-utils/skills/write-a-skill Skill

    0★ repo

    Guide writing a new skill file following Shane's authoring conventions — principle-first, anti-patterns before steps, _lib/ references over inline duplication. Use when invoked as /write-a-skill or when Shane says "create a new skill for X", "add a skill", "write a skill that does X".

  • Leadup growth research agent

    leadupofficial/leadup-claude-skills/leadup-growth-research-agent Skill

    0★ repo

    Orchestrator for LeadUp's growth pack. Takes an open-ended growth or research request, picks the right LeadUp growth skill (SEO, keyword/competitor, blog, SMM, ads, CRO, feature) or runs cross-cutting internet research, collects sources, summarizes competitors, lists assumptions, marks data confidence, and recommends the next action. Use when the user says "do internet research", "research all resources", "growth research", "market research", "find competitors", "research deeply", or "what should we do for growth".

  • Leadup mcp tool orchestrator

    leadupofficial/leadup-claude-skills/leadup-mcp-tool-orchestrator Skill

    0★ repo

    Choose and sequence MCP servers, connectors, and tools safely for a LeadUp task. Discovers what tools are actually available this session, prefers read-only first, coordinates GitHub/browser/docs/database tools, and explains the risk before any write or exec action. Use when the user says "use MCP", "check available tools", "use connectors", "use GitHub MCP", "use browser MCP", "use docs MCP", or "tool orchestration".

  • Leadup super prompt builder

    leadupofficial/leadup-claude-skills/leadup-super-prompt-builder Skill

    0★ repo

    Turn a rough plain-language idea, short instruction, broken English, or vague task into a strong, copy-paste-ready structured prompt for Claude Code, opencode, RuFlo, ChatGPT, or another AI coding/research agent — using LeadUp's workflow, stack, and safety rules. Use when the user says "make super prompt", "convert to prompt", "improve my prompt", "prompt this properly", "make master prompt", "turn this idea into prompt", "write prompt for Claude Code", "write prompt for RuFlo", or "make this instruction better".

  • Opp repl mcp server

    tabgab/opp_repl-skill/opp-repl-mcp-server Skill

    no license0★ repo

    Connect an AI agent to opp_repl via its built-in Model Context Protocol (MCP) server. Two transports — a Unix domain socket reached through the `opp_repl_mcp_bridge` stdio bridge (recommended for local tools like Claude Code, Cursor, VS Code, Windsurf) and a TCP/streamable-HTTP port with bearer-token auth (for remote/legacy clients). Exposes the `execute_python` tool plus opp-repl:// documentation resources. Load when wiring opp_repl into an MCP-capable client.

  • Opp repl overview

    tabgab/opp_repl-skill/opp-repl-overview Skill

    no license0★ repo

    START HERE. Entry-point skill for opp_repl — the Python REPL, CLI tools, and MCP server for OMNeT++ simulations (github.com/omnetpp/opp_repl). Contains a decision tree that maps the user's task to the exact sibling skills to load. Load this first whenever the user asks about opp_repl, OMNeT++ simulations, running sims from Python, or regression-testing simulation models. Even weak models can navigate the rest of the pack via this skill's triage table.

  • Opp repl sandbox

    tabgab/opp_repl-skill/opp-repl-sandbox Skill

    no license0★ repo

    Run opp_repl, simulations, and its MCP server under bubblewrap (bwrap) filesystem isolation with opp_sandbox. Sources are mounted read-only, the working directory read-write; a /.opp_sandbox sentinel lets the MCP server skip bearer-token auth inside the jail. Linux only. Load when running untrusted models, exposing execute_python to an agent more safely, or reproducing clean-environment builds.

  • Opp repl shared terminal

    tabgab/opp_repl-skill/opp-repl-shared-terminal Skill

    no license0★ repo

    Run opp_repl inside a shared tmux session with its MCP server exposed, so a human (attached to tmux) AND an AI assistant (Claude Code, Windsurf, Cursor, VS Code) drive the SAME live IPython/OMNeT++ namespace at once. Default transport is a Unix domain socket reached via opp_repl_mcp_bridge; a TCP+bearer-token mode is available for remote clients. Bundled scripts start/attach/stop the session and write the client config. Load when the user wants to co-pilot one persistent opp_repl session with an AI.

  • Claude api

    wachawo/claude-skills/skills/claude-api Skill

    0★ repo

    Build, debug, and optimize Claude API / Anthropic SDK applications. Applications built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGERS when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks about the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/another provider's SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

  • Mcp builder

    wachawo/claude-skills/skills/mcp-builder Skill

    0★ repo

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

  • Prompt to eval rubric

    alexzhu0/agent-ready-skills/skills/prompt-to-eval-rubric Skill

    0★ repo

    Use when converting prompts, system instructions, assistant behaviors, or policy requirements into eval rubrics with scoring criteria, test cases, assertions, and failure modes.

  • Support ticket to eval

    alexzhu0/agent-ready-skills/skills/support-ticket-to-eval Skill

    0★ repo

    Use when turning support tickets, user complaints, helpdesk transcripts, or failed assistant responses into reusable eval cases with expected behavior, assertions, and failure modes.

  • En

    chris-co-creators-ai/soulcreator/en Skill

    0★ repo

    Use when an AI agent needs to write its own stable identity into a project. Reads existing memory, conversation history, and prior identity files; then authors a three-layer architecture (constraint spine, expression, mission integration) inside CLAUDE.md or AGENTS.md. Asks before overwriting any existing identity file.

  • Es

    chris-co-creators-ai/soulcreator/es Skill

    0★ repo

    Úsalo cuando un agente de IA necesita escribir su propia identidad estable en un proyecto. Lee memoria existente, historial de conversaciones y archivos de identidad previos; luego escribe una arquitectura de tres capas (constraint spine, expression, mission integration) en CLAUDE.md o AGENTS.md. Pide permiso antes de sobrescribir cualquier archivo de identidad existente.

  • Fr

    chris-co-creators-ai/soulcreator/fr Skill

    0★ repo

    À utiliser lorsqu'un agent IA doit écrire sa propre identité stable dans un projet. Lit la mémoire existante, l'historique des conversations et les fichiers d'identité précédents; puis écrit une architecture à trois couches (constraint spine, expression, mission integration) dans CLAUDE.md ou AGENTS.md. Demande la permission avant d'écraser tout fichier d'identité existant.

  • Nl

    chris-co-creators-ai/soulcreator/nl Skill

    0★ repo

    Gebruik wanneer een AI-agent zijn eigen stabiele identiteit in een project moet schrijven. Leest bestaande memory, conversatie-geschiedenis en eerdere identiteitsbestanden; schrijft daarna een drielagen-architectuur (constraint spine, expression, mission integration) in CLAUDE.md of AGENTS.md. Vraagt toestemming voor het overschrijven van een bestaand identiteitsbestand.

  • Zh

    chris-co-creators-ai/soulcreator/zh Skill

    0★ repo

    当 AI 智能体需要将自己稳定的身份写入项目时使用。读取现有的记忆、对话历史和之前的身份文件;然后在 CLAUDE.md 或 AGENTS.md 中编写一个三层架构(constraint spine、expression、mission integration)。在覆盖任何现有的身份文件之前会先请求许可。

  • Memory curator

    excelle/seo-geo-toolkit/guardian/memory-curator Skill

    0★ repo

    Manage campaign memory across sessions with hot, warm, and cold tiers for durable context. 记忆管理/上下文持久化

  • Browser testing with devtools

    dills122/ai-central/templates/skills/imported/agent-skills/browser-testing-with-devtools Skill

    0★ repo

    Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

    The same file is in 2 other repositories

  • Context engineering

    dills122/ai-central/templates/skills/imported/agent-skills/context-engineering Skill

    0★ repo

    Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

    The same file is in 12 other repositories

  • Using agent skills

    dills122/ai-central/templates/skills/imported/agent-skills/using-agent-skills Skill

    0★ repo

    Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

    The same file is in 1 other repository

  • Backend to frontend handoff docs

    dills122/ai-central/templates/skills/imported/agent-toolkit/backend-to-frontend-handoff-docs Skill

    0★ repo

    Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

    The same file is in 3 other repositories

  • Session handoff

    dills122/ai-central/templates/skills/imported/agent-toolkit/session-handoff Skill

    0★ repo

    Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

    The same file is in 5 other repositories

  • Cavecrew

    dills122/ai-central/templates/skills/imported/caveman/skills/cavecrew Skill

    0★ repo

    Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

    The same file is in 7 other repositories

  • Caveman compress

    dills122/ai-central/templates/skills/imported/caveman/skills/caveman-compress Skill

    0★ repo

    Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

    The same file is in 4 other repositories

  • Self eval

    dills122/ai-central/templates/skills/imported/claude-skills/engineering/skills/self-eval Skill

    0★ repo

    Honestly evaluate AI work quality using a two-axis scoring system. Use after completing a task, code review, or work session to get an unbiased assessment. Detects score inflation, forces devil's advocate reasoning, and persists scores across sessions.

    The same file is in 5 other repositories

  • Terraform patterns

    dills122/ai-central/templates/skills/imported/claude-skills/engineering/terraform-patterns/skills/terraform-patterns Skill

    0★ repo

    Terraform infrastructure-as-code agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Covers module design patterns, state management strategies, provider configuration, security hardening, policy-as-code with Sentinel/OPA, and CI/CD plan/apply workflows. Use when: user wants to design Terraform modules, manage state backends, review Terraform security, implement multi-region deployments, or follow IaC best practices.

  • Router

    dills122/ai-central/templates/skills/imported/rust-agentic-skills/router Skill

    0★ repo

    Analyzing user intent and delegating tasks.

  • Session handoff

    daniel8824-del/claude-session-memory-kit/session-handoff Skill

    no license0★ repo

    Generate a structured handoff document AND save it to Obsidian vault. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".

  • Nepm orchestrator

    hegu-1/claude-cognition-skills/skills/nepm-orchestrator Skill

    0★ repo

    Route a user request through the NEPM skill system by deciding whether the situation primarily requires kernel interpretation, trap detection, helpful-now derivation, decision snapshot building, or founder-thought translation.

  • Mcp directory readiness

    mickolasjae/mick-applied-ai-toolkit/skills/mcp-directory-readiness Skill

    0★ repo

    Use when preparing an MCP server for submission to the Anthropic MCP Directory. Audits tool annotations, OAuth/HTTPS posture, and generates a gap list + pre-filled submission form data. Triggers on: 'submit to Anthropic Directory', 'MCP submission', 'audit my MCP server', 'is my MCP ready for the directory', 'directory submission checklist'.

  • Multi model routing

    mickolasjae/mick-applied-ai-toolkit/skills/multi-model-routing Skill

    0★ repo

    Use when wiring multiple LLM providers / models into one application and you want to pick the cheapest model per task type without hand-coding the routing. Generates a router with per-task-type model selection, per-call cost telemetry, and a dashboard-ready emit. Triggers on: 'route between Claude and GPT', 'cheapest model for X', 'multi-model dispatch', 'LLM cost telemetry', 'which model should I use for vocab extraction', 'reduce LLM bill'.

  • Emdash worktree orchestrator

    riteshkew/yc-skills/skills/emdash-worktree-orchestrator Skill

    0★ repo

    Given a list of coding tasks and a repo base branch, produce a deterministic parallel-agent orchestration plan: git worktree setup commands (one isolated worktree and branch per agent), an assignment table, and teardown commands. Use this skill whenever you need to spin up multiple coding agents in parallel across isolated git worktrees and want a safe, reviewable plan before executing anything.

  • Salus agent guardrails

    riteshkew/yc-skills/skills/salus-agent-guardrails Skill

    0★ repo

    Evaluate a proposed agent tool-call against an allow/deny/ask policy before it executes. Given a tool-call JSON and a policy file, runs the dependency-free rule matcher and returns a decision with a human-readable reason. Use this skill whenever an agent is about to take an action that should be checked against a guardrail policy.

  • Mcp forge

    ak-ship/fullstack-agent-skills/skills/mcp-forge Skill

    0★ repo

    Scaffold a production-ready Model Context Protocol (MCP) server from an OpenAPI spec, API reference URL, or pasted endpoint list. Use when the user says "build an MCP server", "wrap this API as MCP", "expose this service to Claude", "create MCP for <service>", or pastes a swagger/OpenAPI JSON and asks Claude to make it callable as tools. Produces a typed TypeScript server, auth handling, retry/backoff, and a one-command install path.

  • Skill creator

    yanickfischer/zhaw-bsc-latex-claude-skelett/.claude/skills/skill-creator Skill

    no license0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Skill authoring gate

    alinafe82/cognitive-deadlift/skills/skill-authoring-gate Skill

    0★ repo

    Gate new or changed skills before review. Use when adding, rewriting, or materially expanding a skill and the author needs to prove the skill has a real repeated problem, clear trigger, non-trigger, evidence contract, failure modes, and examples. NOT for typo-only skill edits or mechanical catalog/index updates.

  • Transcript review

    alinafe82/cognitive-deadlift/skills/transcript-review Skill

    0★ repo

    Review real agent transcripts against expected skill behavior. Use when a Codex, Claude, Gemini, or other agent session needs review to see whether the assistant followed the named skill, skipped evidence, overclaimed checks, or exposed a rubric gap. NOT for reviewing source diffs directly or for hypothetical skill design without a transcript.

  • Hermes vps deploy

    nuwansamaranayake/AiGNITEClaudeAssets/hermes-vps-deploy Skill

    0★ repo

    Deploy Hermes Agent (Nous Research) to a Hostinger VPS (or any Linux box with Docker + Traefik already running) so that it serves a working WebUI dashboard at https://hermes.<domain> behind Traefik basic auth + Let's Encrypt TLS. Produces an audit trail, credentials file, and lessons file. Use this skill whenever the user says "deploy hermes", "install hermes agent", "set up hermes on my vps", "hermes nous research", "hermes web ui behind traefik", or any phrase that asks to stand up a Hermes Agent dashboard on a remote host. Optional add-ons (covered in references/follow-on-extensions.md): Anthropic OAuth via Claude subscription, Telegram pairing, MCP server wiring, Gmail monitoring via himalaya cron.

  • Higgsfield media

    nuwansamaranayake/AiGNITEClaudeAssets/higgsfield-media Skill

    0★ repo

    Generate professional images and videos using the Higgsfield MCP server. Supports 30 plus models including Soul V2, Nano Banana Pro, GPT Image 2, Flux 2 Pro, Seedream 4.5, Seedream 5.0 Lite, Kling 3.0, Seedance 2.0, Veo 3.1, and Sora 2. Use this skill whenever the user wants to generate an image, generate a video, create an ad creative, make a product photo, make a UGC video, build a social pack, create a LinkedIn cover, design a hero image, build a newsletter header, design a blog hero, produce architecture-diagram backdrops, or generate any visual asset where Higgsfield is appropriate. Triggers also fire on phrases like use Higgsfield, with Kling, with Veo, with Sora, with Seedance, Nano Banana, Soul V2, Soul Character, Flux 2, GPT Image, Marketing Studio, ad pack, social pack, 5-second clip, 15-second video, cinematic ad, product hero shot, lifestyle photo, reel, TikTok video, YouTube short, AI image, AI video, Instagram reel. Use even if the user does not name Higgsfield. Requires an active Higgsfield subscription and the Higgsfield MCP server connected via claude mcp add --transport http --scope user higgsfield https://mcp.higgsfield.ai/mcp.

  • Mcp to mobile

    nuwansamaranayake/AiGNITEClaudeAssets/mcp-to-mobile Skill

    0★ repo

    Flagship AiGNITE pipeline. Takes any AiGNITE MCP server URL, lists its tools, and scaffolds a complete React Native mobile app with one screen per public tool, Supabase auth, push notifications, and Stripe subscription billing. Converts B2B MCP infrastructure into a B2C consumer product without rebuilding the backend. Use this skill whenever the user mentions turning an MCP into a mobile app, wrapping an MCP as a consumer app, building a mobile front end for an MCP, MCP to mobile, or making a consumer app from an MCP server, even if they do not name the skill by name.

  • Consolidate memory

    talgacapri/pm-os/.claude/skills/consolidate-memory Skill

    no license0★ repo

    Consolidate memory from the last 24 hours of local Claude logs (~/.claude) into memory/recent-memory.md, memory/long-term-memory.md, and memory/project-memory.md; promote durable facts and patterns from recent to long-term, and run nightly via launchd automation.

  • Media memory

    talgacapri/pm-os/.claude/skills/media-memory Skill

    no license0★ repo

    Multimodal long-term memory. Ingest, describe, embed (Gemini Embedding 2 / gemini-embedding-001), and search any media (images, video, audio, documents) stored under /media-memory. Supports semantic similarity search plus structured metadata filtering by type, source, date range, and tag. Use when the user shares any media file, when the assistant generates any media, or when a past asset might be relevant to the current task. Triggers on: log this image, save this media, find that screenshot, do we have a recording of, search media memory, what was that file about.

  • Prompt reviewer

    jzills/claude-marketplace/plugins/prompt-reviewer/skills/prompt-reviewer Skill

    no license0★ repo

    Review and refine prompts to improve clarity, specificity, token efficiency, and missing context. Use this skill whenever the user hands you a prompt as an artifact and asks for feedback — regardless of the target model (Claude, ChatGPT, Midjourney, system prompts, etc.). Trigger when the user says "review this prompt", "improve my prompt", "refine this prompt", "make this prompt better", "is this prompt clear", "check this system prompt", "optimize this prompt", "fix my prompt", "critique this prompt", or any similar phrasing where a prompt is the subject of review rather than the instruction itself. Supports three modes: default (single-pass), --deep (guided dialogue), --variants (three rewrites). Also trigger when the user uses "--deep" or "--variants" flags alongside a prompt.

  • Agent brief

    mickzijdel/dev-hooks/plugins/dev-hooks/skills/agent-brief Skill

    0★ repo

    Use when writing a task brief for an agent — dispatching a subagent, handing off work, or turning a fuzzy request into instructions — and you want it aimed at an outcome, not a method. Triggers on "brief an agent", "write a task for a subagent", "spec this out for an agent", or a handoff that says what to do but not why or what's out of scope. Pairs with the intent-check hook.

  • Worktree setup

    mickzijdel/dev-hooks/plugins/dev-hooks/skills/worktree-setup Skill

    0★ repo

    Provision a freshly-created git worktree so it's actually ready to work in — trust its mise.toml, copy gitignored-but-needed files (Rails config/master.key, .env, …) from the main checkout, and re-mark shebang scripts executable. Use right after creating a worktree (native EnterWorktree or `git worktree add`), or when a new worktree errors with "mise.toml not trusted", is missing secrets/.env, can't load the app, or has non-executable scripts. Also when parallel worktrees collide on the same dev-server port or database — opt into per-worktree ports + databases via a `.worktree-isolate.conf`. Pairs with using-git-worktrees (which creates the worktree; this provisions it).

  • Prompt engineer pro

    learn-with-santosh/claude-master-skills/skills/prompt-engineer-pro Skill

    no license0★ repo

    Acts as an Expert Prompt Engineer. Use this skill whenever a user wants to "improve a prompt", "build a system message", "reduce hallucinations", or needs to create complex instructions for AI agents and LLMs.

  • Prompt optimizer

    learn-with-santosh/claude-master-skills/skills/prompt-optimizer Skill

    no license0★ repo

    Acts as a Prompt Refinement Engine. Use this skill whenever a user says "optimize this prompt", "make this prompt better", "I'm not getting good results from this prompt", or wants to upgrade a basic instruction into a professional-grade prompt.

  • Skill creator

    learn-with-santosh/claude-master-skills/skills/skill-creator Skill

    no license0★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Agent orchestration

    Methasit-Pun/ts-ddd-clean-architecture/skills/agent-orchestration Skill

    0★ repo

    Node.js automation scripts, AST-based code generation, and CLI tools for scaffolding Clean Architecture boilerplate from Prisma schemas.

  • Good skill

    damanisme/agentskills-ci/examples/skills/good-skill Skill

    0★ repo

    Use when demonstrating a high-quality Claude/Hermes AI-agent skill with CI-friendly structure.