agentsclimarketplace

Context & AI engineering

25,745 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

  • Benchmark sandbox

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/.claude/skills/benchmark-sandbox Skill

    5★ repo

    Run vercel-plugin eval scenarios in Vercel Sandboxes instead of local WezTerm panels. Provisions ephemeral microVMs with Claude Code + plugin pre-installed, runs benchmark prompts, extracts hook artifacts, and produces coverage reports.

  • Benchmark testing

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/.claude/skills/benchmark-testing Skill

    5★ repo

    Create and launch benchmark test projects to exercise vercel-plugin skill injection across realistic scenarios. Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts.

  • Vercel plugin eval

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/.claude/skills/vercel-plugin-eval Skill

    5★ repo

    Run live eval sessions against the vercel-plugin to verify hook behavior, skill injection, dedup correctness, and coverage. Launches real Claude Code sessions via WezTerm, monitors debug logs, and produces a structured coverage report.

  • Agent browser verify

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/agent-browser-verify Skill

    5★ repo

    Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.

  • Agent browser

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/agent-browser Skill

    5★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.

  • Upstream

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/agent-browser/upstream Skill

    5★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

  • Ai sdk

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/ai-sdk Skill

    5★ repo

    Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

  • Vercel agent

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/vercel-agent Skill

    5★ repo

    Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.

  • Vercel api

    build-with-dhiraj/ai-workflow-framework-portability-kit/Plugins/vercel-marketplace-source/skills/vercel-api Skill

    5★ repo

    Vercel MCP and REST API expert guidance. Use when the agent needs live access to Vercel projects, deployments, environment variables, domains, logs, or documentation through the MCP server or REST API.

  • Arize prompt optimization

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/arize-prompt-optimization Skill

    5★ repo

    Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.

  • Building claude portability kit

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/building-claude-portability-kit Skill

    5★ repo

    Snapshot Claude Code setup (agents, skills, plugins, MCP, tooling) into a portable folder. Use for backup or Mac migration.

  • Seo dataforseo

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/claude-seo/extensions/dataforseo/skills/seo-dataforseo Skill

    5★ 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".

    The same file is in 1 other repository

  • Seo dataforseo

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/claude-seo/skills/seo-dataforseo Skill

    5★ 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".

    The same file is in 1 other repository

  • Dspy gepa reflective

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/dspy-gepa-reflective Skill

    5★ repo

    This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA optimizer", "LLM reflection", "execution trajectories", "agentic systems optimization", or needs to optimize complex multi-step agents using textual feedback on execution traces.

  • Eval audit

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/eval-audit Skill

    5★ repo

    Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).

  • Evaluate rag

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/evaluate-rag Skill

    5★ repo

    Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating synthetic QA pairs for retrieval testing, or optimizing chunking strategies.

  • Evaluating agent behavior

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/evaluating-agent-behavior Skill

    5★ repo

    Build agent behavioral evals — tool choice, steerability, constraint compliance. Triggers on "behavioral eval".

  • Flutter embedding native views

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/flutter-embedding-native-views Skill

    5★ repo

    Embed native Android, iOS, or macOS views in a Flutter app. Use for maps, web views, complex native components.

  • Git guardrails claude code

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/git-guardrails-claude-code Skill

    5★ repo

    Set up Claude Code hooks blocking dangerous git commands (push, reset --hard, clean, branch -D) before execution.

  • Langsmith evaluator

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/langsmith-evaluator Skill

    5★ repo

    INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.

  • Llm eval

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/llm-eval Skill

    5★ repo

    Build LLM eval suites, run prompt regression tests, score AI outputs with deepeval. Triggers on "eval this prompt", "build eval suite", "hallucination check".

  • Loop engineering

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/loop-engineering Skill

    5★ repo

    Design and operate loop-engineered agent systems in Claude Code and Cursor. Use for loop engineering, harness design, Ralph loops, /loop, /goal, agent hub, self-improving agents, SKILL.md optimization, or choosing installable loop tooling from the research corpus.

  • Memory router

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/memory-router Skill

    5★ repo

    Decides whether new information should be stored in the Obsidian vault (RAM — mutable, evolving content) or in Pinecone (HD — immutable, archive-shaped content) for D Rage's JoVE knowledge system. Apply BEFORE creating any new artifact in the JoVE vault, BEFORE upserting anything to Pinecone, or BEFORE running deep-research that produces a non-trivial output. Also use when the user asks "where should this go?", "should I save this?", or any variant of routing intent — even if they don't mention Obsidian or Pinecone by name. Built on Karpathy LLM-Wiki + Jack Roberts dual-layer memory pattern.

  • Obsidian brain eval

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/obsidian-brain-eval Skill

    5★ repo

    Test your Obsidian RAG, measure your second brain's retrieval quality, and score your vault on Recall@10 against a gold-set generated from your own notes. Pluggable retrieval backends (BM25 zero-infra, LanceDB hybrid FTS+vector). Pure Python CLI, read-only. The skill is the only tool that publishes a methodology and a default 0.85 pass/fail threshold for "is your vault chat actually working". Use when the user asks any of: test my obsidian rag, measure my second brain, is my pkm answering well, obsidian retrieval quality, test my obsidian search, recall at 10 my vault, evaluate my obsidian rag, obsidian rag benchmark, score my obsidian retrieval, is my second brain working, obsidian search quality, pkm retrieval eval, obsidian eval framework, gold set obsidian, smart connections eval, obsidian copilot eval, rag over my vault, does my vault chat work, vault retrieval test. Works on any markdown vault using wikilinks (Obsidian, Logseq, Foam, Quartz). Complements obsidian-graph-auditor (measures graph topology); brain-eval measures retrieval quality.

  • Prompt engineering

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/prompt-engineering Skill

    5★ repo

    Design, iterate, or debug LLM prompts — system prompts, few-shot, chain-of-thought, tool-use, eval rubrics. Triggers on "write a better prompt", "improve this prompt".

  • Rag patterns

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/rag-patterns Skill

    5★ repo

    Build RAG pipelines — vector DB + LLM, document Q&A, chunking/embedding strategies. Triggers on 'build RAG', 'document Q&A', 'retrieval pipeline', 'embed and search'.

  • Supabase

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/supabase Skill

    5★ repo

    Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).

  • Token coach

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/token-coach Skill

    5★ repo

    Context window coach — token-efficiency guidance for Claude Code/Codex, multi-agent systems, and skill architecture.

  • Write a skill

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/write-a-skill Skill

    5★ repo

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    The same file is in 20 other repositories

  • Write judge prompt

    build-with-dhiraj/ai-workflow-framework-portability-kit/Skills/write-judge-prompt Skill

    5★ repo

    Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

  • Optimize memory allocation

    zystem-io/zymtrace-skills/zymtrace/skills/optimize-memory-allocation Skill

    5★ repo

    Analyze JVM memory-allocation profiles with zymtrace — find what allocates the most (bytes/objects), why GC is busy, and where allocation churn is burning CPU. **Java/JVM only** — zymtrace memory-allocation profiling is supported for the JVM; non-Java workloads have no allocation profile. The zymtrace MCP pulls the allocation rankings + flamegraph (the allocation dimension); YOU analyze — name the hot allocation sites and the pattern (autoboxing, String churn, collection resizing, large arrays/buffers, per-request object graphs), then recommend AND apply the fix in the user's source (ask for the path if it isn't local) and close with a follow-up. Use when allocation rate / garbage collection is the concern on a Java service, or when a CPU profile turned out allocation/GC-bound (the CPU skill hands off here). **Allocation profiling is opt-in** — if the Java service has no allocation profile yet, this skill enables it first (ask the user for target/sampling/JVMTI inputs; apply via the agent-config MCP or `POST /public/api/v1/agent/config/set`, or a profiler flag), then analyzes; docs: https://docs.zymtrace.com/allocation-profiling. NOT for GPU memory (use optimize-gpu-workloads), NOT for non-JVM CPU work (use optimize-cpu-workloads), and NOT for OOMKilled / crash diagnosis (that's troubleshoot-zymtrace-profiler / troubleshoot-zymtrace-backend). Trigger phrases: "what's allocating the most memory", "analyze the JVM allocation profile", "java/JVM memory allocations", "JVM allocation hot spots", "why is GC so busy/high", "reduce GC pressure", "too much garbage collection", "allocation churn", "what's creating the most objects/garbage", "JVM memory allocation flamegraph", "reduce heap churn", "which Java code allocates the most", "enable/turn on/set up allocation profiling".

  • Openplan core

    BANANASJIM/openplan-skill/skills/openplan-core Skill

    5★ repo

    Apply OpenPlan philosophy as a platform-neutral agent operating protocol. Use when Codex, Claude Code, or another coding agent must preserve OpenPlan-style principles without depending on project-specific enforcement tools: minimal effective context, human-owned decisions, dispatcher/subagent boundaries, evidence-backed state, separation of roles, authority flow from goal/intent and design to execution, reversible automation, and no silent approval.

  • Openplan garden

    BANANASJIM/openplan-skill/skills/openplan-garden Skill

    5★ repo

    Inspect and improve documentation quality using OpenPlan-style document gardening. Use when Codex or Claude Code must check memory, docs, design notes, handoff snapshots, review reports, specs, or generated documentation for goal/intent drift, broken structure, missing rationale, stale claims, duplicated content, unclear authority, poor future-agent readability, zero-context comprehension gaps, or periodic documentation maintenance. This skill is platform-neutral and read-only by default; local link checkers and linters are optional evidence sources, not required gates.

  • Openplan handoff

    BANANASJIM/openplan-skill/skills/openplan-handoff Skill

    5★ repo

    Create a minimal OpenPlan-style handoff snapshot for cross-agent or cross-session continuity. Use when work must move between Codex, Claude Code, subagents, reviewers, auto/YOLO runs, or compacted sessions while preserving minimal context, human decisions, dual-surface state, evidence, blockers, next safe action, and residual risk. This skill creates handoff artifacts; it does not approve or continue the work itself.

  • Openplan operate

    BANANASJIM/openplan-skill/skills/openplan-operate Skill

    5★ repo

    Initialize and run an OpenPlan-style agent session on Codex, Claude Code, or another agent platform. Use after openplan-core when a task needs startup discipline, behavior constraints, subagent delegation rules, mode selection, dual-surface awareness, or safe auto/YOLO execution before alignment, research, design, implementation, testing, or review. This skill is platform-neutral and treats enforcement checks as optional evidence, not prerequisites.

  • Openplan record

    BANANASJIM/openplan-skill/skills/openplan-record Skill

    5★ repo

    Organize, update, and reconcile memory and documentation as human goal/intent records in an OpenPlan-style workflow. Use when Codex or Claude Code must classify or propose what belongs in memory, docs, handoff snapshots, review reports, or temporary briefs; when consolidating user preferences, project philosophy, design decisions, workflow constraints, or lessons learned; or when preventing agent inference from being recorded as the human goal/intent. This skill is for goal/intent preservation and documentation maintenance, not code implementation.

  • Openplan review

    BANANASJIM/openplan-skill/skills/openplan-review Skill

    5★ repo

    Review automated or YOLO-mode agent output using OpenPlan philosophy without requiring project-specific enforcement tools. Use for Codex or Claude Code automated review flows when changes, plans, generated docs, specs, code patches, skill/plugin artifacts, or multi-agent workflow results must be checked for minimal context, human decision boundaries, layered authority, role/mode separation, research-before-design, evidence-backed findings, reversible automation, and no silent approval. This is a read-only review skill, not an implementation or auto-fix skill.

  • Openplan test

    BANANASJIM/openplan-skill/skills/openplan-test Skill

    5★ repo

    Design, run, and report a proportional OpenPlan-style test evidence framework. Use when Codex, Claude Code, or another agent must choose test layers, prove regression tests are meaningful, separate fast checks from privileged or expensive checks, compare implementation behavior with fixtures/oracles/properties, or report tests run/skipped without treating passing tests as approval.

  • Mb for user delegation

    jthingelstad/mb/skills/mb-for-user-delegation Skill

    5★ repo

    Use this skill when acting on behalf of a human user with mb. It teaches consent boundaries, voice preservation, cautious social behavior, and how to manage a user's micro.blog presence without flattening it into generic assistant output.

  • Aoa eval

    8Dionysus/aoa-skills/skills/core/engineering/aoa-eval Skill

    5★ repo

    Select or apply an owner-local or cross-repository eval, route a confirmed no-fit to intake/design, or classify supplied session hits as eval candidates. Use aoa-evals for central proof bundles, named results or verdicts, reports, and lifecycle. Do not use for ordinary tests, undefined invariants, or generic session harvesting.

  • Promptkitty author agent instructions

    baldaworks/promptkitty/cli/assets/opencode/skills/promptkitty-author-agent-instructions Skill

    5★ repo

    Turn a fully assembled PromptKit prompt into ready-to-commit project instructions or a provider-native subagent profile. Use when the user asks to create persistent agent guidance, custom agent instructions, an agent profile, a subagent, or equivalent files for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, or Cursor.

  • Promptkitty author agent instructions

    baldaworks/promptkitty/plugins/promptkitty/prefixed-skills/promptkitty-author-agent-instructions Skill

    5★ repo

    Turn a fully assembled PromptKit prompt into ready-to-commit project instructions or a provider-native subagent profile. Use when the user asks to create persistent agent guidance, custom agent instructions, an agent profile, a subagent, or equivalent files for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, or Cursor.

  • Author agent instructions

    baldaworks/promptkitty/plugins/promptkitty/skills/author-agent-instructions Skill

    5★ repo

    Turn a fully assembled PromptKit prompt into ready-to-commit project instructions or a provider-native subagent profile. Use when the user asks to create persistent agent guidance, custom agent instructions, an agent profile, a subagent, or equivalent files for Codex, Claude Code, Grok Build, GitHub Copilot, OpenCode, or Cursor.

  • Agentic workflow designer

    rshade/finfocus/.github/skills/agentic-workflow-designer Skill

    5★ repo

    Conversational skill that interviews users to design new agentic workflows

  • Agentic workflows

    rshade/finfocus/.github/skills/agentic-workflows Skill

    5★ repo

    Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

  • Aipom eval scorecard builder

    deanpeters/ai-product-operating-model-skills/skills/aipom-eval-scorecard-builder Skill

    no license5★ repo

    Define calibrated AI evaluation metrics, rubrics, judges, thresholds, sampling, uncertainty, ownership, and decision rules tied to behavior and consequences.

  • Workflow orchestrator

    stefanoskarakasis/Product-Marketing-Skills/pmm-go-to-market/skills/workflow-orchestrator Skill

    5★ repo

    Orchestrates multi-skill PMM programs end-to-end — chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps, and retros into one coherent program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive program", "new market entry program", "full PMM onboarding", or any request for a multi-step PMM initiative that spans more than one skill.

  • Claude subagent creator

    BjornMelin/dev-skills/plugins/claude-core/skills/claude-subagent-creator Skill

    no license5★ repo

    Author, validate, and install custom Claude Code subagents as .claude/agents Markdown files. Use when the user asks to create a subagent, custom agent, or .claude/agents role; define a reusable reviewer, explorer, planner, or worker persona; set an agent's model or tool allowlist; or turn a recurring workflow into a delegatable role. Produces Markdown agent files with YAML frontmatter (name, description, model, tools) plus a focused system-prompt body, scoped to the smallest tool surface that does the job (read-only by default). Covers naming, description wording for autonomous delegation, model policy (Opus for reasoning/review, inherit for scans), tool scoping, project vs user scope, and a smoke test. Pairs with fan-out, which delegates to these roles. Not for one-off ad-hoc delegation (use fan-out) or authoring Agent Skills (SKILL.md files).

  • Agents md maintainer

    BjornMelin/dev-skills/skills/agents-md-maintainer Skill

    no license5★ repo

    AGENTS.md maintenance rules for deciding when durable repo guidance should be updated after implementation.

  • Ai sdk agents

    BjornMelin/dev-skills/skills/ai-sdk-agents Skill

    no license5★ repo

    Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep, callOptionsSchema/prepareCall, dynamic tool selection, tool loops, or agent workflows (sequential, routing, evaluator-optimizer, orchestrator-worker). Triggers: ToolLoopAgent, agent loop, stopWhen, stepCountIs, prepareStep, callOptionsSchema, prepareCall, hasToolCall, InferAgentUIMessage, agent workflows.

  • Ai sdk core

    BjornMelin/dev-skills/skills/ai-sdk-core Skill

    no license5★ repo

    Expert guidance for AI SDK Core: text generation, structured data, tool calling (tool/dynamicTool), MCP integration (createMCPClient, Experimental_StdioMCPTransport), embeddings/reranking, provider setup, middleware, telemetry, and error handling. Use when building with generateText/streamText, generateObject/streamObject, tools (needsApproval, strict, inputExamples, activeTools, toolChoice, experimental_context), embeddings (embed/embedMany/rerank), or MCP tools/resources/prompts/elicitation.

    The same file is in 1 other repository

  • Codex sdk

    BjornMelin/dev-skills/skills/codex-sdk Skill

    no license5★ repo

    Architect-level guidance, workflows, and scripts for building agentic coding systems with OpenAI Codex. Use for Codex SDK (@openai/codex-sdk) threads + streaming JSONL events; Codex CLI automation (codex exec, output schema, JSONL, resume); MCP server usage (codex mcp-server) and dynamic tool integration; multi-agent orchestration with OpenAI Agents SDK (handoffs, gating, tracing); durable state, caching, and memory using SQLite; safe-by-default sandbox/approval patterns and execpolicy rules.

    The same file is in 4 other repositories

  • Kimi ui agent

    BjornMelin/dev-skills/skills/kimi-ui-agent Skill

    no license5★ repo

    Explicit-only Kimi-powered frontend/UI orchestration skill and CLI for repo profiling, design-system context generation, Codex/Kimi Code/Claude Code adapter setup, plan-first git worktree runs, status/reply/finalize lifecycle control, and review artifacts. Use only when the user explicitly invokes `$kimi-ui-agent` or asks to use Kimi UI Agent for frontend/UI audits, redesigns, components, screenshots, implementation planning, or worktree orchestration.

  • Langgraph multiagent

    BjornMelin/dev-skills/skills/langgraph-multiagent Skill

    no license5★ repo

    Architect-level development, audit, and migration of multi-agent systems using LangGraph (v1+) and LangChain (v1+). Use when building or refactoring supervisor/subagent architectures, orchestrator-worker workflows, routing/hand-offs, agentic RAG, memory (short + long-term), state + context engineering, guardrails + human-in-the-loop, MCP tool integration, observability (LangSmith/OpenTelemetry), deployment, and performance/cost optimization — or when migrating off deprecated patterns like `langgraph.prebuilt.create_react_agent` and libraries like `langgraph-supervisor(-py)`, LlamaIndex agents, CrewAI, Agno, or OpenAI Agents.

  • Subagent creator

    BjornMelin/dev-skills/skills/subagent-creator Skill

    no license5★ repo

    Create, validate, install, and smoke-test Codex custom subagents from TOML templates. Use for ~/.codex/agents or project .codex/agents roles, subagent templates, model and sandbox defaults, or reusable agent packs.

  • Subspawn

    BjornMelin/dev-skills/skills/subspawn Skill

    no license5★ repo

    Bounded subagent delegation and synthesis. Use for explicit subagent, delegation, fan-out, spawn policy, custom agent routing, wait behavior, and evidence-first synthesis.

  • Navigate

    alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/navigate Skill

    5★ repo

    Routes ambiguous mechanism comparisons to the smallest appropriate agent mechanism and skill. Use when the user is unsure whether they need instructions, a prompt, skill, subagent, hook, scheduler, MCP, plugin, Claude workflow, or Codex workflow; if the artifact is already selected, its specialist skill wins.

  • Prompt

    alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/prompt Skill

    5★ repo

    Improves, rewrites, or designs concise prompts with clear outcomes, context, boundaries, output requirements, and verification. Use for direct requests such as “improve this prompt,” for Claude or Codex task formulation, weak-response troubleshooting, or turning a rough objective into a ready-to-run task.

  • Skill

    alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/skill Skill

    5★ repo

    Turns a repeated workflow into one narrow, reusable, validated agent skill with reliable triggers and progressive disclosure. Use when the user asks to create, revise, split, review, or test a SKILL.md workflow for Claude, Codex, or another Agent Skills-compatible surface; not when the request is to distribute a bundle as a plugin.

  • Subagent

    alessiomarcone/agent-fieldbook/plugins/knowledge-pack/skills/subagent Skill

    5★ repo

    Decides whether selected delegated work needs agents and designs a strict, product-correct subagent contract with isolated context, bounded tools, authority, deliverables, and tests. Use when the user asks to create, configure, delegate to, or troubleshoot Claude or Codex subagents, parallel agents, custom agents, or managed-agent workflows; not for open mechanism comparisons.