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
Destynova2/cli-code-skills/cli-forge-quorum Skill
5★ repoGenerate a Byzantine-fault-tolerant multi-agent orchestration using the REC-Quorum pattern (Reflect/Execute/Control with adaptive quorums, tickets pré-signés, leaderless execute, view-change timeouts). Use when a brigade-style orchestrator has stalled on a single-leader bottleneck, when deterministic decision quality is required (SLA/compliance/incident-response), when the team has > 5 agents with parallelism, or when operators mention 'BFT agents', 'REC-Quorum', 'deterministic consensus', 'threshold signatures', 'quorum adaptatif', 'view-change', 'leaderless execute', 'Byzantine orchestration'. Upgrade path from cli-forge-chef when Brigade stalls or requires formal audit trail.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-claude-code-conventions Skill
5★ repoProvides canonical engineering standards for authoring agents, skills, hooks, and pipeline orchestration in Claude Code. Use when authoring or modifying agents, skills, hooks, or pipeline-orchestration artifacts — covers model-tier selection, prompt-cache discipline, frontmatter schemas, and progressive-disclosure rules.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-dynamic-routing Skill
5★ repoMaps pipeline agent roles to intent-based model categories on Tier 1 (Claude Code). Use when a Tier 1 pipeline stage requires model assignment beyond the two-slot fast/deep abstraction — e.g., pure read-only audit agents, deep architectural planners, or visual-analysis roles. Non-CC tiers resolve models via platform_profile.model_tiers only; this skill must not be invoked on tier_1b/1c/1d/2.
gustavo-meilus/superpipelines/plugins/superpipelines/skills/sk-worktree-safety Skill
5★ repoEnforces a mandatory 4-step safety protocol (Ignore, Setup, Baseline, Commit) for creating, managing, and destroying git worktrees in pipeline isolation contexts. Use when a pipeline step declares `isolation: worktree`, when parallel pattern tasks require branch isolation, or when the iterative or spec-driven patterns require atomic rollback capability.
Verification before completion
gustavo-meilus/superpipelines/plugins/superpipelines/skills/verification-before-completion Skill
5★ repoEnforces the Iron Law — no completion claim without fresh verification evidence. Use when an agent is about to claim work is complete, a bug is fixed, or a system state is passing; before committing changes or opening PRs; or after receiving a subagent DONE report that has not been independently verified.
gustavo-meilus/superpipelines/skills/sk-claude-code-conventions Skill
5★ repoProvides canonical engineering standards for authoring agents, skills, hooks, and pipeline orchestration in Claude Code. Use when authoring or modifying agents, skills, hooks, or pipeline-orchestration artifacts — covers model-tier selection, prompt-cache discipline, frontmatter schemas, and progressive-disclosure rules.
gustavo-meilus/superpipelines/skills/sk-dynamic-routing Skill
5★ repoMaps pipeline agent roles to intent-based model categories on Tier 1 (Claude Code). Use when a Tier 1 pipeline stage requires model assignment beyond the two-slot fast/deep abstraction — e.g., pure read-only audit agents, deep architectural planners, or visual-analysis roles. Non-CC tiers resolve models via platform_profile.model_tiers only; this skill must not be invoked on tier_1b/1c/1d/2.
gustavo-meilus/superpipelines/skills/sk-worktree-safety Skill
5★ repoEnforces a mandatory 4-step safety protocol (Ignore, Setup, Baseline, Commit) for creating, managing, and destroying git worktrees in pipeline isolation contexts. Use when a pipeline step declares `isolation: worktree`, when parallel pattern tasks require branch isolation, or when the iterative or spec-driven patterns require atomic rollback capability.
Verification before completion
gustavo-meilus/superpipelines/skills/verification-before-completion Skill
5★ repoEnforces the Iron Law — no completion claim without fresh verification evidence. Use when an agent is about to claim work is complete, a bug is fixed, or a system state is passing; before committing changes or opening PRs; or after receiving a subagent DONE report that has not been independently verified.
sergeyklay/.agents/.agents/skills/context-files Skill
5★ repoCreate or validate project context files (AGENTS.md, CLAUDE.md, GEMINI.md). Use when bootstrapping a new project, initializing agent configuration, writing a context file, or when asked to create, review, audit, or validate an existing context file. Handles codebase archaeology, user interviews, golden-rule validation, and platform-specific formatting. Do NOT use for creating Agent Skills, rules or .instructions.md files.
sergeyklay/.agents/.agents/skills/make-skill Skill
5★ repoUse when creating, improving, comparing, evaluating, reviewing or packaging Agent Skills following the agentskills.io specification. Also use when deciding whether a skill is the right solution vs MCP servers, Claude Rules Files, CLAUDE.md or AGENTS.md. Handles SKILL.md authoring, frontmatter optimization, description writing, progressive disclosure, platform targeting, invocation control, vendor-specific extensions, and distribution.
klovaaxel/web-a11y-agent-skills/skills/web-a11y-orchestrator Skill
5★ repoCentral routing and orchestration skill for web accessibility work. Use as the default entrypoint for accessibility-related UI tasks to select the right authoring, review, remediation, and testing workflows.
IncommensurableHubris/fullstack-director/.agents/skills/status Skill
5★ repoThe project's read-only 'where am I / what's next' oracle - scans the artifact chain, INTEGRITY-CHECKS the spine, counts the governance blockers 06-release gates on, DERIVES live state, and routes the NEXT COMMAND. READ-ONLY with respect to truth: never edits the spine or realizations; the only writes are two generated views, keeping docs/spec/** byte-identical. SEQUENTIAL - no subagents (a single derive-only read). Graded value: the DETERMINISTIC verdict (PASS, or FAIL naming the REQ-ID), pending/deferred amendment + [NEEDS CLARIFICATION] counts, and the routed next command. Use when the user says 'status', 'where are we', or 'what's next', or at session start. Reads docs/spec/** and the artifact chain + git state. Writes ONLY CLAUDE.md Current State + AGENTS.md. Do NOT plan/design/architect/build/review/ship/secure/refactor - it ROUTES to the owning skill. Do NOT edit the spine to fix findings - an integrity FAIL is REPORTED (repair via /00-discovery), never silently corrected.
uwuclxdy/agenticat/skills/docs-sync Skill
5★ repoReconciles `README`, `docs/*`, `CLAUDE.md`, and agent/skill/plugin prompt files with what the code does: stale, missing, or overpromising claims; verifies quoted commands/flags/paths. Use when a change alters documented behavior, a tool's output shape changes, or to sweep all docs.
uwuclxdy/agenticat/skills/handoff Skill
5★ repoSome of my Agents & Skills, compatible with most AI coding tools
UK Environmental Intelligence MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-environmental-intelligence MCP server
no license5★ repoAccess UK flood warnings, river levels, water quality, Met Office forecasts, and carbon data
UK Legislation MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-legislation MCP server
no license5★ repoSearch UK Acts, Statutory Instruments, and legislation with full text retrieval
UK Parliament MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-parliament MCP server
no license5★ repoSearch MPs and Lords, fetch profiles, synopses, and Westminster constituencies
UK Petitions MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-petitions MCP server
no license5★ repoSearch UK Parliament petitions, view signatures, government responses, and debate outcomes
UK Planning Data MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-planning MCP server
no license5★ repoSearch UK planning applications, entities, datasets, and conservation areas
UK Air Quality MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-air-quality MCP server
no license5★ repoAccess UK air quality data, monitoring sites, and hourly pollutant measurements across regions
UK Property & Business Intelligence MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-property-business MCP server
no license5★ repoSearch UK companies, land registry prices, charities, OS locations, and traffic data
Agent Interviews MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/agent-interviews MCP server
no license5★ repoAgent Interviews is an AI-powered research platform designed to conduct qualitative interviews an...
UK Court Finder MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-court-finder MCP server
no license5★ repoFind UK courts and tribunals by location, name, or law area with addresses and contacts
UK Police MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-police MCP server
no license5★ repoAccess street-level crime reports, stop and search data, and outcomes across UK police forces
UK Civic & Parliamentary Data MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-civic-parliamentary MCP server
no license5★ repoQuery UK Parliament, elections, crime stats, ONS census data, and national archives
UK Public Services & Health MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-public-services-health MCP server
no license5★ repoAccess CQC care ratings, NHS health services, and food hygiene data across the UK
UK Constituencies MCP Server from MCPBundles
thinkchainai/mcpbundles/com.mcpbundles/uk-constituencies MCP server
no license5★ repoSearch UK parliamentary constituencies by name, get boundaries and ONS codes
aernouddekker/macos-mcp/io.github.aernouddekker/mailappmcp MCP server
5★ repoMCP server for macOS Mail.app — gives Claude native email access via AppleScript
aernouddekker/macos-mcp/io.github.aernouddekker/numbersmcp MCP server
5★ repoMCP server for macOS Numbers.app — spreadsheet access via AppleScript
aernouddekker/macos-mcp/io.github.aernouddekker/printmcp MCP server
5★ repoMCP server for macOS printing — wraps CUPS (lp/lpstat/lpoptions) for printer discovery and printing
aernouddekker/macos-mcp/io.github.aernouddekker/remindersmcp MCP server
5★ repoMCP server for macOS Reminders.app — list and reminder management via AppleScript
aernouddekker/macos-mcp/io.github.aernouddekker/contactsmcp MCP server
5★ repoMCP server for macOS Contacts.app — contact management via AppleScript
arifulislamat/database-mcp/io.github.arifulislamat/database-mcp-mysql MCP server
5★ repoMCP server for MySQL. Read-only by default, row caps, statement timeouts, secrets never logged.
arifulislamat/database-mcp/io.github.arifulislamat/database-mcp-mariadb MCP server
5★ repoMCP server for MariaDB. Read-only by default, row caps, timeouts, secrets never logged.
arifulislamat/database-mcp/io.github.arifulislamat/database-mcp-postgres MCP server
5★ repoMCP server for PostgreSQL. Read-only by default, row caps, timeouts, secrets never logged.
doc2mcp/doc2mcp/io.github.doc2mcp/lightfield MCP server
5★ repoMCP server for lightfield documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/developer MCP server
5★ repoMCP server for developer documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/cavalry MCP server
5★ repoMCP server for cavalry documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/opencode MCP server
5★ repoMCP server for opencode documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/stocksense-ai MCP server
5★ repoMCP server for stocksense-ai documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/sunpeak MCP server
5★ repoMCP server for sunpeak documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/tabletopsimulator MCP server
5★ repoMCP server for tabletopsimulator documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/manus MCP server
5★ repoMCP server for manus documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/uagents MCP server
5★ repoMCP server for uagents documentation, generated by doc2mcp.
doc2mcp/doc2mcp/io.github.doc2mcp/langchain MCP server
5★ repoMCP server for langchain documentation, generated by doc2mcp.
VersoXBT/claude-initial-setup/skills/agent-patterns/agent-communication Skill
4★ repoPatterns for inter-agent communication including message passing, shared state, event-driven architectures, pub/sub, inbox/outbox, and structured vs freeform messages. Use when the user is building systems where multiple agents need to communicate, share information, coordinate work, or pass data between processing stages.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/agent-patterns/context-management Skill
4★ repoStrategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage large amounts of information within limited context windows.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/agent-patterns/multi-agent-orchestration Skill
4★ repoPatterns for multi-agent systems including orchestrator, pipeline, consensus, delegation, supervisor, and swarm patterns. Use when the user is building multi-agent workflows, coordinating multiple AI agents, implementing agent delegation or supervision, or designing systems where agents collaborate on complex tasks.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/claude-api/prompt-engineering Skill
4★ repoPrompt engineering patterns for Claude including system prompts, few-shot examples, chain-of-thought, structured output, templates, and prefilling. Use when the user is writing prompts, designing system instructions, extracting structured data, building prompt templates, or optimizing Claude responses for quality and consistency.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/claude-api/tool-use-patterns Skill
4★ repoPatterns for Claude tool use including tool definition schemas, multi-tool orchestration, parallel tool calls, error handling, and result formatting. Use when the user is defining tools for Claude, building agentic workflows with tool calling, handling tool errors, or implementing multi-step tool pipelines.
The same file is in 2 other repositories
VersoXBT/claude-initial-setup/skills/hooks/hook-recipes Skill
4★ repoReady-to-use hook recipes for common Claude Code automation: prettier on edit, tsc check, console.log warning, git push review, doc blocker. Use when the user wants a specific hook example, asks "how do I auto-format" or "block markdown creation", or needs a hook for a common development workflow.
VersoXBT/claude-initial-setup/skills/mcp-development/mcp-resource-patterns Skill
4★ repoPatterns for MCP resources including URIs, templates, subscriptions, dynamic resources, context provision, and MIME types. Use when the user is exposing data as MCP resources, designing resource URIs, implementing resource templates with parameters, setting up resource subscriptions, or providing context to Claude through resources.
VersoXBT/claude-initial-setup/skills/mcp-development/mcp-server-creation Skill
4★ repoGuide for creating MCP (Model Context Protocol) servers in TypeScript and Python, including scaffolding, transports, lifecycle hooks, and testing. Use when the user wants to build an MCP server, add tools/resources/prompts to an MCP server, configure stdio or SSE transport, or test MCP server functionality.
VersoXBT/claude-initial-setup/skills/mcp-development/mcp-tool-design Skill
4★ repoBest practices for designing MCP tools including naming conventions, input schemas, error responses, pagination, idempotency, and descriptions. Use when the user is designing tools for an MCP server, writing tool schemas, handling tool errors, or needs guidance on tool naming and input validation patterns.
VersoXBT/claude-initial-setup/skills/memory-management/memory-patterns Skill
4★ repoPatterns for structuring MEMORY.md and topic-based memory files for Claude Code persistent memory. Use when the user asks about remembering things across sessions, wants to organize project knowledge, or needs guidance on what to save vs not save.
irfad7/claude-power-skills/skills/coordinator-mode Skill
4★ repoWhen the user has a complex task that would benefit from multiple agents working in parallel or in sequence. Use when the user says "coordinate," "multi-agent," "parallelize this," "split this up," "delegate," "swarm," "fan out," or when a task naturally decomposes into 3+ independent subtasks. Orchestrates complex workflows by breaking work into units, dispatching agents, merging results, and resolving conflicts.
irfad7/claude-power-skills/skills/prompt-speculation Skill
4★ repoUse proactively after completing any task to suggest logical next steps. Also use when the user seems unsure what to do next, says "what now," "what else," "what should I do," "what's next," "continue," or pauses after a milestone. Anticipates what the user likely needs next based on context and proactively offers actionable suggestions.
josephneumann/claude-corps/skills/summarize-session Skill
4★ repoUse for a read-only progress snapshot without committing, pushing, or closing anything
hereinthehive/kickstart/.claude/skills/onboarding Skill
no license4★ repoSet up Claude Code for this project — interviews you, builds CLAUDE.md and settings, then has the curator subagent review everything before handing off