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
siglernir-ai/codex-claude-handoff/.ai/skills/codex-claude-handoff Skill
0★ repoTurn Codex and Claude Code into an accountable engineering pair for one supervised Git task, with durable local state, configurable roles, independent review by a different agent, bounded correction after rejection, exact-scope verification, fail-closed stops, and user approval gates. Use only when the user selects codex-claude-handoff through /skills, mentions $codex-claude-handoff, names codex-claude-handoff, or explicitly requests the full cross-agent workflow; do not trigger for ordinary project tasks.
siglernir-ai/codex-claude-handoff/templates/.agents/skills/codex-claude-handoff Skill
0★ repoTurn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.
siglernir-ai/codex-claude-handoff/templates/.ai/skills/codex-claude-handoff Skill
0★ repoTurn Codex and Claude Code into an accountable engineering pair for one supervised Git task, with durable local state, configurable roles, independent review by a different agent, bounded correction after rejection, exact-scope verification, fail-closed stops, and user approval gates. Use only when the user selects codex-claude-handoff through /skills, mentions $codex-claude-handoff, names codex-claude-handoff, or explicitly requests the full cross-agent workflow; do not trigger for ordinary project tasks.
siglernir-ai/codex-claude-handoff/templates/.claude/skills/codex-claude-handoff Skill
0★ repoTurn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.
stoicpickle/skillseeking/tests/fixtures/malicious-skills/body-prompt-injection Skill
0★ repoPretends to summarize text.
meyverick/agy-skills/skills/unity-csharp-memory-stripping Skill
0★ repoOptimizes C# script compilation for WebGL, reducing the size of the final compiled WebAssembly binary by minimizing heavy dependencies and GC allocations.
vikenpatel14/cursor-qa-skills/jira-teamwork Skill
no license0★ repoManage JIRA issues, sprints, and boards using the Atlassian MCP server for QA testing workflows. Use when the user mentions JIRA, tickets, issues, sprints, backlog, board, standup, bugs, testing, QA, regression, defects, or wants to create, update, search, or track work items.
rfl-designer/rfl-laravel-skills/skills/setup/setup-rfl-laravel-skills Skill
no license0★ repoBootstrap a Laravel project to use the rfl-laravel-skills plugin — verify prerequisites (gh CLI, Pest, Pint, laravel/boost), create docs/ tree (adr, prd, roadmap, runbooks), seed .claude/<config>.json files for each skill, and add an "Agent skills" block to CLAUDE.md/AGENTS.md. Run ONCE per repo before first use of /grill-with-docs, /to-prd, /to-issues, /open-pr, /organize-docs, or /update-roadmap.
0xdeafcafe/skills/skills/drive-plan Skill
0★ repoUse when the user says "/drive-plan", "drive a plan", "drive this feature end-to-end with planning", "let's build feature X properly", "kick off this change with planning rigour", or asks Claude to drive a substantial change all the way through planning, implementation, and review in one composed workflow. Calls /plan-change interactively to produce ADR + Gherkin spec, then /implement-change to translate spec into code, then /review-change to audit and dispatch fixes via the agent pipeline; recommends /open-pr at the end. Use /drive-plan for substantial changes warranting planning rigour; use /drive-change for quick changes that don't need formal planning; use /drive-pr to iterate an already-open PR. Confirms with the user at each phase boundary because this skill writes a lot of state.
0xdeafcafe/skills/skills/drive-pr Skill
0★ repoUse when the user says "drive this PR", "/drive-pr", asks to resolve all PR comments, get a PR green, address review feedback, or otherwise wants Claude to iterate on an open pull request until every trusted comment is resolved, CI is passing, and the PR description matches the code. Runs /review-pr upfront for a baseline audit (informational by default; pass --audit-blocks to make P0s gate the exit). Code-change comments are batched into synthetic findings and dispatched via the agent pipeline (orchestrate-merge + fix-applier under sensitivity gating) so edits across files apply in parallel. Reply-only comments stay on the existing inline path. GH-specific ops (post replies, resolve threads, monitor CI) remain in the skill. Operates only on the current branch's PR or an explicitly passed PR number/URL.
dsisnero/crystal_forge/skills/crystal-forge-setup-project Skill
no license0★ repoSet up or retrofit a repo with Crystal Forge project scaffolding. Use when a repository lacks `CLAUDE.md`, `AGENTS.md`, baseline docs, or consistent local quality gates.
bitrails-dev/skills/gsd/skills/gsd-eval-review Skill
no license0★ repoRetroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
bitrails-dev/skills/mattpocock/skills/engineering/setup-matt-pocock-skills Skill
no license0★ repoSets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
The same file is in 15 other repositories
bitrails-dev/skills/mattpocock/skills/misc/git-guardrails-claude-code Skill
no license0★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
The same file is in 18 other repositories
bitrails-dev/skills/mattpocock/skills/productivity/handoff Skill
no license0★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 2 other repositories
bitrails-dev/skills/mattpocock/skills/productivity/write-a-skill Skill
no license0★ repoCreate 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
bitrails-dev/skills/mrt-prompt/skills/background-orchestrator Skill
no license0★ repoOrchestrate tasks via fresh-context agents, parallelize independent work, and return only concise synthesized results.
bitrails-dev/skills/mrt-prompt/skills/prompt-refiner Skill
no license0★ repoRefines a prompt into a precise execution brief, decomposes into sub-tasks, executes with parallel agents, and verifies all outputs through self-check and independent verification. WHEN: 'refine and execute', 'run with agents', 'parallel task execution', 'refine prompt', 'execute with verification'
bitrails-dev/skills/mrt-prompt/skills/refactor-prompt Skill
no license0★ repoClassify, analyze, and refactor prompts into optimized instructions with domain-specific enhancement, ambiguity intelligence, and agentic workflow support. WHEN: 'improve this prompt', 'rewrite my prompt', 'optimize this instruction', 'refactor prompt', 'make this prompt better', 'enhance this prompt', 'fix my prompt'
bitrails-dev/skills/mrt-prompt/skills/research-prompt Skill
no license0★ repoRewrite a prompt into a research-grade instruction set optimized for deep analytical exploration
knokmki612/skills/skills/serena-semantic-search Skill
0★ repoTrigger at the moment you are about to grep an identifier (a function/class/method/variable name) to find its definition, references, implementations, or call sites — or about to read a whole source file just to map its structure. Use Serena's language-server-backed read tools for that instead; also for compiler/LSP diagnostics. Needs the Serena MCP server. Literal-text search (strings, error messages, config keys), line-range reads, and file listing stay on the existing grep/sed/Read tools.
danielvogler/ai-skills-library/.agents/skills/adk-debug Skill
0★ repoUse when debugging ADK agents, inspecting sessions, testing agent behavior, troubleshooting tool calls, event flow issues, or diagnosing LLM/model problems.
danielvogler/ai-skills-library/.agents/skills/browser-testing-with-devtools Skill
0★ repoTests 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
danielvogler/ai-skills-library/.agents/skills/configuring-dbt-mcp-server Skill
0★ repoGenerates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
danielvogler/ai-skills-library/.agents/skills/context-engineering Skill
0★ repoOptimizes 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
danielvogler/ai-skills-library/.agents/skills/deep-agents-memory Skill
0★ repoINVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
The same file is in 1 other repository
danielvogler/ai-skills-library/.agents/skills/deep-agents-orchestration Skill
0★ repoINVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
The same file is in 1 other repository
danielvogler/ai-skills-library/.agents/skills/using-agent-skills Skill
0★ repoDiscovers 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
pngdeity/apm-user-repository/packages/agent-architect/.apm/skills/agent-architect Skill
0★ repoArchitect, write, structure, and maintain AI agent context files (AGENTS.md and SKILL.md). Use when creating new agent context configurations, scaffolding AGENTS.md files, designing SKILL.md modules, or determining where content belongs in the agent abstraction stack. Not for writing code or implementing features.
pngdeity/apm-user-repository/packages/ai-agent-orchestration/.apm/skills/ai-agent-orchestration Skill
0★ repoAI agent orchestration design patterns and production workflows. Use when designing multi-agent systems, choosing orchestration strategies (sequential, concurrent, group chat, handoff, magentic), refactoring monolithic agents into coordinated sub-agents, implementing production hardening (structured outputs, RAG pipelines, observability, circuit breakers), or planning multi-agent refactors with verification gates. Not for single-agent tool selection or prompt engineering within one agent.
pngdeity/apm-user-repository/packages/codecompanion/.apm/skills/codecompanion Skill
0★ repoComplete documentation reference for CodeCompanion.nvim, the AI coding plugin for Neovim. Use when the agent needs details about the plugin's features, configuration, commands, adapters, or MCP server setup.
pngdeity/apm-user-repository/packages/custom-skill-creator/.apm/skills/custom-skill-creator Skill
0★ repoMeta-skill for creating and packaging new AI agent skills. Use when requested to create a skill, document a multi-step process, or configure agent behavior as a procedural skill module. Not for single atomic functions or global architecture constraints — those go in AGENTS.md.
pngdeity/apm-user-repository/packages/skill-eval-pipeline/.apm/skills/skill-eval-pipeline Skill
0★ repoOrchestrate end-to-end AI agent skill evaluation — structural validation, trigger testing across opencode and gemini CLI, output quality measurement with graded assertions, and automated revision synthesis. Use when a SKILL.md needs measurable quality verification or when implementing CI/CD quality gates for agent context files.
popsiclelmlm/skills-cn/skills/engineering/setup-matt-pocock-skills Skill
0★ repo在 AGENTS.md/CLAUDE.md 和 `docs/agents/` 中设置 `## Agent skills` block,让 engineering skills 知道该 repo 的 issue tracker(GitHub 或 local markdown)、triage label vocabulary 和 domain doc layout。在第一次使用 `to-issues`、`to-prd`、`triage`、`diagnose`、`tdd`、`improve-codebase-architecture` 或 `zoom-out` 前运行;如果这些 skills 看起来缺少 issue tracker、triage labels 或 domain docs 上下文,也运行它。
popsiclelmlm/skills-cn/skills/misc/git-guardrails-claude-code Skill
0★ repo设置 Claude Code hooks,在危险 git commands(push、reset --hard、clean、branch -D 等)执行前阻止它们。当用户想防止破坏性 git 操作、添加 git safety hooks,或在 Claude Code 中阻止 git push/reset 时使用。
popsiclelmlm/skills-cn/skills/productivity/handoff Skill
0★ repo将当前对话压缩成 handoff document,供另一个 agent 接手。
popsiclelmlm/skills-cn/skills/productivity/write-a-skill Skill
0★ repo创建结构合适、具备 progressive disclosure 和 bundled resources 的新 agent skills。当用户想创建、编写或构建一个新 skill 时使用。
Techtide aws bedrock agent security governor
TechTideOhio/techtide-harness-kit/skills/aws/techtide-aws-bedrock-agent-security-governor Skill
0★ repoReview Amazon Bedrock agents, AgentCore, Guardrails, knowledge bases, action groups, memory, MCP/tool integrations, prompt-injection and prompt-leakage defenses, PII handling, encryption, logging, observability, and least-privilege IAM. Use for AWS-native GenAI and agent security posture.
Techtide aws devops agent skill designer
TechTideOhio/techtide-harness-kit/skills/aws/techtide-aws-devops-agent-skill-designer Skill
0★ repoDesign, review, and improve AWS DevOps Agent-compatible skills, investigation workflows, learned skills, tool-use best practices, agent type targeting, frontmatter descriptions, reference materials, and operational output contracts. Use when creating or adapting skills for AWS DevOps Agent or AWS-style incident agents.
TechTideOhio/techtide-harness-kit/skills/core/core-context-management Skill
0★ repoKeep agent sessions from drifting by packaging concise project context, current state, decisions, and verification results. Use when expanding, reviewing, or operating skills, rules, prompt kits, provider lanes, or generated-code handoffs in the TechTide skill library.
TechTideOhio/techtide-harness-kit/skills/core/core-handoff-readiness-review Skill
0★ repoReview agent session output before it enters the durable TechTide repo by checking provenance, tests, security, deployment boundaries, and rollback expectations. Use when expanding, reviewing, or operating skills, rules, prompt kits, provider lanes, or generated-code handoffs in the TechTide skill library.
TechTideOhio/techtide-harness-kit/skills/core/core-mcp-tool-safety Skill
0★ repoReview agent tool and MCP usage for credential scope, network egress, mutation risk, logging, and human approval gates. Use when expanding, reviewing, or operating skills, rules, prompt kits, provider lanes, or generated-code handoffs in the TechTide skill library.
Core multi agent orchestration
TechTideOhio/techtide-harness-kit/skills/core/core-multi-agent-orchestration Skill
0★ repoCoordinate agents with each other by splitting work into bounded scopes, clear contracts, integration checks, and review gates. Use when expanding, reviewing, or operating skills, rules, prompt kits, provider lanes, or generated-code handoffs in the TechTide skill library.
TechTideOhio/techtide-harness-kit/skills/core/core-prompt-hardening Skill
0★ repoHarden agent prompts so the work has explicit scope, constraints, data states, guardrails, and validation evidence. Use when expanding, reviewing, or operating skills, rules, prompt kits, provider lanes, or generated-code handoffs in the TechTide skill library.
Techtide nvidia agentic ai platform review
TechTideOhio/techtide-harness-kit/skills/nvidia/techtide-nvidia-agentic-ai-platform-review Skill
0★ repoUse this skill when reviewing agentic-AI platforms built on the NVIDIA stack - NeMo Agent Toolkit, NIM-as-tool patterns, retrieval-augmented generation pipelines, tool-call safety, agent memory boundaries, and per-tenant audit logging. Trigger when the user asks whether agent tool calls are sandboxed, whether agent memory is tenant-scoped, whether tool definitions are signed, or whether the deployment meets NCP-AAI expectations.
Techtide nvidia tensorrt llm deployment review
TechTideOhio/techtide-harness-kit/skills/nvidia/techtide-nvidia-tensorrt-llm-deployment-review Skill
0★ repoUse this skill when reviewing TensorRT or TensorRT-LLM deployment artifacts statically - ONNX/PyTorch export pipelines, precision selection (FP16/BF16/INT8/FP8/INT4), calibration cache integrity, dynamic shape profiles, custom plugin loading, engine cache and serialized engine provenance, runtime memory pool sizing. Trigger when the user asks whether a TensorRT build script, calibration pipeline, or trtexec invocation follows NVIDIA's published guidance.
Techtide oci compute instance agent operator
TechTideOhio/techtide-harness-kit/skills/oci/techtide-oci-compute-instance-agent-operator Skill
0★ repoOperate OCI Compute Instance Agent commands and executions safely for diagnostics, automation, and remediation. Use when issuing, tracking, or reviewing instance-agent commands across compute fleets.
Techtide oracle oci mcp grounded advisor
TechTideOhio/techtide-harness-kit/skills/oci/techtide-oracle-oci-mcp-grounded-advisor Skill
0★ repoUse this skill when the user asks about Oracle MCP servers, SQLcl MCP, OCI MCP, Oracle Database agent access, OCI automation, or cloud/database advice that must be grounded in official Oracle sources.
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-agent-autopsy-report Skill
0★ repoPerform post-run analysis of failed or risky agent work by reconstructing goal, context, tool calls, failure mode, missing guardrails, and preventive skill updates. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide ai tool decision router
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-ai-tool-decision-router Skill
0★ repoRoute development work to Cursor, Claude Code, Codex, Lovable, v0, Replit, or a human approval lane based on scope, blast radius, context size, and verification needs. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide cursor claude codex workflow router
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-cursor-claude-codex-workflow-router Skill
0★ repoCoordinate Cursor, Claude Code, and Codex across a coding task so inline edits, repo reasoning, tests, and final review happen in the right lane. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide design stack research synthesizer
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-design-stack-research-synthesizer Skill
0★ repoSynthesize design-tool research into practical app-building guidance across Stitch, Figma, Claude Code, v0, Lovable, and repo-native frontend implementation. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide knowledge ingestion guardrail review
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-knowledge-ingestion-guardrail-review Skill
0★ repoReview knowledge ingestion pipelines for source provenance, chunking, embedding, search behavior, redaction, access control, and evidence traceability. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide lovable production handoff
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-lovable-production-handoff Skill
0★ repoConvert a Lovable prototype into a repo-owned production candidate by extracting code, documenting assumptions, replacing mocks, and adding tests and deployment gates. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide mcp tool trust review
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-mcp-tool-trust-review Skill
0★ repoReview MCP servers, tool connectors, and agent tool surfaces for trust boundaries, credential scope, network egress, mutation risk, logging, and approval gates. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide multi agent worktree dispatch
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-multi-agent-worktree-dispatch Skill
0★ repoSplit substantial engineering work across agents or worktrees with disjoint ownership, clear contracts, validation checkpoints, and integration review. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide prompt to architecture extractor
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-prompt-to-architecture-extractor Skill
0★ repoConvert rough prompts, transcripts, and prototype notes into architecture decisions, constraints, interfaces, data flows, and implementation-ready work packages. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
Techtide v0 ui prompt hardener
TechTideOhio/techtide-harness-kit/skills/techtide/techtide-v0-ui-prompt-hardener Skill
0★ repoShape v0 UI prompts into implementable, accessible, responsive interface specifications with explicit data states, constraints, and handoff checks. Use when an agent needs Alex Cinovoj / TechTide live-coding patterns, tool routing, guarded prototype-to-production workflows, or cross-harness prompt/skill adapters.
mukiwu/hyday-skills/skills/hyday-whiteboard Skill
0★ repoCreate, edit, list, query, inspect, and lay out Hyday whiteboards through the hyday-whiteboard MCP server. Use whenever the user adds, modifies, moves, deletes, lists, or asks about whiteboard cards, sticky notes, groups, or connections — or wants to inspect what's on a board, build a layout from existing notes, or organize notes visually — or mentions whiteboard, canvas, board, sticky note, group. Common triggers: "幫我做張白板", "列出我的白板", "把這幾篇筆記放上白板", "白板上有什麼", "整理筆記成白板". Requires the `hyday-whiteboard` MCP server to be configured (see installation below).
marktantongco/opencodelinux/skills/agent-ui Skill
no license0★ repoBatteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop