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
VectorPeak/vectorpeak-agent-skills/knowledge-skills/github-clippings-vp Skill
2★ repoConvert one or many GitHub repository, pull request, issue, discussion, commit, or code URLs into structured LLM_wiki GitHub raw-corpus Markdown. Use when the user invokes $github-clippings-vp, provides GitHub URL batches, asks to save GitHub material into 01.raw/10.GitHub, build GitHub source cards, organize repo/PR/issue URLs, or create engineering-case notes for later LLM/code-agent reference.
selic/skills/skills/mcp-server-review Skill
2★ repoReview an MCP (Model Context Protocol) server for tool-design quality: tool naming and granularity, description/annotation accuracy, input schema strictness, output token budgets, error handling, and role/permission safety. Produces a prioritized findings list, not a rewrite. Use when reviewing, auditing, or hardening an MCP server or its tool definitions. Triggers on: review my MCP server, audit MCP tools, MCP tool design, are my tool descriptions good, MCP server quality.
selic/skills/skills/publish-mcp-server Skill
2★ repoPublish and distribute an MCP server — npm packaging, official MCP registry (mcp-publisher/server.json), Claude Desktop MCPB bundle, GitHub release automation, and directory listings (Glama, Docker MCP Catalog, Cline, awesome-mcp-servers). Use when asked to publish, release, distribute, or list an MCP server, or to prepare one for public distribution.
selic/skills/skills/release-mcp-version Skill
2★ repoCut and publish a NEW version of an MCP server that already has its distribution pipeline set up — lockstep version bump across package.json/server.json/manifest.json, land on main, tag, and let CI publish to npm + the official MCP registry + a GitHub release (.mcpb) + a container image. Use when asked to release/ship/publish a new version, cut a release, or "bump and publish" an MCP server. For FIRST-TIME distribution setup use publish-mcp-server instead. Triggers on: "release a new version", "publish vX.Y.Z", "cut a release", "bump the version and publish", "ship the new version".
Ken-Technology/cold-email-skills/prompt-writer Skill
2★ repoGenerate AI personalization prompts for cold email campaigns. Reads the AI variables from a campaign strategy and outputs detailed prompts you can run in any personalization tool or LLM to tailor each email per prospect. Use after campaign strategy, or when creating prompts for an existing sequence. Triggers on "write prompts for this campaign", "generate personalization prompts".
bogdanbaciu21/skills/chat-analysis Skill
2★ repoAnalyze Codex or Claude Code session transcripts for failure patterns and propose agent-instruction improvements. Runs the four-stage pipeline (parse → filter → label → compile) via scripts/chat_analysis.py. Use when the user says "analyze my chats", "run chat analysis", "review my sessions", "what am I doing wrong", "chat analysis", or "/chat-analysis".
bogdanbaciu21/skills/deep-research-agents Skill
2★ repoUse Dan's paid deep-research providers as one capability: Claude Managed Agent, Gemini Deep Research, Parallel.ai, Exa, and Firecrawl Research Index. Trigger when the user asks for deep research, a research harness, multi-angle research fan-out, five angles, Workflow tool unavailable, Gemini API deep research, Claude managed agent research, Parallel.ai research, or wants the same research methodology to work across repos such as dans-brain and bogdanbaciu-dot-com.
bogdanbaciu21/skills/handoff Skill
2★ repoSummarize the current session's work into a structured handoff block and a saved markdown artifact that a fresh coding-agent session can execute on, including Codex, Claude Code, a VPS shell, or another local environment. Use whenever the user says "handoff", "hand off", "pass to next session", "wrap up for handoff", "session summary for next chat", "continue in new chat", or anything about transferring context to a new conversation or environment. Also use when the user is about to end a session with unfinished work. Includes the GitHub issue reference if one exists. Do NOT use for PR descriptions, commit messages, or release notes — those summarize code changes for reviewers, not session state for the next agent. Do NOT use to dispatch parallel agents — that's `parallel-dispatch`.
bogdanbaciu21/skills/parallel-dispatch Skill
2★ repoGenerate copy-paste agent prompts and a coordinator playbook from a pre-built parallel work plan, or turn a cheap design dispute into competing "code wins" implementation variants. Use when the user has decomposed a large task into independent, conflict-free parallel tracks and needs formatted prompts for multiple coding-agent sessions; or when the user says "parallel dispatch", "parallel agents", "dispatch tracks", "multi-agent", "generate agent prompts", "code wins", "build competing implementations", or "settle this by building variants". Optionally layers in per-runner insight-lock capture (condensed into one cross-track insight memo at the end) and end-of-run pagecraft polish for HTML deliverables. Do NOT use to invent a decomposition from scratch, to author handover documents, or to launch/monitor agents. Do NOT use for single-session sub-agent delegation via the Agent tool — this is for spinning up separate coding-agent sessions.
bogdanbaciu21/skills/weekly-update Skill
2★ repoDraft a weekly stakeholder update for any software project. Use when the user asks for a weekly update, Friday email, status report, sprint summary, or stakeholder progress report. Pulls commits from git and issue counts from the project's tracker (GitHub Issues by default; Linear or Jira when an MCP server, API token, or CLI is available), asks a short set of clarifying questions, and produces a draft markdown file in docs/weekly-updates/. Optionally renders an HTML email using a brand template if one is configured.
Context engineering memory design
jukrap/ai-agent-playbook/skills/ai-harness/context-engineering-memory-design Skill
2★ repoUse when designing or reviewing agent instructions, context surfaces, prompt/cache budget, project memory, compaction behavior, durable memory promotion, or stale fact handling.
jukrap/ai-agent-playbook/skills/ai-harness/mcp-server-design Skill
2★ repoUse when designing or changing MCP tools, resources, prompts, permission tiers, write gates, cache/index surfaces, or agent harness integrations.
Knowledge retrieval pipeline review
jukrap/ai-agent-playbook/skills/data/knowledge-retrieval-pipeline-review Skill
2★ repoUse when reviewing document ingestion, parsing, chunking, metadata, deduplication, embeddings, vector stores, retrieval quality, citations, or stale RAG/search indexes.
jukrap/ai-agent-playbook/skills/delivery/eval-harness-design Skill
2★ repoUse when agent evals need graders, pass@k, regression gates, or reliability evidence.
jukrap/ai-agent-playbook/skills/design/image-to-code-handoff Skill
2★ repoUse when turning generated images, screenshots, mockups, reference boards, or Figma frames into implementation-ready UI specs and verification criteria.
jukrap/ai-agent-playbook/skills/frontend/design-system-handoff Skill
2★ repoUse when turning Figma, brand, design-token, component-library, theme, variant, or visual-spec guidance into maintainable frontend implementation.
jukrap/ai-agent-playbook/skills/meta/agent-skill-authoring Skill
2★ repoUse when creating, reviewing, or reorganizing reusable agent skills, skill references, trigger descriptions, or skill/template boundaries.
jukrap/ai-agent-playbook/skills/project/adr-spec-handoff Skill
2★ repoUse when turning decisions, architecture constraints, specs, milestone outcomes, worklogs, or implementation handoffs into durable ADR/spec/runbook/project-memory documentation.
jukrap/ai-agent-playbook/skills/quality/review-work-light Skill
2★ repoUse when doing a lightweight review of recent implementation work, local diffs, or a completed change before handoff without starting a blocking multi-agent review process.
adtn0810/truestack/skills/truestack-mcp-integration Skill
2★ repoAct on external systems through connected MCP servers — query or write a database, search a vector store, call a payment or webhook API, hit a third-party service — instead of only advising about them. Use whenever a task needs live data or a real external action performed through a connected MCP server, or when setting up / configuring MCP servers (.mcp.json) for a project; a more specific vendor skill that matches the tool or server takes precedence in both cases. Applies the same accuracy, security, and honesty discipline to tool calls as truestack-backend-development applies to code.
adtn0810/truestack/skills/truestack-project-memory Skill
2★ repoBuild and maintain persistent, repo-local memory of a codebase so the other skills stop re-discovering the same facts. Use this on the FIRST substantial task in any repo (study the project before doing the work), whenever project facts seem missing or stale, and whenever the user says "set up project memory", "onboard this repo", or "remember this about the project". Creates and updates a committed memory folder the other skills read first.
adtn0810/truestack/skills/truestack-prompt-optimizer Skill
2★ repoTurn a raw prompt into a sharpened, optimized brief before any work runs on it — classify the task, fill or ask about missing components, pick the technique, and prepend the matching expert persona, without changing what the user asked for. Use whenever truestack-orchestrate hands a request to a downstream skill (every handoff gets primed — a terse or underspecified handoff gets enriched, a sharp one passes through), or when the user says "sharpen this prompt", "enrich the prompt", "optimize my prompt", "rephrase this as an expert would", "prime the task", or "adopt an expert persona". A persona never licenses guessing — the optimized brief keeps the honesty contract.
rumotion/ai-agent-project-template/.agents/skills/docs-memory-maintainer Skill
2★ repoUpdates project documentation and Memory Bank files after meaningful changes. Use after features, refactors, setup changes, architecture decisions, or user requests to update memory.
rumotion/ai-agent-project-template/.cline/skills/delegation-coordinator Skill
2★ repoCoordinates task delegation across Gemini, Codex, Claude, and subagents using the portable subagent contract.
rumotion/ai-agent-project-template/.cline/skills/docs-memory-maintainer Skill
2★ repoUpdates project documentation and Memory Bank files after meaningful changes. Use after features, refactors, setup changes, architecture decisions, or user requests to update memory.
guofu-shiqu/ux-expert-skills/skills/exp-orchestration-design Skill
2★ repo体验编排设计。当需要将旅程中的关键节点转化为 Agent 可执行的自动化机制时调用。
b2bforce/b2bforce/.agents/skills/firm-pdca-eval Skill
2★ repoIndependently evaluate a PDCA cycle against the acceptance criteria written before the work started, using deterministic checks first and an LLM judge second. Use before a cycle's Check, when verifying whether work actually met its criteria, or when a result needs a second opinion that is not the executor's.
ProdaZhang/aigd/aigd Skill
2★ repoAIGD (AI Game Design) main entry / orchestrator. Use this when the user wants to **start a game project from scratch**, is **unsure which phase to use**, wants to **survey or advance the entire development pipeline**, or needs to **maintain the project spine (project charter / manifest)**. This skill only does "read the spine → judge progress → dispatch to the matching sub-skill"; **if a specific step is already clear (concept / build a system / iterate / finalize / sync-back / screenshot capture), use the corresponding sub-skill directly** (aigd-concept / aigd-system / aigd-iterate / aigd-handoff / aigd-sync / aigd-ui-capture). The methodology ships with references/ and does not depend on any specific project.
jasonChen0604/codebase-to-portfolio/skills/init-project-doc Skill
2★ repoAuto-generate a portfolio-ready project doc (CLAUDE.md / AGENTS.md) from a project's directory structure and source code. Triggers when the user provides a project's directory tree or source snippets and asks to "generate a project doc", "initialize this project", "analyze this project", "產出作品集文件", or "初始化這個專案".
Lord1Egypt/scientific-agent-toolkit/scientific-skills/autoskill Skill
2★ repoObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
Lord1Egypt/scientific-agent-toolkit/scientific-skills/bgpt-paper-search Skill
2★ repoSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
The same file is in 2 other repositories
bmob/agent-skills/skills/bmob-mcp Skill
2★ repoUse when the user has the Bmob MCP server configured (http://mcp.bmobapp.com/mcp) and wants to perform LIVE operations against their Bmob backend cloud project from the IDE. Triggers: 'list bmob tables', 'show bmob schema', 'create bmob table', 'add a row to bmob', 'update bmob record', 'delete bmob data', '生成 bmob curl', 'design bmob schema', '上传云函数', '部署云函数', '发布云函数', '同步云函数', '同步函数', '拉取云函数', '下载云函数', '调用云函数', '执行云函数', 'invoke cloud function', 'run cloud function', '一键部署网站', '静态托管', '部署静态站点', 'deploy static site', 'deploy website'. Provides 12 tools: get_project_tables (ALWAYS call first to discover schema before any write), create_table, add_single_data, update_single_data, delete_single_data, generate_code, deploy_cloud_function, invoke_cloud_function, list_cloud_functions, get_cloud_function, deploy_static_site, mcp_endpoint_mcp_post. NOT for writing client/SDK code that will ship in the user's app — for that use bmob-database-{javascript,android,ios,swift,flutter,restful}. NOT for ACL / role design (use bmob-acl-and-roles) or cloud function development (use bmob-cloud-function-development).
bmob/agent-skills/skills/bmob Skill
2★ repoUse whenever the user mentions Bmob backend cloud (Bmob, BmobApp, bmobapp.com, Bmob 后端云) for ANY task: design data tables, perform CRUD, sign up / login users, upload files, push notifications, send SMS, accept payments, write or invoke cloud functions, configure ACL / roles, debug error codes, or operate the project via the Bmob MCP server. This is the routing entry — it dispatches to platform-specific skills: bmob-database-{javascript,android,ios,swift,flutter,restful}, bmob-auth-*, bmob-storage-*, bmob-cloud-function-*, bmob-mcp, bmob-error-codes, bmob-bql, bmob-acl-and-roles. For operation-level MCP vs SDK vs REST routing, read shared/operation-routing.md. NOT a substitute for those sub-skills — once the platform and feature are clear, read and follow the matching sub-skill before writing code.
r-irbe/proof-skills/skills/ai-agentic-evolving Skill
2★ repoUSE FOR: Agentic AI systems, multi-agent coordination, evolving agents, agent lifecycle management, emergent behavior, and trust dynamics in autonomous systems. Use for reasoning about agent architectures, communication protocols, coalition formation, reputation systems, and the mathematical foundations of agentic safety and multi-agent trust formalization. DO NOT USE FOR: formal verification of those AI systems (use @lean-ai-formalization); high-stakes / verifiable AI mode (use @ai-high-stakes-verifiable); causal/deontic reasoning (use @ai-causal-deontic). TRIGGERS: agentic AI, multi-agent, evolving agent, agent lifecycle, emergent behavior, trust dynamics, autonomous system.
r-irbe/proof-skills/skills/lean-ai-formalization Skill
2★ repoUSE FOR: Formal verification of AI systems — agentic AI safety, alignment, high-stakes AI, evolving agents, neural network properties, and AI governance constraints. Use when formalizing safety envelopes, trust dynamics, multi-agent composition, AI act compliance, reward specifications, alignment properties, or any AI system property that must be formally verified. DO NOT USE FOR: AI methodology itself (use @ai-high-stakes-verifiable or @ai-agentic-evolving); security-specific formalisation (use @lean-security-formalization); knowledge formalisation (use @lean-knowledge-formalization). TRIGGERS: AI formalization, agentic safety, alignment proof, high-stakes AI, neural network property, AI governance.
shandar/memory-map/skills/memory-recall Skill
2★ repoLoad and summarise stored project memory at the start of a session, or whenever the user asks what Claude remembers about their work. Use this skill when the user says things like "what do you remember", "what's the context", "where did we leave off", "catch me up", "what's the current state", "show me the memory map", or "what do you know about my projects". Also trigger proactively at the start of any new conversation if a memory store exists — surface the current state and pending items without being asked, so the user does not have to re-orient Claude. Pairs with memory-map (which writes memory) and memory-prune (which cleans it). Together they form a complete memory loop across Claude sessions.
john-data-chen/hermes-agent-backup/skills/autonomous-ai-agents/claude-code Skill
2★ repoDelegate coding to Claude Code CLI (features, PRs).
The same file is in 2 other repositories
john-data-chen/hermes-agent-backup/skills/autonomous-ai-agents/hermes-agent Skill
2★ repoConfigure, extend, or contribute to Hermes Agent.
john-data-chen/hermes-agent-backup/skills/cavecrew Skill
2★ repoDecision 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".
john-data-chen/hermes-agent-backup/skills/caveman-compress Skill
2★ repoCompress 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"
john-data-chen/hermes-agent-backup/skills/creative/claude-design Skill
2★ repoDesign one-off HTML artifacts (landing, deck, prototype).
john-data-chen/hermes-agent-backup/skills/creative/touchdesigner-mcp Skill
2★ repoControl a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
The same file is in 3 other repositories
john-data-chen/hermes-agent-backup/skills/mlops/evaluation/lm-evaluation-harness Skill
2★ repolm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
The same file is in 3 other repositories
john-data-chen/hermes-agent-backup/skills/research/llm-wiki Skill
2★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
The same file is in 1 other repository
john-data-chen/hermes-agent-backup/skills/software-development/hermes-agent-skill-authoring Skill
2★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure, and writing-quality principles.
The same file is in 1 other repository
hec-ovi/blockchain-skill/plugins/agent-wallet/skills/agent-wallet Skill
2★ repoOperate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet, mainnet, sepolia.
hec-ovi/blockchain-skill/skills/agent-wallet Skill
2★ repoOperate a non-custodial blockchain wallet on-chain (EVM and Bitcoin), no exchange or MetaMask. Create or import a wallet, balances, send native/ERC-20/BTC, swap tokens, compile/deploy/call Solidity. Trigger on wallet, crypto, ETH, BTC, ERC-20, token, send, transfer, swap, trade, Solidity, contract, on-chain, testnet, mainnet, sepolia.
xFurti/leogriel/skills/leogriel Skill
2★ repoManage Agent Skills with the leogriel CLI: search, info, add, install, outdated, update, sync, import, audit, plugins, behavioral tests, completion, and portable manifest/lock workflows across Claude, Cursor, Codex, Grok, Gemini, Pi, and OpenCode. Use when the user mentions leogriel, agent-skills.json, agent-skills.lock, syncing skills, importing from npx skills, or skill portability across machines.
synerarg/claude-code-skills/plugins/mercadopago/skills/mercadopago Skill
no license2★ repoSkill UNICA y completa para todo Mercado Pago en aplicaciones web (Next.js, React, Vanilla JS). COBRAR: Checkout Pro (redireccion), Checkout Bricks (Payment, Card, Wallet, Status Screen), Orders API (nuevo modelo) y Suscripciones (preapproval / pagos recurrentes). ENVIAR dinero: Money Out (transferencias/retiros a cuentas bancarias y cuentas MP, Pix) y Marketplace / split de pagos (cobrar para terceros con comision). Ademas: webhooks con validacion x-signature, reembolsos totales/parciales, cancelaciones, capturas manuales, contracargos, comisiones y liberacion de dinero, y medios de pago por pais. Incluye adaptadores de base de datos (Supabase, Prisma, Raw pg), troubleshooting detallado, tarjetas de test por pais, ejemplos de prompts, y uso del MCP server oficial de MP. Usar cuando se necesite: (1) Integrar pagos con MercadoPago en cualquier modalidad, (2) Implementar Checkout Pro o Bricks, (3) Usar la Orders API, (4) Configurar webhooks/notificaciones, (5) Implementar reembolsos o cancelaciones, (6) Troubleshootear errores de integracion MP, (7) Hacer un setup asistido con el MCP server oficial de MP (crear app, credenciales, webhooks) y validar calidad, (8) Enviar dinero a cuentas bancarias (Money Out / payouts), (9) Cobrar para terceros con split de pagos (marketplace), (10) Cobrar de forma recurrente (suscripciones), o entender comisiones y costos de MP. Triggers: MercadoPago, Mercado Pago, pagos MP, checkout MP, bricks, orders API MP, webhook mercadopago, reembolso mercadopago, refund MP, money out, transferencias MP, payout, marketplace MP, split de pagos, suscripciones MP, preapproval, comisiones mercadopago, costos MP. Soporta: Argentina (ARS), Brasil (BRL), Mexico (MXN), Colombia (COP), Chile (CLP), Peru (PEN), Uruguay (UYU).
xAmirHamza77/PenKit51/skills/llm-prompt-injection-testing Skill
no license2★ repoTesting LLM-backed features for prompt injection, jailbreaks, system-prompt leakage, tool/agent abuse, and unsafe output handling
xAmirHamza77/PenKit51/skills/pentest-orchestration Skill
no license2★ repoOrchestration layer that coordinates specialized subagents for security assessments
kimgoetzke/coding-agent-configs/skills/write-a-skill Skill
2★ repoCreate new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/context-engineering Skill
no license2★ 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.
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/dispatching-parallel-agents Skill
no license2★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/subagent-driven-development Skill
no license2★ repoUse when executing implementation plans with independent tasks in the current session
3awny/qship/templates/skills/qship Skill
2★ repoFull Jira-ticket → PR pipeline (plan, implement, review, test, ship). Supports parallel and epic-mode execution. Two independent engine knobs — `provider=claude|codex` chooses the Step 7 implementer (default Claude Opus 4.7 1M, medium reasoning), and `reviewer=claude|codex` chooses the Phase 2 reviewer (default Claude). Most useful combination beyond defaults is `provider=claude reviewer=codex` (Opus implements, gpt-5.5 high reasoning hunts bugs) — different model families catch different defects.
3awny/qship/templates/skills/qshipmaster Skill
2★ repoEpic-level orchestrator for qship. Takes a Jira Epic ID, builds a topologically-sorted wave plan from its children, spawns one qship-persist.sh per ticket per wave in parallel, merges each wave into a consolidated epic branch, runs a lightweight wave-gate after each wave (migration check + targeted tests + 2 bug hunters + qbcheck, blocks only on Critical) and ONE full epic-level Phase 2 review after the last wave on the cumulative diff, and ships ONE consolidated PR per repo. Two engine knobs — `provider=claude|codex` chooses the Step 7 implementer (default Opus 4.7 1M, medium), and `reviewer=claude|codex` chooses the Phase 2 reviewer (default Claude). The diversified combo `provider=claude reviewer=codex` runs Opus implementing + gpt-5.5 high reviewing for different-family second opinion. Set `QSHIP_PER_WAVE_REVIEW=full` to restore full Phase 2 per wave, or `=none` to skip per-wave review entirely. Resumable, state-driven, idempotent.
vignesh2027/AI-AGENT-SKILLS/skills/context-engineering Skill
2★ repoManage what goes into the AI agent context window for maximum quality and minimum waste
vignesh2027/AI-AGENT-SKILLS/skills/llm-evaluation Skill
2★ repoSystematically evaluate LLM outputs, prevent regressions, and measure quality
vignesh2027/AI-AGENT-SKILLS/skills/prompt-engineering Skill
2★ repoWrite prompts that are reliable, testable, versioned, and safe