Context & AI engineering
25,831 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
skrun-dev/skrun/agents/knowledge-base-from-vault Skill
208★ repoTurn a folder of Markdown notes (Obsidian vault, Notion export, plain repo docs) into a navigable static HTML knowledge base bundled as a single .zip file. Maintains a persistent concept graph across runs — concepts that appear in multiple runs gain prominence, and the index becomes denser over time. Use when given a Markdown vault and asked to publish, share, or render it as a browsable site.
aigorahub/elves/aliases/claude/cobbler Skill
203★ repoInvoke Elves Cobbler, the default orchestration model for fitted answers and agent routing. Use when the user types /cobbler or asks for Cobbler coordination in Claude Code.
aigorahub/elves/aliases/claude/setup-cobbler Skill
203★ repoConfigure Cobbler model routes and external-agent preferences for this checkout. Use when the user types /setup-cobbler, asks to set up Cobbler model routes, onboard models, or update which tools handle planning/implement/review in Claude Code.
PramodDutta/qaskills/packs/qa-essentials/skills/claude-code-qa Skill
202★ repoThe complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type, writes reliable Playwright, Cypress, and pytest tests, eliminates flaky tests, enforces coverage, and wires up CI. Claude Code QA testing done right.
PramodDutta/qaskills/packs/qa-essentials/skills/e2e-testing-claude-code Skill
202★ repoMake Claude Code write and maintain end-to-end tests like a senior SDET — Playwright and Cypress flows with stable locators, the Page Object Model, fixtures, reused auth state, network mocking, and flake-free CI. Claude Code E2E testing, done right.
PramodDutta/qaskills/packs/qa-essentials/skills/qa-agent-claude Skill
202★ repoTurn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes tests for real user journeys, executes them, self-heals broken locators, and reports coverage. Build a QA agent skill for Claude Code.
simbajigege/book2skills/skills/compact-memory-implementation Skill
202★ repoDeveloper implementation guide for adding compact memory to an Agent — covers fork agent pattern for compaction, trigger strategy, summary format design, and memory restoration in subsequent sessions. Use when a developer asks how to implement compact memory, context compression, or memory persistence in their agent built with Claude Agent SDK or Anthropic API.
simbajigege/book2skills/skills/folded-memory-implementation Skill
202★ repoDeveloper implementation guide for building hierarchical (folded) memory into an Agent. Three-layer architecture where recent turns stay detailed, older content compresses into episodes, and the oldest distills into durable semantic facts. Use when compact-memory-implementation is not retaining enough, or when agents need to recall decisions from many sessions ago.
simbajigege/book2skills/skills/harness-step1-create-agent-md Skill
202★ repoHarness Engineering 第一阶段:扫描现有项目,生成 AGENTS.md(目录文件)和完整的 docs/ 知识库结构。 当用户想要"为项目添加 agent 支持"、"让 AI 更好地理解我的项目"、"开始 harness engineering"、 "创建 AGENTS.md"、"搭建 agent 文档结构"、"让 Claude Code 更好地工作"时,立即使用此 skill。 也适用于用户说"帮我把项目文档整理好给 agent 用"、"我想开始用 AI agent 开发"、 "梳理这个项目能解决什么业务问题"或要求建立 business-solution.md 等场景。
simbajigege/book2skills/skills/jab-jab-right-hook-vaynerchuk Skill
202★ repoApply Gary Vaynerchuk social content rules for native jabs, right hooks, platform fit, campaign critique, and engagement before conversion.
simbajigege/book2skills/skills/query-loop-implementation Skill
202★ repoImplement a production-ready LLM query loop / agent loop for AI applications. Use this skill whenever the user wants to add tool calling, ReAct-style reasoning-action-observation cycles, function calling loops, query engines, agent runtimes, tool_result feedback, max-turn exits, or Claude Code-like Agent Loop behavior to their own product or codebase.
simbajigege/book2skills/skills/skill-creator Skill
202★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
PramodDutta/qaskills/seed-skills/agent-browser Skill
201★ repoFast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
PramodDutta/qaskills/seed-skills/agentic-testing Skill
201★ repoAI-first testing methodology where autonomous agents plan, generate, execute, and maintain test suites with minimal human intervention, covering agent orchestration, feedback loops, and intelligent test prioritization.
PramodDutta/qaskills/seed-skills/ai-agent-eval Skill
201★ repoComprehensive evaluation patterns for AI agents including multi-turn conversation testing, LLM-as-judge frameworks, benchmark suites, regression detection, and systematic eval pipelines for measuring agent quality and safety.
PramodDutta/qaskills/seed-skills/ai-system-quality-engineer Skill
201★ repoTest LLM, RAG, MCP, and agentic systems end to end. Build golden datasets, run deterministic checks and LLM judges, score retrieval, probe prompt injection, verify tool use, and gate CI on thresholds. Orchestrates DeepEval, Ragas, promptfoo, and Langfuse.
PramodDutta/qaskills/seed-skills/ai-test-generation Skill
201★ repoSystematic patterns for prompting AI coding agents to generate high-quality tests including prompt engineering for test creation, coverage-driven generation, mutation-aware testing, and review checklists for AI-generated test code.
PramodDutta/qaskills/seed-skills/ai-test-orchestration Skill
201★ repoAI-powered test orchestration skill covering intelligent test selection, risk-based test prioritization, flaky test management, test impact analysis, parallel execution optimization, and predictive test failure detection using machine learning.
PramodDutta/qaskills/seed-skills/browser-agent-qa-testing Skill
201★ repoTeach agents to use AI browser agents for exploratory and smoke QA with step budgets, evidence-based assertions, guardrails, and Playwright conversion.
Chrome devtools mcp performance
PramodDutta/qaskills/seed-skills/chrome-devtools-mcp-performance Skill
201★ repoTeach agents to use the Chrome DevTools MCP server for performance testing with traces, Core Web Vitals, throttling, and evidence-based analysis.
PramodDutta/qaskills/seed-skills/claude-code-qa Skill
201★ repoThe complete QA skill for Claude Code — turn Claude into an expert QA engineer that picks the right test type, writes reliable Playwright, Cypress, and pytest tests, eliminates flaky tests, enforces coverage, and wires up CI. Claude Code QA testing done right.
PramodDutta/qaskills/seed-skills/copilot-testing-patterns Skill
201★ repoEffective patterns for using GitHub Copilot to generate, refactor, and maintain test code including prompt engineering for test generation, Copilot Chat for debugging, inline suggestions for assertions, and workspace context optimization.
PramodDutta/qaskills/seed-skills/deepeval-llm-evaluation Skill
201★ repoTest LLM applications with DeepEval, pytest-style unit tests for LLM outputs using G-Eval, answer relevancy, faithfulness, hallucination and custom metrics, with CI quality gates and dataset-driven regression runs.
PramodDutta/qaskills/seed-skills/devin-ai-testing Skill
201★ repoTesting patterns for autonomous AI coding agents like Devin and SWE-Agent including task verification, output validation, sandboxed execution, regression testing for agent behavior, and safety guardrails for autonomous code generation.
PramodDutta/qaskills/seed-skills/e2e-testing-claude-code Skill
201★ repoMake Claude Code write and maintain end-to-end tests like a senior SDET — Playwright and Cypress flows with stable locators, the Page Object Model, fixtures, reused auth state, network mocking, and flake-free CI. Claude Code E2E testing, done right.
PramodDutta/qaskills/seed-skills/langfuse-llm-observability Skill
201★ repoInstrument LLM apps with Langfuse tracing, then use traces, scores, and datasets to test in production, run evaluations on real traffic, catch regressions, and close the loop from incident to golden dataset.
PramodDutta/qaskills/seed-skills/llm-output-testing Skill
201★ repoTesting LLM-powered features including output quality validation, hallucination detection, token usage monitoring, and prompt regression testing.
PramodDutta/qaskills/seed-skills/llm-security-testing Skill
201★ repoSecurity testing for LLM-powered applications including prompt injection, jailbreak detection, data leakage prevention, and AI safety testing.
PramodDutta/qaskills/seed-skills/mcp-server-testing Skill
201★ repoComprehensive testing patterns for Model Context Protocol servers including tool validation, transport testing, schema verification, and end-to-end MCP integration testing with stdio and SSE transports.
PramodDutta/qaskills/seed-skills/memory-leak-detector Skill
201★ repoIdentify and diagnose memory leaks in web applications using heap snapshots, allocation timelines, and automated leak detection patterns.
PramodDutta/qaskills/seed-skills/memory-profiling Skill
201★ repoSystematic memory profiling and leak detection in applications using heap snapshots, allocation tracking, and garbage collection analysis.
PramodDutta/qaskills/seed-skills/openai-evals-trace-grading Skill
201★ repoGrade LLM and agent traces with OpenAI Evals - build datasets, configure string/python/model graders, run eval suites, and gate agent behavior changes in CI.
PramodDutta/qaskills/seed-skills/playwright-cli-agent-loop Skill
201★ repoTeach AI coding agents to use the Playwright CLI and debug loop efficiently with last-failed runs, locator probing, trace evidence, and safe healing.
PramodDutta/qaskills/seed-skills/prompt-testing Skill
201★ repoComprehensive prompt testing and LLM output evaluation skill covering hallucination detection, response quality scoring, regression testing for prompts, A/B testing, and building evaluation pipelines for AI-powered applications.
PramodDutta/qaskills/seed-skills/promptfoo-llm-red-teaming Skill
201★ repoEvaluate and red-team LLM applications with promptfoo, declarative YAML evals, assertions, model comparisons, and automated adversarial scans for prompt injection, jailbreaks, PII leaks, and unsafe outputs in CI.
PramodDutta/qaskills/seed-skills/qa-agent-claude Skill
201★ repoTurn Claude Code into an autonomous QA agent — an explore, generate, run, heal, report loop that maps the app, writes tests for real user journeys, executes them, self-heals broken locators, and reports coverage. Build a QA agent skill for Claude Code.
PramodDutta/qaskills/seed-skills/rag-evaluation-metrics Skill
201★ repoMeasure RAG pipeline quality with context precision/recall, faithfulness, answer relevancy, and groundedness using Ragas and DeepEval, with golden datasets and pass/fail thresholds.
PramodDutta/qaskills/seed-skills/rag-regression-testing Skill
201★ repoGate RAG pipelines in CI with versioned golden eval sets, per-metric thresholds, baseline drift detection, and a build that fails when retrieval or answer quality regresses.
PramodDutta/qaskills/seed-skills/ragas-rag-evaluation Skill
201★ repoEvaluate RAG pipelines with Ragas, measuring faithfulness, answer relevancy, context precision and recall, building golden datasets, and wiring threshold gates into CI for retrieval regressions.
Tencent/SkillHone/skills/skillhone-prd Skill
no license196★ repoInteractively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should <x>-skill do", or before running `skillhone new` / `skillhone optim` on a skill whose requirements aren't fully nailed down. The interview is driven through the `AskUserQuestion` tool — every round is a small set of dependent multi-choice questions, and the skill keeps asking until the user says stop. Final artifacts are three files in the paired `<skill>-eval` repo: `PRD.md` (eval-agent-visible), `PRD.improver_only.md` (improver-agent visible, scoring rubric redacted), and `PRD.choice.md` (the AskUserQuestion transcript). Also mirrors the appropriate pages into Forgejo wiki checkouts when available.
Tencent/SkillHone/skills/skillhone-synthesis Skill
no license196★ repoUse this skill to synthesize closed-form, automatically verifiable benchmark Q/A by exploring a tool environment, building a reusable exploration graph, and mining multiple hard questions from that graph. Use for: building a benchmark, writing eval items, generating evaluation data, closed-form QA, verifiable-answer datasets, synthesising eval data. Applies to any domain with callable tools. Do not use for open-ended writing, subjective scoring, or pure labeling.
ethanhq/cc-fleet/skills/subagent Skill
192★ repoRun a one-shot or flat parallel batch of provider LLM subagents (headless `cc-fleet subagent`) that return a result. Use when fanning out N independent tasks, doing bulk per-file work, or calling a specialized provider model (DeepSeek / GLM / Kimi / Qwen / MiniMax). NOT a long-lived collaborator you message back and forth (that is /cc-fleet:team); NOT a multi-phase pipeline with dependencies or resume (that is /cc-fleet:workflow); NOT trivial work the main session should just do.
ethanhq/cc-fleet/skills/team Skill
192★ repoSpawn long-lived provider LLM teammates in tmux panes that you message via the native agent-team tools — multi-turn, collaborative, watchable. Use for sustained parallel build/work ("spawn workers", N teammates on N files), or when you need a collaborator you message across turns. NOT a fire-and-forget one-shot or a flat batch of independent prompts — that is /cc-fleet:subagent. NOT a scripted multi-phase run — that is /cc-fleet:workflow.
vishalsachdev/canvas-mcp/io.github.vishalsachdev/canvas-mcp MCP server
191★ repoCanvas LMS integration for students and educators with FERPA-compliant analytics and workflows
Azhi-ss/academic-figure-skills/academic-figure-prompt-pastel Skill
189★ repoPastel airy figure prompts for modern ML papers — ICLR/NeurIPS/ICML soft-panel style with tokens, pills, and rounded type. Use when the user wants pastel academic figures, 现代ML论文配图, or 2024-2025 conference airy aesthetics.
Azhi-ss/academic-figure-skills/academic-figure-prompt Skill
189★ repoJSON figure spec for academic diagrams — exact_text layout control for framework, architecture, module, and comparison figures. Use when the user wants paper figure prompts, 架构图/框架图 specs, or academic-figure JSON (text prompts only as simple fallback).
Azhi-ss/academic-figure-skills/academic-figure-workflow Skill
189★ repoEnd-to-end academic figure workflow router — from repo or paper to figure prompt via the minimum sibling skills. Use when the user wants a full pipeline, is unsure which academic-figure skill to start with, or says 完整论文配图工作流 / from paper to figure prompt.
kklimuk/docx-cli/.claude/skills/weak-agent-test Skill
186★ repoRun the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.
zapier/connectors/apps/dataforseo Skill
no license186★ repoAgent-callable DataForSEO tools — Google SERP results, keyword and domain analytics, backlinks, Google Maps business data, on-page audits, and AI-search visibility (LLM answers + brand mentions). Use when the user wants SEO or AI-search data, even if they don't name DataForSEO.
sergebulaev/x-skills/.codex-marketplace/x-skills/skills/x-hook-extractor Skill
184★ repoReverse-engineer the hook from a viral X (Twitter) tweet or thread URL. Identifies which of the 10 canonical 2026 X formulas it uses (one-liner contrarian, data-point, build-in-public, quote-tweet, mini-list, relatable cold-open, listicle-thread, story thread, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal. Use to learn from a tweet you admire. Not for writing your own (use x-post-writer or x-thread-builder).
sergebulaev/x-skills/skills/x-hook-extractor Skill
184★ repoReverse-engineer the hook from a viral X (Twitter) tweet or thread URL. Identifies which of the 10 canonical 2026 X formulas it uses (one-liner contrarian, data-point, build-in-public, quote-tweet, mini-list, relatable cold-open, listicle-thread, story thread, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal. Use to learn from a tweet you admire. Not for writing your own (use x-post-writer or x-thread-builder).
gaasher/Agent-Loop-Skills/loops/hypothesis-gen Skill
183★ repoUse when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain. A multi-agent loop: a Generator proposes candidate hypotheses, a LiteratureScout grounds each in real retrieved literature (already known? closest prior work? what gap does it fill?), and a Judge scores them against a fixed rubric and keeps the strong, non-duplicate ones; rounds repeat — mutating toward the open gaps — until fresh rounds stop adding keepers. Not for sharpening or decomposing a research question (no grounding/scoring there), and not for grading an existing written proposal against the literature.
gaasher/Agent-Loop-Skills/loops/karpathy Skill
183★ repoUse when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.
gaasher/Agent-Loop-Skills/loops/prompt-optimize Skill
183★ repoUse when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved to raise the score against their own evaluation command. Makes one targeted quality edit per iteration — clarity, context, specificity, structure, examples, decomposition, guardrails — re-runs the user's eval to measure the metric, and keeps the edit only if the metric improves, else reverts; loops to a target, plateau, or budget. The metric is whatever the user's eval command prints (task accuracy, an LLM-judge score, a pass rate, a tool-call success rate); the loop is metric-agnostic and never edits the eval. Not for writing a prompt from scratch, not for tuning model weights or hyperparameters, and not for one-off manual prompt edits without a score.
Dynatrace/dynatrace-for-ai/skills/dt-obs-genai Skill
181★ repoSkills, prompts, and instructions for building AI agents on top of Dynatrace production context
The same file is in 3 other repositories
wanshuiyin/Anti-Autoresearch/skills/eval-design-forensics Skill
180★ repoAudit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
wanshuiyin/Anti-Autoresearch/skills/experiment-forensics Skill
180★ repoAudit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".
alfadur7/llm-wiki-newsroom/.claude/skills/guideline-writing Skill
176★ repoGuideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers, pruning, bloat control, blind review protocol, deliberation-narrative ban. Use when writing, editing, or reviewing an agent instruction file, policy, runbook, command SoT, or plan file, or when a guideline change needs a minimal-edit or blind review.
wednesday-solutions/ai-agent-skills/skills/agents/pr-review-agent Skill
174★ repoFull PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this.
lornshrimp/Lorn.NovelWriteSkills/CommonSkills/通用-去AI味重写/taste-skill-main/skills/gpt-tasteskill Skill
no license170★ repoElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
The same file is in 13 other repositories