Context & AI engineering
25,610 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
goharabbas321/zeoel/skills/agent-eval Skill
no license0★ repoHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
The same file is in 5 other repositories
goharabbas321/zeoel/skills/agent-introspection-debugging Skill
no license0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
goharabbas321/zeoel/skills/agentic-engineering Skill
no license0★ repoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
The same file is in 10 other repositories
goharabbas321/zeoel/skills/benchmark Skill
no license0★ repoUse this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
The same file is in 2 other repositories
goharabbas321/zeoel/skills/claude-red Skill
no license0★ repoOffensive security and penetration testing skill. Covers automated vulnerability scanning, secure-coding bypass detection, sanitization reviews, and exploit drafting.
The same file is in 1 other repository
goharabbas321/zeoel/skills/continuous-agent-loop Skill
no license0★ repoPatterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
The same file is in 5 other repositories
goharabbas321/zeoel/skills/cost-aware-llm-pipeline Skill
no license0★ repoCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
The same file is in 9 other repositories
goharabbas321/zeoel/skills/data-scraper-agent Skill
no license0★ repoBuild a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.
The same file is in 8 other repositories
goharabbas321/zeoel/skills/eval-harness Skill
no license0★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
The same file is in 9 other repositories
goharabbas321/zeoel/skills/llm-trading-agent-security Skill
no license0★ repoSecurity patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.
The same file is in 2 other repositories
goharabbas321/zeoel/skills/mcp-server-patterns Skill
no license0★ repoBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.
The same file is in 2 other repositories
goharabbas321/zeoel/skills/orchestration-workflow Skill
no license0★ repoZeoel-AI is a production-grade, multi-agent SaaS software engineering agency. Instead of single, fragile LLM prompts that lose context, Zeoel-AI coordinates a complete team of 33 specialized agents (UX designers, database architects, systems engineers, security auditors, QA engineers, etc.) to brainstorm, plan, build, and verify entire software.
goharabbas321/zeoel/skills/prompt-optimizer Skill
no license0★ repoAnalyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
The same file is in 2 other repositories
goharabbas321/zeoel/skills/recsys-pipeline-architect Skill
no license0★ repoDesign composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is building any system that picks "the top K items for a (user, context)" — social feeds, content CMSs, RAG rerankers, task prioritizers, notification triage, search reranking, ad ranking.
The same file is in 3 other repositories
goharabbas321/zeoel/skills/security-scan Skill
no license0★ repoScan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
The same file is in 9 other repositories
goharabbas321/zeoel/skills/zeoel-security Skill
no license0★ repoCheck any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
The same file is in 1 other repository
vemodalen-x/VEMO_SKILLS/skills/governance/authoring-skills-with-evals Skill
0★ repoAuthor, evaluate, and improve skills with an eval-driven loop instead of by intuition. Use when creating a new skill, revising an existing one, judging whether a skill's description actually triggers, or tuning that description for better trigger accuracy. Runs a with-skill-vs-baseline behavioral eval with variance, a trigger-rate eval, and a train/test-split description optimizer via the repo's skill-creator harness, modeled on Anthropic's official skill-creator. Triggers include create a skill, write a SKILL.md, run a skill eval, benchmark a skill, description not triggering, improve a skill description, skill quality, eval-driven authoring.
vemodalen-x/VEMO_SKILLS/skills/orchestration/breaking-down-prds Skill
0★ repoDecompose a PRD / requirements document into a structured, governable breakdown — functional & non-functional requirements, acceptance criteria, work-breakdown by stage/agent, requirement→stage traceability, and a coverage check. Use at project kickoff or a major new feature, when the orchestrator must turn a PRD into actionable, traceable work before research/build begins. Owned by Framework 0 (orchestration).
vemodalen-x/VEMO_SKILLS/skills/orchestration/designing-diagnostic-prompts Skill
0★ repoDesign structured diagnostic or tutoring prompts and agent workflows that interview the user, locate constraints, configure style/depth, produce a plan, and loop through assessment and feedback. Use when asked to create or improve a Human 3.0-style self-discovery prompt, a Mr. Ranedeer-style tutor prompt, a coaching/custom GPT prompt, an onboarding interview, a diagnostic agent, a personalized learning flow, or any multi-turn prompt that must ask questions before advising.
vemodalen-x/VEMO_SKILLS/skills/orchestration/rendering-html-eval-reports Skill
0★ repoRender pre-computed results into a single self-contained HTML report (CSS inlined, images base64-embedded, mandatory provenance header) in one of two report types — an EVALUATION report (per-class accuracy vs a threshold, a confusion matrix including the abstain/rejection class, a latency distribution, an error-case gallery with overlays) or a TRAINING-EXPERIMENT / ablation report (experiment-ladder table, inline training curves, ablation table, measured-vs-inferred labelling, limitations). Use when an eval run or a training-experiment sweep has produced results that should become a shareable local HTML artifact. Render-only — it consumes results, it does NOT run inference, train, or compute them; the eval type collects ALL error cases (samples only the correct predictions); it embeds only de-identified images per the instance privacy policy; the HTML is a local artifact, not committed to git. Distinct from publishing-deliverables (which publishes a doc to the Feishu/Lark wiki).
codecraftersautomation/claude-code/plugins/ccp/skills/handoff Skill
no license0★ repoPrepare a full handoff so work can continue in the other Claude Code profile (claude-team <-> claude-max) from the same repository. Use this whenever the user is about to switch Claude accounts/launchers, is running low on usage in one profile, says "hand this off", "I need to continue in my other account", "switch to claude-max/claude-team", or wants to capture the current state of work before changing profiles. Writes .claude/ccp/handoff/HANDOFF.md plus a mechanical workstate and a safety report. Does NOT switch accounts or touch credentials.
skillim-hub/skills/crm-integration-agent Skill
0★ repoSyncs WhatsApp, email, and SMS conversations with Monday, HubSpot, and Salesforce for Israeli businesses using live-validated API paths, normalized contacts, consent checks, redaction, and audit logs.
skillim-hub/skills/customer-service-chat-agent Skill
0★ repoHebrew-first customer-service chat agent skill for Israeli small businesses, freelancers, and consumer-facing teams, with FAQ answering, structured triage, and human handoff for edge cases.
skillim-hub/skills/multilingual-support-agent Skill
0★ repoAssist Israeli small businesses, freelancers, and consumers with high-coverage customer support in Hebrew, English, Russian, and Arabic.
mikulgohil/claude-skills/skills/ai-agents/prompt-injection-defense Skill
0★ repoDefend an agent's instruction surface against adversarial content — hidden-Unicode injection (Trojan Source bidi, tag-block ASCII smuggling, zero-width text), homoglyph confusables, and poisoned context. Use when vetting external CLAUDE.md / SKILL.md / MCP tool descriptions, or sanitizing fetched pages and issue/PR bodies before they enter context.
mikulgohil/claude-skills/skills/ai-agents/rag-retrieval Skill
0★ repoRetrieval-Augmented Generation patterns — embeddings, chunking, hybrid search, contextual retrieval, HyDE, reranking, agentic RAG, multimodal RAG, and pgvector. Use when building or tuning a RAG pipeline.
lensetek/Research-Agent-Skills-Collection/skills/agent_update_checker Skill
no license0★ repoBertugas untuk mengecek pembaruan (update) agent skills terbaru dari repositori GitHub dan mengonfirmasi pengguna apakah ingin mengunduh versi terbaru.
lensetek/Research-Agent-Skills-Collection/skills/research_orchestrator Skill
no license0★ repoBerperan sebagai starter utama yang mengoordinasikan seluruh alur kerja riset secara otomatis dari eksplorasi topik, penentuan gap, metodologi, eksperimen data, sintesis literatur, hingga kesiapan publikasi.
guuguo/guugo-skills/skills/skills-governor Skill
no license0★ repoUse when installing, linking, syncing, auditing, repairing, replacing, or removing AI skills across ~/.agents/skills and agent-specific skill directories such as Codex, Claude, Gemini, Antigravity IDE, Qoderwork, or Hermes.
KhurrumMahmood/senior-vibe-engineer/.claude/skills/find-layer-violation Skill
no license0★ repoDetect views, tasks, or other entry points that own business logic. AST-walks the target for core signals (fat body, domain loop over queryset, direct LLM/agent call, dispatch bypass via bare `.delay()`, multi-model write in one function), then asks scouts to judge remaining authority in the entry point: raw SQL/cursors, direct external API clients, import/export construction, direct model/file writes, task dispatch, and transaction/resource policy. Produces an extract-service candidates report. Never edits code — hands off to `/fix-workflow layer:<candidate_id>`.
vindreshsingh/engineering-skills/skills/agent-guardrails Skill
0★ repoAlways-on safety boundaries for AI agents — blocks destructive data operations, secret exfiltration, and security-breaking actions unless the user explicitly approves. Load at every session start and before any tool use that touches data, credentials, or production systems.
vindreshsingh/engineering-skills/skills/agent-memory Skill
0★ repoDesigns durable, curated memory that an agent carries across sessions — what to persist, how to scope and retrieve it, and how to stop it from drifting or poisoning later runs. Use when an agent needs to remember decisions, preferences, or project facts beyond one context window, or when stale/over-generalized memory is corrupting its behavior.
vindreshsingh/engineering-skills/skills/agent-verification Skill
0★ repoStops an AI agent from declaring "done" on work it hasn't actually finished, by separating generation from evaluation and refusing self-graded completion. Use whenever an agent reports a task complete — especially in autonomous or long-running runs — to catch early termination, self-grading bias, and gamed tests before the work is trusted or merged.
vindreshsingh/engineering-skills/skills/design-handoff Skill
0★ repoTurns a visual design into faithful, maintainable front-end code. Use when implementing a mockup or Figma file, matching a design spec, building against a design system, or reviewing how closely an implementation tracks its design.
vindreshsingh/engineering-skills/skills/llm-feature-engineering Skill
0★ repoBuilds reliable product features on top of LLMs — prompts, tools, evals, and guardrails. Use when adding AI/LLM functionality, designing prompts or agent tools, fixing flaky model behavior, or shipping and maintaining a model-powered feature in production.
vindreshsingh/engineering-skills/skills/long-running-agents Skill
0★ repoKeeps an agent (or a planner/worker/judge fleet) coherent across hours or days and thousands of model calls — using external plan and progress files, checkpoint-and-resume, and context compaction so the run survives context limits, crashes, and drift. Use when a task is too big for one context window or must run unattended over a long horizon.
vindreshsingh/engineering-skills/skills/skill-creator Skill
0★ repoAuthors a new engineering skill (or fixes an existing one) so it fires at the right time and gets followed. Use when adding a skill to this repo, splitting an overloaded one, or improving a skill that isn't being triggered.
hillzeealex/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
hillzeealex/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 7 other repositories
meharajM/context-machine/packages/team-project-memory-skill/skills/team-memory-search Skill
0★ repoSearch shared project memory before repeating debugging, setup, build, test, deployment, performance, or architecture investigation already attempted by another developer or agent.
meharajM/context-machine/packages/team-project-memory-skill/skills/team-project-memory Skill
0★ repoRoute shared project-memory work to the smallest specialized skill. Use when configuring, using, reviewing, or improving reusable knowledge shared across developers, agents, sessions, or machines.
meharajM/context-machine/plugins/team-project-memory/skills/team-memory-capture Skill
0★ repoCapture a short reusable project learning after a non-obvious fix, failed approach, setup requirement, decision, or debugging path is verified and likely to save another agent time or tokens.
meharajM/context-machine/plugins/team-project-memory/skills/team-memory-maintenance Skill
0★ repoInitialize or maintain a git-backed shared project-memory store, including policy, layout, deduplication, contradictions, staleness, retention, and conflict-safe publishing.
meharajM/context-machine/plugins/team-project-memory/skills/team-memory-search Skill
0★ repoSearch shared project memory before repeating debugging, setup, build, test, deployment, performance, or architecture investigation already attempted by another developer or agent.
meharajM/context-machine/plugins/team-project-memory/skills/team-project-memory Skill
0★ repoRoute shared project-memory work to the smallest specialized skill. Use when configuring, using, reviewing, or improving reusable knowledge shared across developers, agents, sessions, or machines.
meharajM/context-machine/skills/team-memory-capture Skill
0★ repoCapture a short reusable project learning after a non-obvious fix, failed approach, setup requirement, decision, or debugging path is verified and likely to save another agent time or tokens.
meharajM/context-machine/skills/team-memory-maintenance Skill
0★ repoInitialize or maintain a git-backed shared project-memory store, including policy, layout, deduplication, contradictions, staleness, retention, and conflict-safe publishing.
meharajM/context-machine/skills/team-memory-search Skill
0★ repoSearch shared project memory before repeating debugging, setup, build, test, deployment, performance, or architecture investigation already attempted by another developer or agent.
meharajM/context-machine/skills/team-project-memory Skill
0★ repoRoute shared project-memory work to the smallest specialized skill. Use when configuring, using, reviewing, or improving reusable knowledge shared across developers, agents, sessions, or machines.
Preciso-GR/skills_for_preciso/Reconciliation-Subagent-Skill Skill
no license0★ repoUse this skill when you are a reconciliation subagent asked to clean a single extraction JSON (not raw document text). Your job is to identify entity name variants, duplicate relationships, conflicts, or orphaned references and produce a patch file. Do NOT call any ingest tools. Do NOT rewrite the base extraction. Output must be a patch JSON file with merge/remove/flag directives only.
ctoth/golang-skills-plugin/plugins/golang/skills/go-race-and-memory-model Skill
0★ repoAgent skill plugins for Go code quality and performance work.
tcf-jw/plan-with-loops/skills/plan-with-loops Skill
0★ repoPlan a task like Plan mode, then design the agent loop that executes it. Produces a read-only 4-part design doc: (1) standard step plan, (2) agent roster, (3) loop topology, (4) implementation plan wired to the Claude Code Workflow tool + subagents. Loop complexity scales with effort level (low/medium/high). Decides the roster and loop autonomously, then presents for approval. Writes no files. Use when the user wants to plan multi-agent, looped, or orchestrated work, asks to "design an agent loop", "plan with loops", "orchestrate this", or invokes /plan-with-loops.
dbmrq/agent-skills/skills/manage-agent-skills Skill
no license0★ repoCreate, update, release, and sync skills in the dbmrq/agent-skills repository (source of truth for personal Agent Skills). Use when the user asks to create a new skill, update an existing skill from a conversation or another repo, improve skill authoring practices, publish/release skills, or run install-all / gh skill sync — not when merely using a skill for its domain task.
Yco-0314/strata/skills/l3-execution/subagent-driven-development Skill
0★ repoExecute an implementation plan or set of issues by dispatching a fresh subagent per task, with two-stage review (spec compliance, then code quality) after each.
Yco-0314/strata/skills/l5-meta/drift-eval Skill
0★ repoUse to measure a skill that CONVERGES on single-shot eval (skill-eval Δ 0 because the model already does it by default) — runs an escalating multi-turn pressure scenario and checks whether the skill HOLDS the discipline where the baseline drifts. Triggers: "does this skill matter over a long session", "multi-turn eval", "drift test", "test verification/ponytail/router under pressure".
Yco-0314/strata/skills/l5-meta/skill-eval Skill
0★ repoUse when creating or editing a skill, and before shipping it — measures whether the skill actually changes the model's behavior by running each test prompt with the skill injected and without it (baseline), then comparing pass rates. Use when the user asks to evaluate, benchmark, or justify a skill, or asks "does this skill earn its context?".
yuelenghan/orbit/skills/release-orchestration Skill
0★ repoOrchestrate release preparation, execution, and reporting across tracker, repo, ci, and docs providers. Use for release readiness assessment, release branch creation, tagging, build triggering, tracker version management, or publishing release notes. Trigger phrases: '准备发布', '创建 release 分支', '发版', 'release 1.2', '发布准备', '发布执行', '发布报告', '打 tag', '触发 release build', '生成 changelog', '发布说明'.
aizech/bernhard-zechmann-skills/skills/engineering/mcp-builder Skill
0★ repoCreate an MCP server that exposes external APIs or services as well-designed tools. Use when building a Model Context Protocol server in Python or TypeScript.
aizech/bernhard-zechmann-skills/skills/engineering/skill-creator Skill
0★ repoCreate a new skill or improve an existing one. Use when the user wants to capture a workflow as a reusable skill, edit a skill, or optimize its triggering.
aizech/bernhard-zechmann-skills/skills/personal/agent-interview Skill
0★ repoCreate an audio interview with a selected agent using OpenAI TTS. Generates a single MP3 file with a Q&A podcast session.