Context & AI engineering
25,772 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
FluxonLab/Skillry/community/github-awesome-copilot/skills/python-mcp-server-generator Skill
no license10★ repoGenerate a complete MCP server project in Python with tools, resources, and proper configuration
Typescript mcp server generator
FluxonLab/Skillry/community/github-awesome-copilot/skills/typescript-mcp-server-generator Skill
no license10★ repoGenerate a complete MCP server project in TypeScript with tools, resources, and proper configuration
FluxonLab/Skillry/community/wshobson-agents/skills/embedding-strategies Skill
no license10★ repoSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
FluxonLab/Skillry/community/wshobson-agents/skills/llm-evaluation Skill
no license10★ repoImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
FluxonLab/Skillry/community/wshobson-agents/skills/prompt-engineering-patterns Skill
no license10★ repoMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
FluxonLab/Skillry/community/wshobson-agents/skills/rag-implementation Skill
no license10★ repoBuild Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/40-agent-workflow-design Skill
no license10★ repoUse when you need to design agent roles, handoffs, tool boundaries, workflow routing, and coordination rules.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/41-agent-governance-review Skill
no license10★ repoUse when you need to review agent permissions, recursion, tool access, safety rules, and active context size.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/42-prompt-systems-review Skill
no license10★ repoUse when you need to review prompts, instructions, evaluation criteria, hallucination risk, and execution clarity.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/43-rag-vector-search-review Skill
no license10★ repoUse when you need to review retrieval, embeddings, chunking, vector search, ranking, and grounding strategy.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/44-llm-evaluation-review Skill
no license10★ repoUse when you need to review LLM eval plans, rubrics, datasets, expected outputs, and regression checks.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/45-automation-mcp-gatekeeping Skill
no license10★ repoUse when you need to gate external automation, MCP, Rube, Composio, credentials, scopes, and tool activation.
FluxonLab/Skillry/plugins/ai-and-agent-systems/skills/46-agent-supply-chain-review Skill
no license10★ repoUse when you need to review third-party agents, skills, plugins, prompts, install scripts, and provenance.
FluxonLab/Skillry/plugins/core-operations/skills/89-project-agent-bootstrap Skill
no license10★ repoUse when starting medium or large project work, standardizing project-local agent guidance, or creating minimal AGENTS.md, .codex/project.toml, project skills, or project agent overrides from the global skill and agent pool.
FluxonLab/Skillry/plugins/devops-and-release/skills/62-handoff-readiness-check Skill
no license10★ repoUse when you need to check documentation, runbooks, install commands, local startup, tests, and transfer readiness.
FluxonLab/Skillry/plugins/optional-specialist/skills/79-local-llm-runtime-review Skill
no license10★ repoUse when you need to review local LLM runtimes, model routing, resource limits, privacy boundaries, and offline behavior.
324 memory and resource profiling
FluxonLab/Skillry/plugins/performance-and-cost/skills/324-memory-and-resource-profiling Skill
no license10★ repoUse when you need to profile memory and OS resources — heap profiling, finding leaks and unbounded growth, GC pressure, and leaked file descriptors, sockets, or connections, including processes that hit container memory limits and get OOM-killed.
FluxonLab/Skillry/plugins/performance-and-cost/skills/325-llm-api-cost-optimization Skill
no license10★ repoUse when you need to measure and reduce LLM/API spend with concrete tactics — per-call token instrumentation, prompt caching, model tiering (cheap vs. premium), request batching, context trimming, and a cost-per-request dashboard. Focuses on measurement plus implementable changes.
64 codex final execution prompt
FluxonLab/Skillry/plugins/product-docs-and-research/skills/64-codex-final-execution-prompt Skill
no license10★ repoUse when you need to write strict final execution prompts for Codex, Claude, Copilot, or other coding agents.
FluxonLab/Skillry/plugins/skill-library-and-installation/skills/73-skill-to-agent-router Skill
no license10★ repoUse when you need to map skills to agents, departments, optional bindings, exclusions, and activation rules.
walterkken/doc-driven-engineering-software-skills/comsol-agent Skill
no license10★ repoAutomate COMSOL Multiphysics modeling and simulation tasks through doc-driven workflows: discover installed COMSOL access, retrieve official/local API documentation, generate Java/MATLAB/COMSOL batch scripts, run or guide simulations, diagnose blockers, and search trusted COMSOL forums when needed. Use when Codex is asked to create, modify, run, debug, or explain COMSOL models, MPH files, LiveLink workflows, parametric sweeps, geometry/material/physics setup, meshing, solving, or result export.
walterkken/doc-driven-engineering-software-skills/solidworks-agent Skill
no license10★ repoAutomate SOLIDWORKS modeling, assembly, drawing, and export workflows through doc-driven execution: discover installed SOLIDWORKS/API access, retrieve official/local API documentation, generate VBA/API macro or COM automation guidance, diagnose blockers, and search trusted SOLIDWORKS forums when needed. Use when Codex is asked to create, modify, batch process, debug, or explain SOLIDWORKS parts, assemblies, drawings, features, configurations, equations, mates, BOMs, exports, or CAD automation.
katalon-labs/true-skills/plugins/katalon-true-platform/skills/platform-setup Skill
10★ repoSet up, verify, and troubleshoot Katalon True Platform/TestOps MCP connectivity for any AI coding agent. Use when you need to install or configure the Katalon MCP server, connect to a Katalon platform account, verify available Katalon MCP tools, diagnose missing authentication or repository access, confirm project/repository discovery, or explain what platform operations are and are not exposed through the MCP.
katalon-labs/true-skills/skills/platform-setup Skill
10★ repoSet up, verify, and troubleshoot Katalon True Platform/TestOps MCP connectivity for any AI coding agent. Use when you need to install or configure the Katalon MCP server, connect to a Katalon platform account, verify available Katalon MCP tools, diagnose missing authentication or repository access, confirm project/repository discovery, or explain what platform operations are and are not exposed through the MCP. One-time cross-cutting setup, run once by whoever wires the agent to the platform, before any lifecycle skill can work.
narumiruna/skills/deprecated/naming-agent-skills Skill
10★ repoDeprecated compatibility reference for choosing, reviewing, renaming, or standardizing agent skill names. Use the active creating-agent-skills workflow for current naming and authorized repository rename work.
narumiruna/skills/skills/workflow-repository/creating-agent-skills Skill
10★ repoCreate, name, rename, revise, or review agent skills for reliable triggering, lean instructions, justified resources, aligned UI metadata, repository discovery, and validation. Use for new skills, naming decisions, authorized repository renames, skill scaffolding, workflow-to-skill conversion, prompt optimization, or skill audits.
narumiruna/skills/skills/workflow-repository/maintaining-memory-md Skill
10★ repoRead, maintain, and curate concise repository-root MEMORY.md notes for verified gotchas, durable user preferences, and established repository conventions. Use at repository-conversation start, when MEMORY.md is mentioned, when its curation or cleanup is requested, when concrete evidence suggests it may be stale, or when a qualifying memory emerges.
narumiruna/skills/skills/workflow-repository/scoring-agent-skills Skill
10★ repoScore or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
narumiruna/skills/skills/workflow-repository/writing-agents-md Skill
10★ repoCreate, review, audit, migrate, or update scoped AGENTS.md repository guidance with evidence-backed commands, concise constraints, explicit authority, instruction precedence, and verifiable completion criteria.
liyanqing90/rootloom/plugins/rootloom/skills/project-memory Skill
10★ repoExperimentally initialize, retrieve, and explicitly update Rootloom's repository-owned project memory for architecture, known risks, durable decisions, and evidence-backed failure lessons. Use only when explicitly requested and durable history will change a future engineering decision. Memory is advisory and outside stable Core.
casioreview20-glitch/forge-os/skills-v2/kernel/consolidating-project-memory Skill
10★ repoUse when decisions, blockers, conventions, and stable summaries must survive across tasks without treating conversation transcript as the project source of truth.
casioreview20-glitch/forge-os/skills-v2/kernel/learning-from-agent-failures Skill
10★ repoUse when repeated agent, route, tool, context, or verification failures reveal a reusable technique gap rather than a one-off project defect.
casioreview20-glitch/forge-os/skills-v2/kernel/planning-parallel-agent-work Skill
10★ repoUse when several work units are independent enough to execute concurrently but still need deterministic ownership, coverage, resource locks, and verified joins.
casioreview20-glitch/forge-os/skills-v2/kernel/writing-agent-skills-with-tdd Skill
10★ repoUse when creating or changing an agent skill whose behavior, routing, discipline, or technique must improve over a measurable baseline rather than merely sound persuasive.
casioreview20-glitch/forge-os/skills-v2/l1/planning/assigning-agent-work Skill
10★ repoUse when assigning agent work within planning lifecycle boundaries, especially when does the artifact make the owned decision for assigning agent work explicit and bounded?.
casioreview20-glitch/forge-os/skills-v2/stable/testing-agent-tool-abuse Skill
10★ repoUse when verify that untrusted prompts, retrieved content, and agent outputs cannot exceed tool authority or bypass human decisions, especially when can content from a file or webpage cause a privileged call?.
casioreview20-glitch/forge-os/skills/core/kernel/auditing-agent-actions Skill
10★ repoUse when auditing agent actions is required during kernel work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/core/meta/learning-from-agent-failures Skill
10★ repoUse when learning from agent failures is required during meta work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/core/meta/writing-agent-skills Skill
10★ repoUse when writing agent skills is required during meta work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/core/planning/assigning-agent-work Skill
10★ repoUse when assigning agent work is required during planning work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/core/security/testing-agent-tool-abuse Skill
10★ repoUse when testing agent tool abuse is required during security work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/core/security/testing-prompt-injection Skill
10★ repoUse when testing prompt injection is required during security work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
casioreview20-glitch/forge-os/skills/domains/ai-products/testing-ai-prompt-injection Skill
10★ repoUse when testing ai prompt injection is required during ai-products product work, especially when the result must be traceable, independently reviewable, and safe to hand to another agent.
KemingHe/common-devx/.agents/skills/next-session-handoff Skill
10★ repoGenerate structured handoff documents for context transfer across AI session boundaries. Use at the end of a session to preserve decisions, objectives, and resources for the next session. Triggers: "handoff", "next session", "session handoff", "wrap up session", "context transfer".
cacheforge-ai/cacheforge-skills/skills/swarm-self-heal Skill
10★ repoSwarm reliability watchdog for OpenClaw — validates gateway/channel and every lane, performs bounded recovery, and emits auditable receipts.
The same file is in 4 other repositories
nagarjuna-msr/fable-god-mode/skills/session-handoff Skill
10★ repoPause a heavy session at a NATURAL boundary and hand off to a fresh session via an audited handoff doc + ONE paste-able resume one-liner. Trigger when the user asks to resume/continue in a NEW session or chat ('resume in a new session', 'new session resumption', 'session handoff', 'let's pause and continue in a new chat', 'give me the resume one-liner', 'pause at a natural boundary and continue in a new session'), or asks to wrap up because the session/context is heavy. ALSO trigger proactively: when the session context has grown very heavy (roughly 500k+ tokens of history — multiple compactions, a long multi-phase transcript; a heuristic, not a counter) and a natural boundary is near, PROPOSE this skill to the user in one line; never pause on your own. Project-agnostic — any repo, any teammate, any session type. The handoff gets a MANDATORY clean-context audit (cross-model via Codex preferred when installed AND consented) to minimize context loss, and the deliverable is ONE line pasted into the new session.
Context compaction verification and recovery
ChrisLamDev/hermes-core-skills/skills/context-compaction-verification-and-recovery Skill
10★ repoUse when verifying that tool commands actually executed after compaction.
ChrisLamDev/hermes-core-skills/skills/hermes-agent Skill
10★ repoUse when setting up or extending Hermes Agent.
Multi agent browser text extraction
ChrisLamDev/hermes-core-skills/skills/multi-agent-browser-text-extraction Skill
10★ repoUse delegate_task with multiple browser-equipped sub-agents to extract verbatim text from Chinese academic/religious websites with JavaScript-heavy tree navigation. Covers coordination patterns, site-specific navigation, error recovery, and QA verification.
ChrisLamDev/hermes-core-skills/skills/subagent-driven-development Skill
10★ repoUse when executing implementation plans with independent tasks in the current session
mattbaconz/signal/gemini-signal/skills/signal-ckpt Skill
10★ repoManually triggers a checkpoint compression of the current session state. Collapses conversation history into a compact state atom (≤50 tokens). Use when user types /signal-ckpt, "checkpoint", "compress context", "summarize session", "save state", or when the context window is getting large. In SIGNAL-3 mode this fires automatically every 5 turns.
mattbaconz/signal/kiro-signal/skills/signal-ckpt Skill
10★ repoManually triggers a checkpoint compression of the current session state. Collapses conversation history into a compact state atom (≤50 tokens). Use when user types /signal-ckpt, "checkpoint", "compress context", "summarize session", "save state", or when the context window is getting large. In SIGNAL-3 mode this fires automatically every 5 turns.
jnMetaCode/local-agent-toolkit/skills/tracelet-instrument Skill
no license10★ repoInstrument an AI agent or LLM app with OpenTelemetry and watch its runs live in tracelet (local DevTools). Use when asked to add tracing/observability to an agent, or to debug what an agent actually did.
The same file is in 1 other repository
weklund/fiduciary/.claude/skills/onboard Skill
10★ repoFinancial advisor intake — run when a user first sets up this project, says "onboard", "set up my profile", "get started", "intake", "configure my finances", or when CLAUDE.md has no Client Context section. Conducts a structured interview modeled on the CFP Board's 7-step process and writes personalized context to memory files (never to CLAUDE.md). USE THIS SKILL for any first-time setup or when the user wants to update their financial profile.
pantheon-org/tekhne/crates/skill-validator-rs/tests/golden-corpus/fixtures/examples/review-skill Skill
10★ repoReview a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise authors on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.
pantheon-org/tekhne/skills/agentic-harness/agents-md Skill
10★ repoCreate and maintain AGENTS.md documentation for simple projects, complex monorepos, deterministic discovery, scoped instruction files, low-token navigation; use when generating AGENTS.md, updating agent docs, standardizing AI-facing project guidance.
pantheon-org/tekhne/skills/agentic-harness/opencode-toolkit/design-agents Skill
10★ repoCreate and refine OpenCode agents via guided Q&A. Use when creating an agent file, improving an existing agent, configuring AGENTS.md frontmatter, setting subagent_type, defining allowed-tools, restricting permissions, designing agent routing, writing a system prompt, configuring mode: subagent, setting a permission block, or working with the Task tool delegation pattern. Examples: 'Create an agent for code reviews', 'My agent ignores context', 'Add a database expert subagent', 'Make my agent faster', 'Agent triggers on wrong requests'.
pantheon-org/tekhne/skills/documentation/research/reproduce-benchmark Skill
10★ repoReproduce and verify the benchmark claims of a tool or paper already triaged in the research repo. Locates the benchmark harness, runs it, and records verified vs. reported figures in benchmarks/sources/{slug}-repro.md. Triggers: reproduce benchmark, verify claims, run benchmark, check benchmark, benchmark reproduction, verify numbers.
pantheon-org/tekhne/skills/documentation/research/triage-tool Skill
10★ repoTriage a tool or library into a structured reference summary for the research repo. Use when given a GitHub URL, npm package, PyPI package, or CLI tool name. Creates references/{slug}.md with architecture overview and scope assessment; adds REVIEWED.md entry and REFERENCE_INDEX.md row. Triggers: triage tool, add tool, analyse tool, GitHub project, npm package, PyPI package, library, framework, CLI tool, MCP server, open source project.
pantheon-org/tekhne/skills/repository-mgmt/nx/nx-plugin-authoring Skill
10★ repoCreate Nx plugins with custom generators and executors for TypeScript monorepos. Covers plugin scaffolding, Tree API usage, schema-driven options, ExecutorContext API, template generation, project-graph-safe updates, cache-aware outputs, and testable workflows. Use when creating Nx plugins, building custom generators, implementing executors, enforcing conventions, or extending Nx workspace automation.