Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: AI & models

9,018 results · page 215 of 301

  • review-adversarialSkillAI & models

    Reviews a change adversarially — establishes what it claims to do, hunts candidates from ten angles, then re-derives every candidate from source as a hostile second reader and reports only what survives.

    Ready to connect★ 63

    github.com/gke-labs/kube-agents53 stars

    View details
  • review-preflightSkillAI & models

    Runs the review passes required before a pull request is opened — adversarial and docs-drift — each in a context that did not write the change, and merges what they return into one disposition list.

    Ready to connect★ 63

    github.com/gke-labs/kube-agents53 stars

    View details
  • routeros-fundamentalsSkillAI & models

    RouterOS v7 domain knowledge for AI agents. Use when: working with MikroTik RouterOS, writing RouterOS CLI/script commands, calling RouterOS REST API, debugging why a Linux command fails on RouterOS, or when the user mentions MikroTik, RouterOS, CHR, or /ip /system /interface paths. Scope: RouterOS

    Ready to connect★ 63

    github.com/tikoci/routeros-skills63 stars

    View details
  • season-wordsSkillAI & models

    Use when a haiku needs a seasonal reference (kigo). Lists season words to weave in.

    Ready to connect★ 63

    github.com/fastagent-sh/fastagent58 stars

    View details
  • skill-reviewSkillAI & models

    Reviews agent skill definitions for token efficiency, clarity, and standardized formatting.

    Ready to connect★ 63

    github.com/gke-labs/kube-agents53 stars

    View details
  • skills-managerSkillAI & models

    Keep the AGENTS.md skills tables generated from skill descriptions, and understand how a fork syncs its skills from upstream. Use after editing a skill's frontmatter, when adding or removing a skill, or when the AGENTS.md skills-table check fails.

    Ready to connect★ 63

    github.com/nrjdalal/zerostarter63 stars

    View details
  • workload-rebalancingSkillAI & models

    Orchestrate cross-cluster workload rebalancing using the kanban board with the validation-then-declare pattern. Use when fleet utilization shows one cluster overutilized and another with headroom and a workload should move.

    Ready to connect★ 63

    github.com/gke-labs/kube-agents53 stars

    View details
  • add-chart-typeSkillAI & models

    Use when adding a new built-in chart type to drizzle-cube. Covers type definition, component, config, the unified chartRegistry entry, lazy loading, icons, exports, and the deliberately-separate chart-type lists in the MCP app, agent tools and CLI.

    Ready to connect★ 62

    github.com/cliftonc/drizzle-cube60 stars

    View details
  • addin-operationsSkillAI & models

    TIA Portal Add-In development in Visual Studio Code: creating Add-In C# projects, adding Add-In templates, compiling and debugging Add-Ins, converting Add-Ins from older TIA Portal versions and configuring Add-In project parameters.

    Ready to connect★ 62

    github.com/czarnak/totally-integrated-claude62 stars

    View details
  • Analogical ReasoningSkillAI & models

    This skill is triggered when an AI agent needs to handle the following situations: 1. The current case/problem has no direct, explicit provision in existing law (a legal gap); 2. Existing precedents, similar cases, or related legal norms need to be referenced to derive a solution for the current pro

    Ready to connect★ 62

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Argument Strength AssessmentSkillAI & models

    After an AI agent completes a piece of legal reasoning or argumentation, it should self-assess the conclusion, judge the overall strength and confidence of the argument, and identify and flag weak links in the reasoning chain. Trigger conditions include but are not limited to: - Providing a reliabil

    Ready to connect★ 62

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • arrow-typed-errorsSkillAI & models

    Models Kotlin logical failures with Arrow's context-parameter Raise DSL and wrappers such as Either, nullable, Option, and Ior. Use when implementing or simplifying typed-error flows, translating error types, replacing verbose Either handling, validating input with accumulation, or selecting an erro

    Ready to connect★ 62

    github.com/alexandru/social-publish62 stars

    View details
  • cae-coreSkillAI & models

    Shared foundation for Kit-CAE agent skills. Contains import APIs, visualization commands, stage discovery, format references, and utility scripts used by cae-visualization and cae-capture. Not invoked directly by users - loaded as a dependency by other CAE skills.

    Ready to connect★ 62

    github.com/nvidia-omniverse/kit-cae59 stars

    View details
  • cleaning-up-stale-feature-flagsSkillAI & models

    Identify stale feature flags in a PostHog project and clean up the code that checks them. Use when the user wants to find, audit, or remove unused, fully rolled out, or abandoned feature flags. When the agent can read and edit a repository it performs the code cleanup itself: tested local changes, a

    Ready to connect★ 62

    github.com/posthog/skills62 stars

    View details
  • comic-asset-ref-generatorSkillAI & models

    Phase-1 (S4) of a comic movie — PRODUCE the canonical reusable references the whole spiral conditions on. Per asset it bakes ONE canonical 1:1 white-bg identity ref via the agent mcp__codex__codex sidecar bake (Codex native image_gen — conditioned, never hand-pasted) OR, for a deterministic motif (c

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • comic-asset-review-loopSkillAI & models

    Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panel_gate (composed-output) or t

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • comic-authorSkillAI & models

    Phase 1 ORCHESTRATOR of a movie/comic — turn a fuzzy story idea into the Authored Source of Truth (a schema-valid comic.json + its locked asset library) by driving the detailed author skills in order (intent → style → outline → storyboard → assets → blueprints → prompts → comic.json), each gated by

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • comic-blueprint-authorSkillAI & models

    Phase-1 (S7 of the comic-author suite) — turn ONE locked panel_spec into a deterministic content-SVG blueprint that becomes the bake condition (reference #1 of the agent mcp__codex__codex sidecar bake), by WRITING A PYTHON GENERATOR (never raw SVG in chat — LLMs botch coordinates). The HEADLINE comi

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • comic-panel-prompt-builderSkillAI & models

    Phase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vetoes). No Codex call

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • comic-style-bible-lockSkillAI & models

    Phase-1 (S2) of the comic-author suite — compile the project's ART_BIBLE.md into an EXECUTABLE convergence target, not aesthetic prose. The bible is the ONE visual dialect read verbatim into every bake prompt AND into every visual reviewer's rubric (`style_consistency`/`identity_consistency` literal

    Ready to connect★ 62

    github.com/wanshuiyin/aris-movie-director62 stars

    View details
  • Deep ResearchSkillAI & models

    In-depth web research. Breaks a research question into subtopics, searches, reads, and filters across multiple sources, then generates a structured research report with citations. Based on the GPT Researcher methodology, with zero extra dependencies.

    Ready to connect★ 62

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Evidence EvaluationSkillAI & models

    This skill is triggered when evidence materials in a case need to be assessed for authenticity, legality, relevance (the three attributes of evidence), and probative value. Typical trigger scenarios include, but are not limited to: - After a party or their agent submits evidence, determining whether

    Ready to connect★ 62

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • exploring-mcp-intent-clustersSkillAI & models

    Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what

    Ready to connect★ 62

    github.com/posthog/skills62 stars

    View details
  • exploring-mcp-sessionsSkillAI & models

    Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions ha

    Ready to connect★ 62

    github.com/posthog/skills62 stars

    View details
  • exploring-mcp-tool-usageSkillAI & models

    Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how is my MCP doing?", "what should I look at?", "explore my tool calls", "who uses my MCP tools?", "what are agents doing with the MCP?", or pa

    Ready to connect★ 62

    github.com/posthog/skills62 stars

    View details
  • frontend-a11ySkillAI & models

    Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. Use when building any interactive UI component or form.

    Ready to connect★ 62

    github.com/dekaprayoga/aurixagent62 stars

    View details
  • gsd-add-backlogSkillAI & models

    Add an idea to the backlog parking lot (999.x numbering)

    Ready to connect★ 62

    github.com/tomascortereal/claude-code-setup62 stars

    View details
  • gsd-add-phaseSkillAI & models

    Add phase to end of current milestone in roadmap

    Ready to connect★ 62

    github.com/tomascortereal/claude-code-setup62 stars

    View details
  • gsd-add-testsSkillAI & models

    Generate tests for a completed phase based on UAT criteria and implementation

    Ready to connect★ 62

    github.com/tomascortereal/claude-code-setup62 stars

    View details
  • gsd-analyze-dependenciesSkillAI & models

    Analyze phase dependencies and suggest Depends on entries for ROADMAP.md

    Ready to connect★ 62

    github.com/tomascortereal/claude-code-setup62 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

54,826 of the 55,257 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI