41,031 tagged agent-skills, measured the same way as everything else here.
Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 154ai-skills 152anthropic-claude 136claude-ai 136
Nagacash/character-continuity-skill
Skill Claude CodeCodex
Guides character and continuity consistency across the shots of an AI-generated film, so a character looks like the same person in every shot. Should be used when planning or producing a multi-shot film, series, ad or music video that features a recurring character, and when diagnosing a face that has drifted…
Skill Claude Code
A release checklist for research repositories that publish versions with Zenodo, a service that assigns permanent digital object identifiers (DOIs) to research outputs. It also records a Software Heritage identifier, which helps identify archived source code.
Skill Claude CodeCodex
Build and run a source-verified Markdown knowledge vault (opens as an Obsidian vault). Ingests books, PDFs, transcripts, and articles into atomic, cross-linked, cited notes, then gates every note and every answer behind an independent verification pass that re-reads the source cold and loops until a round finds…
Skill Claude Code
Cost-tiered planning pipeline. Use when the user asks to plan a feature, refactor, migration, or fix with agentmaster, or invokes /agentmaster-plan. A frontier orchestrator dispatches cheap scout/code-analyst workers for evidence, detects the project toolchain, drafts a parallel-safe plan with an evidence ledger, and…
Skill Codex
Act as a senior GitHub platform architect, open-source maintainer, DevSecOps engineer, and repository governance specialist. Produce repository systems that are understandable, maintainable, secure by default, automation-friendly, and practical for real teams.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A workflow for comparing two versions of a prompt, skill, or piece of text without revealing which one is the new version. Separate agents create the versions, and a person scores them without seeing their labels.
Skill Claude Code
Two-phase PR review companion. Phase 1: Socratic conversational walkthrough that builds the reviewer's mental model through guided questions — fighting cognitive debt by ensuring comprehension before approval. Phase 2: automated quality checks via pr-review-toolkit (Claude Code) or inline review (any host). Use when…
Skill Claude CodeCodex
Creates reviewable atomic git commits from explicit file or folder paths after the user asks to commit. Use when committing selected files, preserving unrelated work, splitting broad changes into logical commits, committing ticket-scoped work, or preparing a clean review series through scoped inspection, boundary…
Skill Claude CodeCodex
A business-data analysis assistant for MySQL databases and CSV or Excel files. It helps explain business measures such as sales value, daily active users, conversion, retention, repeat purchases, and customer groups.
sowadalmughni/contextual-humanizer
Skill Claude CodeCodex
Remove signs of AI-generated writing from any text: articles, essays, documentation, reports, fiction, blog posts, LinkedIn posts and articles, emails, landing pages, ads, and marketing copy. Determines whether the piece is neutral/narrative (strip promotional language, tighten prose) or persuasive/converting (keep…
Skill Claude Code
Build or edit Figma designs and components using the ( ) design system. Load alongside figma-use whenever a task targets / / products — reusing the published Variables, UI Kit, and Icons libraries (semantic tokens, text styles, effect/elevation styles, components) instead of hardcoding colors, spacing, type, or…
CarterIrish/code-architecture-skill
Skill Claude CodeCodex
Plans, documents, and reviews code architecture for software projects. Produces structured architecture documents with Mermaid diagrams through a collaborative interview workflow. Triggers on architecture planning, project structuring, folder organization, system design, component design, data flow planning, codebase…
astropham1808/astro-agent-skills
Skill Codex
Run a repository story through two isolated Codex sessions, with one implementer working in a Git worktree and one independent reviewer inspecting the branch, followed by a bounded fix pass, deterministic verification, and a human PR and merge gate. Use when the user explicitly asks for a dual-agent Codex workflow, an…
Skill Claude CodeCodex
Honest-completion ruleset for changes that touch tests or the code they cover. Use before deleting, skipping, renaming, or rewriting a test, before weakening an assertion, and before hardcoding or stubbing an implementation to make a test pass. Also covers what to do when a test looks genuinely wrong.
brackendev/clojurescript-skills
Skill Claude CodeCodex
Use when writing, editing, reviewing, or discussing ClojureScript code that compiles to JavaScript and runs on a JS host (browser, Node.js, or other JS runtime). Triggers: .cljs files, .cljc files compiled to JS, shadow-cljs.edn, figwheel-main.edn, ClojureScript deps.edn projects, cljs.test, JavaScript interop (js/…
Skill Claude Code
Run work in an isolated workspace: git worktree + devcontainer, driven through the fr isolation CLI (exec-bridge). Use when feature work must not touch the base repo, when fr-brainstorming or fr-goal needs a workspace, when the operator says "isolate this" / "run it in the container", or to clean up after a merged PR.…
Skill Claude CodeCodex
Standing session rules that must be loaded at the start of every session, before any other work. Covers the quality bar (never trade correctness for token savings), the total ban on em-dashes, the useEffect ban, the comment policy, and per-commit/per-push authorization. After loading, wait for the user's actual…
Skill Claude CodeCodex
Turn a codebase into interactive architecture diagram as a single HTML file: four levels of drill-down, hover a port to see what the interface actually carries, hover an inventory row to see the real source snippet, and play back representative end-to-end scenarios. File/class/function inventories are extracted from…
Skill Claude Code
Evidence-driven dissection of an existing service, written plan, or codebase area. Interrogates every entity (table, field, component, endpoint, module, boundary) against ground truth from multiple sources at once, red-teams each verdict devil's-advocate style, and arrives at the minimal-build optimization plan. Runs…
Skill Claude CodeCodex
Use when debugging failures, writing tests, starting multi-step tasks, modifying build systems, integrating APIs, or validating assumptions before heavy execution.
Skill Claude CodeCodex
A lightweight engineering workflow for turning an idea into a real, shippable product with an AI coding agent. Core = Karpathy's four coding disciplines (think before coding / simplicity first / surgical changes / goal-driven; battle-tested), plus an Explore→Plan→Build→Polish→Ship process, task tiers (skip the process…
lubochka/xiigen-general-skills
Skill Claude CodeCodex
Resolve which instructions win when rules conflict. Use at the start of every task and whenever instructions disagree.
Skill Codex
Coordinate substantive software work with GPT-6 Astra at the root and verified Astra and Luna executor profiles. Covers durable assignments, isolated writer worktrees, candidate review, validated delivery, and human-confirmed Ultra takeovers. Invoke it before planning, delegating, coordinating, or validating…
Skill Claude CodeCodex
Anti-sycophancy protocol (明辨). Use whenever the user contradicts, corrects, or pushes back on one of your conclusions; when you notice you are about to reverse a position mainly because the user insisted; or when a disagreement has run two or more rounds without new evidence. Classifies the dispute (fact / tradeoff /…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: