Claude Code Skills · page 72

Context-aware translation that preserves tone, style, and natural word order. Use when translating UI strings, documentation, marketing copy, or any multilingual content. Infers register, domain, and style from the source text and surrounding codebase context.

Short-form, explainer, and demo video generation via a key-optional 3-tier router. Composes scripts, oma-voice narration, oma-image/oma-slide/stock visuals, key-free captions, and a per-run agent-authored Remotion composition (always-latest Remotion + remotion-dev/skills) into reproducible run directories. Routes three modes — shorts/reels (9:16), explainer (16:9 README/code/data), and demo/walkthrough (screen capture, incl. supervised headed web-app capture of any URL). Use for video, shorts, reels, short-form, demo, explainer, walkthrough, screencast, web capture, video generation, 영상, 숏폼, 쇼츠, 릴스, 데모, 설명 영상.

>

A skill whose body deliberately exceeds the 500-line recommendation.

A minimal, fully spec-conformant fixture skill used to exercise the happy path.

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Generate a Python code skeleton from an experiment blueprint

Search academic literature and generate research hypotheses

Produce an experiment blueprint from a research hypothesis

Draft a LaTeX research paper from all previous stage outputs

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis

Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction

>

Deep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning

Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing

Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)

Generate personalized news intelligence with verified sources (7-day freshness requirement)

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say "log this to my journal", "add to today's journal", "reflect on today/yesterday", or when finishing a meaningful chunk of work in any session.

Pick the right way to represent a dataset so a reader gets the finding in three seconds — a catalog of 20+ chart and diagram forms with when-to-use and failure modes, plus the encoding decisions that make any of them readable (takeaway headline, direct labels, kill the axis, highlight-and-mute, show the caveat). Style-agnostic — use with whatever palette or design system the destination already has. Use when charting survey results, benchmark data, usage metrics, or research findings for a post, brief, deck, or report, and whenever the default bar chart feels like it's burying the point.

>

Audit and export open issues from any project tracker with summary analysis and vault archival

Generate product requirements documents with optional publishing to Confluence or other wiki platforms

Generate categorized release notes from any source (GitHub, Linear, Jira, or manual input) with optional publishing

>

Build frameworks from scattered insights across all braindumps and notes

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).

Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering

Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries

Source authentic, high-res PUBLIC-DOMAIN artwork from museum open-access APIs (Met, Cleveland, SMK, Rijksmuseum, NGA, Art Institute of Chicago, Getty, Smithsonian) instead of AI-generated or generic-stock imagery. The default move whenever a visual needs an aesthetic, credible image (blog heroes, decks, social cards, essay/spec figures). Verified keyless recipes + licensing rules inside.

Edit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.

Personalize COG for your workflow - creates profile, interests, and watchlist files with guided setup (run this first!)

Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansion, keyboard/a11y). House-system-first; maps to Carbon/Polaris/Atlaskit/Fluent/Primer/Material3/Radix-shadcn/Ant. The counterpart to taste-skill, which owns landing/portfolio/marketing.

Publish any markdown file from the vault to Confluence with format conversion and approval gate

>

Produce and continuously maintain ONE living review document for a multi-item session — a cockpit header (Progress checklist, Working folder, Context) plus per-item review cards that you approve or request changes on directly in the doc or side panel. Use whenever a session has multiple deliverables you need to review/approve (meeting-processing + planning, multi-ticket work, briefs with several drafts, any "do X, then plan/draft Y and Z"). The doc is the interaction surface: you edit it (or reply in chat) to approve/change; the agent keeps it live as work progresses.

Evaluate URLs and tools — check vault coverage, assess relevance, recommend save or skip

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Generate daily team intelligence brief by cross-referencing GitHub, Linear, Slack, PostHog, meetings, and braindumps with two-way Linear sync-back

>

Check for and apply upstream COG framework updates (skills, docs, scripts) without touching personal content

Maintain and update product knowledge base from releases, features, and project changes with optional wiki sync

Quick capture URLs with automatic content extraction, insights, and categorization into knowledge booklets

Cross-domain pattern analysis and strategic reflection for weekly review

Use when a Hermes agent needs to evaluate agent behavior, run Autocontext scenarios, inspect Hermes curator state, export reusable knowledge, or prepare local MLX/CUDA training data through the autoctx CLI.

Operational knowledge for the grid_ctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging grid_ctf strategies.

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing commands or fixing bugs in existing commands.

Writes Vitest tests following project patterns: __tests__/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment variable save/restore in beforeEach/afterEach, vi.clearAllMocks() lifecycle, and test file organization. Use when user says 'write tests', 'add test coverage', 'test this', creates *.test.ts files, or when test failures appear in CI. Do NOT use for non-test code or for debugging without writing tests.

Discovers and installs community skills from the public registry. Use when the user mentions a technology, framework, or task that could benefit from specialized skills not yet installed, asks 'how do I do X', 'find a skill for X', or starts work in a new technology area. Proactively suggest when the user's task involves tools or frameworks without existing skills.

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error handling via tracking and recovery. Use when adding a new model backend, integrating a third-party LLM API, or extending LLM platform support. Do NOT use for fixing bugs in existing providers, modifying existing provider behavior, or changing the LLMProvider interface.

Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in the future.

Add a new deterministic scoring check in src/scoring/checks/ that evaluates config quality. Follows the Check[] return pattern, uses point constants from src/scoring/constants.ts, and integrates via filterChecksForTarget() in src/scoring/index.ts. Use when user says 'add scoring check', 'new check', 'modify scoring criteria', or works in src/scoring/checks/. Do NOT use for display changes or refactoring scoring logic.

Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.

Add a new platform writer module in src/writers/ that generates and writes agent config files for a supported platform. Each writer exports a function that accepts a config interface, creates directories (rules/, skills/, mcp configs), writes files with proper formatting and frontmatter, and returns string[] of written file paths. Use when adding platform support for a new agent, integrating a new code AI tool, or extending caliber to support new targets. Do NOT use for modifying existing writers, refactoring scoring logic, or changing how writers are invoked.

Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab / cloudflared / llama.cpp / Node. Encodes exactly which files to edit (`sidecar/package.json`, `sidecar/scripts/vendor-platform.ts`), how to source each version and compute its SHA256, the Claude SDK↔CLI lockstep rule, npm dist-tags caveats (latest vs next vs stable), the cross-arch (arm64+x64) SHA requirement, and the mandatory verification gates. Use whenever the user wants to upgrade / bump / update / refresh a bundled agent CLI or SDK version, check whether a vendor is behind latest, or run a dependency version sweep in the Helmor repo.

Use the Helmor CLI to remote-control Helmor from the terminal. Use when the user asks to inspect Helmor data/settings, manage repositories/workspaces/sessions/files, send prompts to agents, list models, use GitHub integration, inspect scripts, run Helmor as an MCP server, generate shell completions, quit a running app, check/install/update the Helmor CLI beta, install/update Helmor skills through the beta app flow, or needs the Helmor command reference. Also plan and build a large change as a stack of dependent PRs (`/helmor-cli stack`), split a change you've already written into a stack (`/helmor-cli break`), and re-sync a stack after lower layers change or merge (`/helmor-cli restack`).

Autonomous local-development debugging loop for Helmor bugs. Use when the user asks an agent to reproduce, diagnose, instrument, fix, or verify a Helmor local dev build issue using repeated local UI simulation, temporary logging, Tauri MCP/towery MCP, screenshots, DOM/accessibility snapshots, IPC traces, console/system logs, terminal/run-script logs, or multi-attempt verification. This skill coordinates with $helmor-debug-operate for operating the running desktop app.

Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing, terminal/run-script buffer inspection, switching workspaces or sessions, creating/renaming/closing sessions, typing or sending composer prompts, inspecting styles/logs, or reproducing Helmor desktop behavior as a user would.

Prepare Helmor releases by inspecting the current branch, drafting a concise user-facing Changesets entry first (bump + body — keep it as short as possible), creating any needed pending in-app release announcement under `.announcements/`, and then showing the user the result with a short menu of adjustments they can pick from. Use when the user wants to cut a release, write a changeset, decide patch/minor/major, draft GitHub release notes, create a release announcement, or summarize branch changes into release-ready language.

Run the AI Search Hub browser automation scripts for Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, and MiniMax. Use this skill when the user wants to ask one of those sites a prompt, auto-start or attach to a Chrome DevTools session on port 9222, seed an isolated debug browser profile from the user's local browser data, detect whether login is required, wait for the user to finish logging in if needed, and then continue automatically.

Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk', 'seminar slides', 'thesis defense', 'research presentation', 'academic deck', 'academic presentation'. Also triggers when the user asks to 'make slides' in combination with academic content (e.g., 'make slides for my paper on X', 'create a presentation for my dissertation defense', 'build a deck for my grant proposal'). This skill governs CONTENT and STRUCTURE decisions. For the technical work of creating or editing the .pptx file itself, also read the pptx SKILL.md.

>

>

>

>

Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop>/README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.

Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.

>

>

>

Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram.

29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.

Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. Invoke it on your own initiative the moment you finish writing, editing, or refactoring non-trivial production code, before presenting or committing — don't wait to be asked. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).

Review generated or changed documentation before it ships — READMEs, API references, docstrings, PHPDoc/JSDoc, changelogs, tutorials, and doc sites. Best used reactively after an agent writes or edits docs, after code changes documented behavior, or before publishing docs. Use when the user says 'review the docs', 'is this documentation accurate', 'update the docs', 'write a README', 'document this API', 'add a docstring', or 'add a changelog entry'. Core job: verify every referenced function, flag, endpoint, config key, and code sample against the source; catch docs-vs-code drift; strip filler and unverifiable claims. DO NOT USE for production code review (use clean-code-guard), test review (use test-guard), marketing copy or blog posts, prose style editing of non-technical writing, or documentation site theming.

Review generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactors tests, before presenting, committing, or merging them. Use for pytest (test_*.py, *_test.py), PHPUnit/Pest (*Test.php), Jest/Vitest (*.test.ts, *.spec.js), Go (*_test.go), files under tests/, __tests__/, or spec/, and review requests like 'write tests for X', 'add tests', 'test this', 'review these tests', or PR diffs containing tests. Can also guide test writing when explicitly invoked before the work. This skill is the quality gate that prevents AI-generated test bloat. DO NOT USE for production or implementation code review (use clean-code-guard), CI or test-runner configuration, running or debugging tests, or general architecture discussion.

Review generated or changed WooCommerce code — extensions, payment and shipping integrations, checkout customizations, and order/product logic — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WooCommerce APIs: wc_get_order, wc_get_orders, wc_get_product, WC() cart or session, woocommerce_* hooks, Store API endpoints, payment gateways, order or product meta, HPOS, subscriptions, or bookings. Use on 'review this Woo plugin', 'is this HPOS compatible', or after tasks like 'write a WooCommerce extension', 'add a checkout field', 'hook into the order flow', or 'update stock'. Enforces HPOS-safe order access, CRUD over direct meta, feature-compatibility declarations, server-side checkout validation, money-handling discipline, and hooks over template overrides. DO NOT USE for WordPress code without WooCommerce APIs (use wp-guard), generic code review (use clean-code-guard), test review (use test-guard), or store configuration and admin-screen questions.

Review generated or changed WordPress code — plugins, themes, and blocks — before it ships. Best used reactively after an agent writes, edits, or reviews code touching WordPress APIs: add_action/add_filter, shortcodes, meta boxes, AJAX handlers, REST routes, WP_Query or $wpdb, widgets, or WP-CLI commands. Use on 'review this plugin', 'is this safe to ship', 'make this translatable', 'speed up this query', or after tasks like 'write a plugin' or 'add an endpoint/shortcode/meta box'. Enforces escaping and sanitization, nonces plus capability checks, prepared database queries, core-API-first development, translation-ready strings, and query/caching discipline. DO NOT USE for WooCommerce-specific order, product, or checkout logic (use woo-guard), non-WordPress PHP, generic code quality review (use clean-code-guard), test code review (use test-guard), server or hosting configuration, or conceptual WordPress questions.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Run, interpret, and iterate on the OpenInference GenAI conformance MVP at python/openinference-instrumentation/scripts/conformance/. Use when the user mentions GenAI conformance, OTel GenAI semantic conventions, Weaver registry live-check, the dual-write conversion (`_genai_conversion.py`, `enable_genai_semconv`), `gen_ai.*` attribute coverage, or asks to add new providers / scenarios to the conformance harness.

>

>

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

Investigate and propose fixes for Python canary cron failures in the openinference repo. Use when the user mentions Python canary failures, Python cron failures, or when the auto-fix CI job reports Python instrumentation canary issues.

>

AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends AIPex's capabilities with specialized knowledge, workflows, or tool integrations.

Minimalist UX/Interaction Audit Expert that deconstructs complex interactions through cognitive load and operational efficiency lenses. Use this skill when you need to perform a UX walkthrough audit on a Figma prototype or web interface, evaluating usability based on principles like fewer clicks, less UI elements, no hidden logic, and self-explanatory design.

WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.