Claude Skill Registry

Provides a concise reference for using the Ky HTTP client, covering core usage, options, retries, hooks, error handling, and best practices.

Cut AI tells and restore human voice. Fires when drafting or editing prose, reviewing text for AI tells, or when the user asks to remove AI patterns or add voice.

Provides RESTful API design patterns and best practices for creating endpoints, designing APIs, and implementing routes.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Writes and edits .omg.md files, a human-first DSL for API specification that compiles to OpenAPI 3.1.

Fetch GitHub CI failure information, analyze root causes, reproduce locally, and propose a fix plan. Use `/fix-ci` for current branch or `/fix-ci <run-id>` for a specific run.

Changes the current working directory in Bash using the provided path without modification.

Use when the user asks "how does X work" and wants an architecture walkthrough of the code path or subsystem, including its gotchas. Don't use for tasks that require source or remote-system changes.

Clones disks, benchmarks I/O, and converts files with progress monitoring options.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use contexts for runtime behavior.

Process JSON data from files or standard input using jq filters for extraction, filtering, and transformation.

CRITICAL learning capture. Extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes and preserve what works. Use PROACTIVELY after user corrections ("no", "wrong"), after praise ("perfect", "exactly"), when discovering edge cases, or when skills are heavily used. Without reflection, valuable learnings are LOST forever. Acts as continuous improvement engine for all skills. Invoke EARLY and OFTEN - every correction is a learning opportunity.

Before and after changing anything shared — a function's return value, a signature, a schema, a label set, a config default, a constant, a file format — find every consumer and actually run them. Catches the change that looks purely additive but silently breaks a contract in a file you never opened. Use when editing shared code, adding a field/column/return element, renaming, changing units or defaults, or touching a pipeline that produces reported numbers.

Configure Gemini and Codex CLI tools with Cloudflare AI Gateway endpoints and MCP servers.

Use when you need to interact with Google services from Clawdbot, including Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Designs Elasticsearch indexes and mappings, tunes queries, sizes clusters, and handles operations like shard/replica strategy, ILM, monitoring, troubleshooting, and safe reindexing or upgrades.

Configure which models pstack uses per role. Detects your available Claude models and writes a per-role override file that the user can include from their CLAUDE.md. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.

Defines end-to-end user experience behavior and interaction logic, covering flow design, state machines, error recovery, validation, accessibility, and testable acceptance criteria.

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

Quick reference for the Agent Farm CLI, covering tower, dashboard, builder management, and configuration commands.

Use when asked to audit comments in code files and propose structural replacements or deletions with per-candidate approval. Enumerates comments in C, JavaScript, TypeScript, HTML, CSS, and shell-style syntax, classifies each as earned or unearned, drafts structural alternatives, and returns a complete accounting ledger. Not for deterministic commented-out-code removal; use deslop.

Covers AI, machine learning, LLMs, prompt engineering, and blockchain development with code examples and best practices for building AI applications and smart contracts.

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.

Make the user defend a proposal they committed to. Use when a proposal is committed but its decisions are undefended.

Fetches any X/Twitter post as structured JSON, including full article content, author info, and engagement metrics, without scraping or a browser.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Creates, validates, and improves ALPS profiles for RESTful API design, generating them from natural language descriptions and providing structured feedback.

Activate Specification Know-How: load the SpecBook format contract, the SpecBook schema configuration of the project, and the list of specification (SPEC) artifacts into the context, so the specification can be read, queried, explained, and edited ad-hoc in plain conversation. Use *automatically* whenever the user wants to work with the specification files -- asks what the "spec" or "specification" says, wants to "look up", "query", "check", or "explain" specification content, or wants a small ad-hoc change to it -- and no dedicated specification skill (`ase-spec-edit`, `ase-sync-import`, `ase-sync-reconcile`, `ase-sync-export`) is invoked, as those activate the know-how implicitly.

查询高德地图的实时天气、地点搜索、驾车路线规划、地理编码和行政区划信息，帮助用户获取地理位置相关数据。

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.

Provides curl command examples for downloading files, making HTTP requests, handling authentication, using proxies, and performing FTP operations.

Summarize authored commits over a user-specified time period into a concise update

Build trading, liquidity provision, and pool management applications on Solana and Eclipse using the Orca Whirlpools SDK, covering swaps, positions, and fee harvesting.

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

Interact with the Taco crypto trading platform via API to fetch market data, manage positions, and compute technical indicators across multiple exchanges.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

Search movies and TV shows, retrieve cast, ratings, streaming availability, and personalized recommendations via the TMDb API.

Use when the user says 'plan a campaign', 'promote this product', 'write the copy for our sale', 'what should we push this month', or 'draft the launch for this collection'. Reads what the store actually sells, drafts the campaign around it, and stages every page and product change for approval.

Build type-safe APIs with tRPC, covering procedures, routers, middleware, React integration, subscriptions, and error handling.

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

Provides Rust code patterns for building blocking HTTP clients with ureq, including request construction, response handling, SSE streaming, and timeouts.

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

Provides a command-line interface to the bat file viewer, including help, run, info, and status commands.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Quick reference for Windows Command Prompt commands, including environment variable editing, remote desktop, and encoding settings.

Use when the user says 'run a sale', 'discount this category', 'set up a coupon', 'reprice these products', 'end the sale', or asks what a discount would cost them. Plans the price change, shows it as a preview before anything moves, writes it with a snapshot, and can put it back.

Runs the dcg operator skill using Codex and the local shell, following the source skill's domain behavior and commands.

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

Installs and configures ktx, the open-source context layer for data agents, including database connections, embeddings, agent integration, and context ingestion.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

Runs the NTM operator skill through Codex, using the local shell and returning concrete evidence of commands run and files touched.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

Manages command-line snippets by saving, searching, and executing complex commands from a local TOML file.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Provides a Codex-native entry point for the rch operator skill, directing the agent to load the source skill and follow its runtime contract.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

Operates the sbh skill through Codex, reading the source skill and prompt profile to run commands and report evidence.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

Provides guidance on using Zsh, including Oh My Zsh plugins, themes, and performance best practices.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.