Explore

Trigger language server code generation — implement interface stubs, generate test skeletons, add missing methods, generate mock types. Uses suggest_fixes to surface generator options and execute_command to run them.

Format a file or selection using the language server's formatter. Use before committing to apply consistent style, or after generating code to clean up indentation and spacing. Supports full-file and range-based formatting.

Apply available quick-fix code actions for all current diagnostics in a file, one at a time with re-collection between each fix. Use to bulk-resolve errors and warnings the language server can fix automatically.

Extract a selected code block into a named function. Primary path uses the language server's extract-function code action; falls back to manual extraction when no code action is available. Validates captured variables, scope shadowing, and compilation after extraction.

"Tell me about this symbol": hover + implementations + call hierarchy + references in one pass — for navigating unfamiliar code.

Edit a named symbol without knowing its file or position. Use when you want to change a function, type, or variable by name and don't have exact coordinates. Resolves the symbol to its definition, retrieves its full range, and applies the edit.

Safe workflow for editing exported symbols or public APIs. Use when changing a function signature, modifying a public type, or altering any symbol used outside its own package — finds all callers first so nothing breaks silently.

Three-tier documentation lookup for any symbol — hover → offline toolchain doc → source definition. Use when hover text is absent, insufficient, or the symbol is in an unindexed dependency.

Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.

Cross-repository analysis — find all callers of a library symbol in one or more consumer repos. Use when refactoring a shared library and need to understand how consumers use it.

Concurrency safety audit for a type or file. Maps all fields, traces which are accessed from concurrent contexts (goroutines, threads, async tasks), and flags fields that lack synchronization. Produces a field-level safety report. Language-agnostic across 4 concurrency families.

Generate a structural architecture overview of a codebase: languages, package map, entry points, dependency graph, and hotspots. One call for the big picture.

Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when asked to draw, diagram, chart, or visualize a system, process, or dataset.

Guide for structuring graph input (nodes and edges) for the Excalidraw Architect MCP tool to produce clean, readable diagrams. Use when generating architecture diagrams, flow diagrams, or any visual diagram via create_diagram or mermaid_to_excalidraw.

Guide for reading a codebase and building a high-quality, persistent architecture knowledge graph via the Excalidraw Architect MCP kg_* tools. Use when creating or updating the knowledge graph (.claude/architecture.md), mapping services and their dependencies, or analyzing one or more repos to capture how services communicate.

Formats meeting notes into a consistent outline

Speeds up reviews by fetching the latest ruleset

Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.

Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools. Use when creating, editing, restructuring, or diagramming Outline documents — covers Outline markdown quirks (mermaidjs code fences), document and collection structure, string-match editing, staged rewrites, batch operations, and search status filters.

MemoryWhale debugging; compiler failures; terminal diagnostics.

Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and it's worth remembering. Works across machines and past sessions.

Ask clarifying questions to users via interactive TUI. Use when you need user input on preferences, implementation choices, or ambiguous instructions.

Retrieve a current stock quote and market snapshot with price, range, volume, and moving-average context. Use when the user asks for the latest stock price, quote, intraday range, or a quick market snapshot.

Analyze 10-K annual filings to extract business model, financial priorities, risk factors, segments, and notable changes. Use when the user asks about 10-Ks, annual filings, SEC risk factors, or filing-based due diligence.

Generate Kalshi prediction market research reports or fetch structured event history. Use when the user mentions Kalshi, prediction markets, market probability, expected return, or event history.

Validate Octagon plugin configuration and run a lightweight smoke test across the main Octagon MCP workflows. Use when checking whether the plugin is configured correctly, debugging auth, or verifying tool availability.

Route broad company, sector, valuation, filings, transcript, and market data questions into the right Octagon workflow. Use when the user wants full-scope investment research or when multiple Octagon skills may be needed.

Analyze earnings call transcripts for guidance, management commentary, analyst concerns, and strategic signals. Use when the user asks about earnings calls, transcript takeaways, management tone, or future guidance.

Retrieve analyst financial estimates including revenue and EPS projections with ranges and coverage. Use when analyzing forward expectations, consensus assumptions, or valuation inputs for a public company.

Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.

Use this skill when the operator needs Yandex Market data — price checks across many sellers, product ratings with their star breakdown, or buyer reviews. Trigger on Russian queries like "цена на Яндекс Маркете", "отзывы на маркете", "найди на яндекс маркете", "сравни предложения продавцов", or English equivalents. Skip for Wildberries/Ozon-specific tasks.

Use this skill when the operator needs Wildberries data — product price/availability checks, review pool analysis, seller identity and tax details, catalog category browsing, finding root_id (imt_id) for product variants, or comparing SKUs. Trigger on Russian queries like "цена на WB", "отзывы на вб", "найди на вайлдберриз", "кто продавец", "какие категории", or English equivalents. Skip for non-WB tasks.

Use this skill when the operator needs Taobao marketplace data — search Chinese listings or read an item card. Trigger on Chinese or English queries like "taobao", "淘宝", "найди на таобао", "цена taobao". Always needs the operator's Chrome over CDP (signed mtop API). Skip for non-Taobao tasks.

Use this skill when the operator needs Ozon marketplace data — product details, search, prices, ratings, or reviews. Trigger on Russian queries like "найди на озоне", "цена ozon", "отзывы на озоне", or English mentions of Ozon. Tier 1 (TLS impersonation) handles most queries with no browser; Chrome CDP is only the tier-2 fallback when Cloudflare challenges. Skip for non-Ozon tasks.

Use this skill for MPStats sales/stock analytics on a specific Ozon or Wildberries item — per-day sales, current price and stock, FBS/FBO warehouse split, seller/brand identity, and a rolling orders-per-day average. Trigger on "продажи товара на озон", "аналитика ozon sku", "mpstats по артикулу", "продажи за 30 дней", or English equivalents. Requires a paid MPStats account (MPSTATS_MP_AUTH env). Skip raw catalog price checks — use wb_/ozon_ connectors (no account needed).

Use this skill when the operator needs Megamarket data — search the catalog or read a product card. Trigger on "мегамаркет", "megamarket", "цена мегамаркет". Always needs the operator's Chrome over CDP (ServicePipe IP block). Skip for non-Megamarket tasks.

Use this skill when the operator wants the full marketplace mount, routing metadata, or client setup. Trigger on "один MCP", "все источники", "marketplace_sources", "настроить marketplace", or "full marketplace". Route price questions such as "где дешевле" and "compare prices" to compare-prices; skip single-source tasks.

Use this skill when the operator needs Lamoda fashion data — search or a product card with sizes. Trigger on "ламода", "lamoda", "кроссовки lamoda". Cards try anonymous GraphQL first, then the operator's Chrome when it is refused; search needs Chrome over CDP. Skip for non-Lamoda tasks.

Use this skill when the operator needs DNS-Shop electronics data — search or a product card. Trigger on "днс", "dns-shop", "dns", "ноутбук днс". Always needs the operator's Chrome over CDP (Qrator proof-of-work). Skip for non-DNS tasks.

Use this skill when the operator needs Detsky Mir data — prices and availability for kids' and baby goods, toys, strollers, nappies, kids' clothing. Trigger on Russian queries like "цена в детском мире", "детский мир наличие", "сколько стоит коляска", or English equivalents. Skip for general marketplace tasks; note that Detsky Mir has NO text search, so discovery goes through categories.

Use this skill when the operator asks where something is cheapest across marketplaces. Fans out to ten searchable sources — Wildberries, Ozon, Yandex Market, Avito, Taobao, Megamarket, Lamoda, DNS, Citilink and AliExpress (Detsky Mir is excluded — no text search; Taobao is ranked in yuan, never against rubles). Trigger on "где дешевле", "сравни цены", "сколько стоит X на маркетплейсах", "найди самую низкую цену", or English equivalents. Skip single-marketplace questions — use the per-marketplace skills.

Use this skill when the operator needs Citilink electronics data — search or a product card. Trigger on "ситилинк", "citilink", "ситилинк цена". Always needs the operator's Chrome over CDP (Qrator rate block + gRPC-web). Skip for non-Citilink tasks.

Use this skill when the operator needs Russian real-estate data from Cian (cian.ru) — flats, rooms, houses or commercial property for sale, long-term rent or daily rent, or one offer's card with price history and publisher. Trigger on Russian queries like "найди на циане", "квартира на циан", "снять квартиру", "снять посуточно", "квартира на сутки", "купить однушку в Москве", "сколько стоит квартира на", "объявление циан", or English mentions of Cian. Needs the operator's Chrome over CDP (Cian's WAF blocks plain HTTP by IP). Skip for goods, marketplaces, and non-Cian real estate.

Use this skill when the operator needs Avito classifieds data — search listings, item cards, or seller reputation. Trigger on Russian queries like "найди на авито", "цена avito", "объявления авито", "продавец на авито", or English mentions of Avito. Needs the operator's Chrome over CDP from a datacenter IP (IP firewall). Skip for non-Avito tasks.

볼트 점검. 지금 어긋난 곳과 끊긴 곳을 찾아 사람 말로 정리하고, 각각을 고치는 정확한 호출을 함께 낸다. 아무것도 고치지 않는다. "어디가 문제야" · "점검해줘" · "성한지 봐줘" 일 때 쓴다.

다음 한 걸음. 이 볼트에 무엇을 더하면 값이 가장 큰지 후보를 근거와 함께 뽑아 보여 준다. 사람이 고르기 전에는 한 글자도 쓰지 않는다. "다음에 뭐 채워" · "빈 곳 찾아줘" · "더 넣을 거 있어" 일 때 쓴다.

글에서 개념 뽑기. 회의록·기획서·PR 설명에서 개념 후보를 뽑되 중복부터 먼저 확인한다. 사람이 고르기 전에는 쓰지 않는다. "이 글에서 뽑아줘" · "이 문서 반영해줘" 일 때 쓴다.

Periodic security sweep of Atlas in four areas (MCP and CLI, the Tauri desktop shell, the web renderer and connectors, the supply chain and CI) that follows untrusted input to what it can reach, proves each reach with a planted input, and turns every confirmed finding into a fix slice with a regression test. Not for a single diff, which takes the reviewer's security lens.

Sync an existing Atlas ontology after feature, refactor, rename, or cleanup work that may change modeled meaning. Inspect the delta and apply only confirmed, authorized updates; skip prose, style-only, lint, and fixture changes.

Run an Atlas ontology quality field trial when requested or when construction rules or MCP behavior can change vault contents. Skip UI and wording-only changes that preserve evidence, approval, and write contracts.

Extract reviewable Atlas ontology candidates when the user asks to extract from prose, or to absorb a wiki page read through their own registered wiki MCP. Pasted text alone does not request vault changes.

Verify a new or changed automated gate with deliberate failing and passing cases, a nonempty inventory, and CI wiring.

Select and run pixiv-cli regression, TDD, document, SDK, CLI/MCP, and build checks. Use when changing behavior, reproducing a bug, choosing test scope, or reporting readiness. Separates offline fixtures, native evidence, and explicitly authorized live API tests.

Review pixiv-cli working changes, commits, or pull requests for requested behavior, Go design, SDK/CLI/MCP contracts, security, native boundaries, and verification gaps. Use for independent review or pre-delivery self-review; review-only unless edits are authorized.

Prepare pixiv-cli bilingual versioned release notes, audit source coverage, coordinate an authorized version release, or recover its independent publishers. Use for release preparation and historical Release synchronization, not routine feature PR metadata.

Prepare, update, or verify a pixiv-cli pull request using its current template, trusted verification policy, reviewed diff, and head-specific check results. Use for contributor handoff or PR readiness; merging, live /test execution, and releases are separate actions.

Change or validate pixiv-cli Rust ugoira, cgo/FFI, committed static libraries, vendored dependencies, Linux ABI, and native runner evidence. Use when native sources, library hashes, target toolchains, or encoder behavior change; not for routine Go-only or documentation edits.

Add, change, or review a pixiv-cli Pixiv or FANBOX MCP tool, including schema, SDK routing, structured output, errors, and stdio behavior. Use for MCP tool implementation or compatibility work, not routine installed-CLI operation.

Edit pixiv-cli documentation, AGENTS.md, client bridges, repository maintenance skills, or the distributed product skill. Use when commands, APIs, configuration, architecture, testing, or contributor workflows change and their documentation must stay accurate and portable.