Diagram maker for the Karvey method. Natural language in, diagram out — mermaid source + editable .excalidraw + rendered SVG/PNG. Offline-friendly.
Documentation engineer for the Karvey method. Generates Diataxis docs (tutorial/how-to/reference/explanation) from code, updates stale project docs to match what shipped, and…
Safety guardrails for the Karvey method. Installs/disables the opt-in enforcement hooks (git-flow + plan-gate), grants temporary override, and can edit-lock work to a single…
Execute implementation tasks sequentially with ClickUp time tracking or PLAN.md updates. Read → execute → test → validate cycle per task.
Generate EARS-format requirements and spec-delta for a Karvey spec. Creates Features in ClickUp or updates PLAN.md. Use after karvey-init.
Independent cross-model code review for the Karvey method. Get an adversarial second opinion from a different AI model (e.g. Claude vs GPT/Codex/Gemini).
Orchestrate an improvement cycle: diagnose, select methodology, execute, record, persist. The meta-pattern that connects all skills into a coherent workflow.
Use to ship a batch of katas selected by ids, priority, parent, or label. Orders the wave, runs scope review by default, then invokes kata-ship per kata.
Use to verify a Kata Flight setup. Read-only health check for the .kata-flight seam, marker vars, engine layout, context root, optional RDR binding, and skill links.
Use to bind a consumer repo to Kata Flight: create or refresh .kata-flight seam, env/resources files, optional workspace marker, and optional RDR binding.
Use for a read-only kata flow dashboard or stuck-state report. Shows lifecycle depth, inbox, batch depth, and illegal/stale states without mutating git or kata.
Use to resolve, fix, or work on one or more kata issues in a consumer repo. Reads kata state, works in isolation, commits a fix, and closes/comments as appropriate.
Use to scope-review, consolidate, dedupe, or route katas before shipping. Mutates only the kata tracker; never code.
Use to ship one or more kata issues end to end: resolve in a worktree, rebase, run roborev refine, fast-forward merge, tear down, and close.
Audit / curate KB-vault hygiene — surfaces mechanical drift (broken [[wikilinks]], dangling §-pointers, status-enum violations, status-drift, index-row bloat) the librarian's…
Run kube-coder's full CI suite locally before pushing — helm lint + unit tests, server.py tests, dashboard + controller SPA builds + vitest, and shell syntax checks.
Keil MDK 工程构建工具，用于扫描 .uvprojx/.uvmpw 工程、枚举 Target、执行 build/rebuild/clean 并解析构建日志，返回可供 jlink/openocd 复用的产物路径。 flash 子命令仅作为兼容入口保留。当用户提到 Keil、MDK、uVision、UV4、 Target…
Author a keiro service as a typed `.keiro` specification and drive the keiro-dsl toolchain end to end: write the spec, `check` it, `scaffold` the deterministic layer plus explicit…
Run pronto's kernel presence checks — non-delegable filesystem checks (AGENTS.md, project/, .pronto/, README, LICENSE, .gitignore, .claude/)
Easter-egg alias for /catchup. Same return-from-absence briefing, squeezier name. Use exactly like /catchup — all flags pass through unchanged.
Build a deduplicated, intent-classified, volume/difficulty-annotated master keyword list from seed terms — output CSV feeds straight into keyword-clustering-and-mapping.
Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools.
Manufacturing and fabrication workflow for KiCAD projects via MCP tools. Triggers on: "send to fab", "order boards", "gerbers", "JLCPCB", "manufacturing", "export for production",…
Workflow skill for KiCAD PCB layout and routing via MCP tools. Triggers on: "layout the board", "route traces", "PCB", "place footprints", "copper pour", "board outline",…
Design review and validation workflow for KiCAD projects via MCP tools. Triggers on: "review my design", "check for errors", "audit", "DRC", "ERC", "find problems", "design…
Workflow skill for KiCAD schematic design via MCP tools. Triggers on: "design a circuit", "add a component", "wire up", "connect pins", "build schematic", "place resistor", "place…
Host-only — remove a paired peer. Drops their SSH pubkey from authorized_keys and deletes their peer record. IRC /kick analog. Joiners cannot kick.
Generate a complete first-draft site from a single prompt. Usage: /kickstart [what you're building]
Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces…
Kimball dimensional modeling methodology with semantic layer declarations, 1-table-per-file DDL, load types, pipeline metadata, and version-controlled business logic.
Implement approved tasks using TDD with an independent reviewer gate per task. Executes directly in the main context (default) or via native subagent dispatch for parallelizable…
Generate implementation tasks from requirements and design. Use when creating actionable task lists.
Interactive technical design quality review and validation. Use when reviewing design before implementation.
Analyze implementation gap between requirements and existing codebase. Use when planning integration with existing systems.
Evidence trail management. Start sessions, record decisions during work, close sessions, index decisions, validate trail integrity.
Install generated Cartographing Kittens agents, skills, and prompt commands into a selected Codex configuration path.
Full autonomous engineering workflow — plan, work, review with Cartographing Kittens-first inline-first orchestration.
Structured code review using Cartographing Kittens-powered reviewer agent swarms. Use when the user says "review this", "check my code", "code review", or before creating a PR.
Execute implementation plans with Cartographing Kittens-first worker swarms. Use when the user says "build this", "implement", "execute the plan", "start working", or after…
SOP guidelines and claim submission templates for lost or damaged courier packages (J&T, JNE, SiCepat, Shopee Xpress).
Retrieve claudit knowledge cache domains (ecosystem, core-config, optimization). Checks freshness and auto-refreshes stale domains.
This skill should be used when the user asks 'what do I know about [topic]',
Ajout rapide de notes dans la documentation personnelle (tips, todo, veille, changelog)
This skill should be used when the user asks to 'prime context', 'load project knowledge', 'what do we know about this project', 'knowledge brief', 'project context', 'what…
Looks up and tracks known Claude product issues — searches known GitHub bugs, checks service health and model quality, and maintains a persistent registry of tracked issues.
Generate images and videos using Krea AI. Use when user asks to create, generate, or make images, pictures, videos, or visual content with AI.
Pesquisa etimologia de um nome kung fu chinês (nome Moy Yat / Ving Tsun) e cria nota de discípulo no Scholion com decomposição de ideogramas e etimologia das traduções em…
Decide between KV Watch and JetStream Stream for a new communication path. Use when designing inter-component communication, adding new message flows, or choosing storage…
Brain dump and compile knowledge before structuring a plan. Use when starting any non-trivial knowledge work — after a meeting, when tackling a new problem, or when you need to…
Multi-reviewer quality check for knowledge work. Runs strategic alignment and data accuracy reviewers on plans, briefs, and strategy docs.
Execute a knowledge work plan. Break it into tasks, do the work, and track what happened. Use after planning to actually produce the deliverables.
操作 KWeaver 知识网络与 Decision Agent — 构建知识网络、查询 Schema/实例、 语义搜索、执行 Action、Agent CRUD 与对话、Trace 数据分析。 操作 Skill 管理模块 — 注册 Skill、市场查找、渐进式读取、下载与安装。 操作 Vega 可观测平台 — 查询…
Stage and commit changes with conventional commit format. Smart analysis groups changes, proposes splits, and writes structured commit descriptions.
Create a draft pull request targeting develop. Auto-generates PR body from design files, GitHub issues, and/or commit history. Use when opening a PR.
Execute the label→action mapping when a GitHub trigger label dispatches the CI harness: enrich an issue in place, or implement it end-to-end (branch → PR).
Добавление, удаление или переименование меток GitHub с синхронизацией labels.yml. Используй при изменении набора меток проекта, добавлении новой категории или исправлении опечатки…
Проверка labels.yml и меток на GitHub — синхронизация с репозиторием, валидация Issue/PR. Используй для аудита меток, после изменения labels.yml или при проверке корректности…
Calculate the complete landed cost of importing a product — from factory to warehouse door. Covers duty, taxes, fees, freight, insurance, brokerage, and entry type selection.
Use when the user asks to "pre-launch check the landing page", "run a Quality-Score preflight", or "verify ad-to-page message match before launch"; produces an ad↔page continuity…
Audits any landing or service page across 48 checks in 10 categories for LLM/AI discoverability, GEO readiness, content clarity, schema markup, internal linking, freshness…