Use when the user wants to set up config sync for the first time, connect to GitHub, or re-initialize the backup repo.
Import or update a skill from another project into a subdirectory-package skills repository (the current one or an auto-detected sibling).
Sync Claude Code skills to GitHub repository. Use when you want to backup skills, update the repo after creating/modifying a skill, or share skills.
코드 변경 후 사용자 문서(docs/guides, docs/api, docs/index.md, docs/glossary.md 등)를 코드 기반으로 동기화합니다.
Multi-agent debate system supporting 6 AI providers (Gemini, OpenAI, DeepSeek, Groq, Grok, Mistral)
Read a merged-PR markdown export and synthesize a typed workflow SOP into Meta/Workflows/. Trigger /synth-pr-to-sop
.
Read a resolved Slack thread markdown export and synthesize a typed memory entry (decision, exception, or workflow) into Meta/.
Deduplicate and reconcile multiple completed review reports into one prioritised revision plan with conflicts and dependencies made explicit.
Synthesize customer feedback into thematic clusters when the user asks to analyze feedback, review VoC data, or understand customer sentiment
Deep cross-domain synthesis engine for the vault. Triggers on "synthesize X", "what do I know about X", "connect ideas about X", "cross-domain analysis of X", "map everything in…
Help users get started with the Synthetix perps exchange — install the SDK, connect to the API, fetch market data, and place their first trade.
Walk through every cost and revenue assumption in your business model using structured checklists. Surfaces hidden risks, flags unknowns, and builds a complete assumptions map.
Identify and break the biggest bottleneck in your startup using a diagnostic loop based on Goldratt's Theory of Constraints.
Self-assessment across four dimensions — Skills, Experience, Leadership, Doing Hard Things — on a 2x2 of Capability vs. Willingness.
Break a large goal down into a connected hierarchy from decade-level vision to today's next action. Systematically chunks across seven time horizons so every daily effort connects…
Work through a hard decision by naming fears, writing mitigations, and rating actual severity. Adapted from Tim Ferriss's fear-setting framework with a numerical rating system by…
Walk through Chris Salter's Five-Finger Pitch framework -- a five-minute verbal pitch where each finger represents one minute of content.
Honest behavioral assessment to help founders identify which of three types they are currently operating as -- delusional, pretender, or real deal -- based on what they actually…
Define three scope tiers for any project -- LOW (minimum proof of concept), HIGH (dream version), and MEDIUM (best balance of value and cost) -- to make smarter build decisions…
Walk backward from a revenue target to the daily growth you actually need. Five-minute back-of-napkin model that exposes whether your plan adds up -- or whether you are off by an…
Collaborative exercise to create a crystal-clear definition of "done" before any work begins. You describe the vision, the AI asks clarifying questions until both sides see the…
Rank a list of ideas, initiatives, features, or life decisions by scoring 2-4 dimensions on a coarse 1-5 scale. The simplest matrix that still beats gut-feel ordering.
Reclaim 5-15 hours per week by auditing your time and applying the 3 D's — Delete, Delegate, Delay — to every low-value activity.
Audit your product's path from first use to first delight ("wow moment"), then systematically optimize time, friction, and drop-off points.
Performs a meta-level review of how well an implementation followed its plan, classifying divergences and recommending AI-Layer improvements.
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation.
Survey a codebase and produce a reverse-spec backlog in `specs/systems.yml`. Use when you want a queue of stable system domains to reverse-engineer over time.
Manage ClickUp tasks, comments, time tracking, docs, and chat via the ClickUp MCP server. Use for 'create clickup task', 'update clickup', 'find clickup tasks', 'log time on…
Maintain TheOneKit repos as a kit maintainer. Use for releasing kits, scaffolding new kits, cross-kit validation, schema migration, and E2E test runs.
Manage optional skill modules for modular kits. Use for 'install module X', 'remove module Y', 'list available modules', 'apply a preset', 'update modules', or auditing module…
Front-loaded pre-spec thinking — walk values, trade-offs, halt conditions and kill conditions across a card or cluster to produce aligned specs
Use when the user asks to "list my claude sessions", "which windows are waiting", "/ar:tabs". Discovers Claude sessions across tmux windows and reports which need attention.
Use when the user asks to "continue every session", "send this to all windows", "/ar:tabw". Acts on Claude sessions across tmux windows; destructive to in-flight work, so it…
Conductor for the issue-tackle workflow. Triage a GitHub issue or PR, scan for open tasks, propose a resolution plan, create an isolated worktree, guide execution through the…
Take over a stale or abandoned PR. Checks out the work, merges main, deep-reviews the code, addresses all review comments, then re-creates a clean PR crediting the original author.
Взять задачу в работу и запустить полный цикл разработки. Определяет размер (S/M/L), запускает агентов по пайплайну, проверяет quality gates.
Deep talisman.yml configuration expertise — init, audit, update, guide, status, split, merge. Scaffolds project-specific talisman.yml from canonical template, detects missing…
Create and audit presentations (Beamer or Quarto RevealJS). Combines talk creation, visual audit, and compilation. Replaces /create-talk, /visual-audit, /compile-latex (for talks).
Channel Tom di Mino's daimonic voice for writing. Invoke when Tom asks to write prose, essays, tweets, poetry, or technical docs in his own voice—possessed by the daimon, not…
Use when the user pastes a stack trace, traceback, panic, crash log, or error message WITH a file:line reference and wants to know the root cause.
Creates a Ready-status backlog task from a pre-approved template, bypassing the full review cycle. Performs a single LLM freshness check against recent git changes; if FR — from…
**WORKFLOW SKILL** — Understand before implementing. USE FOR: any task where the agent might rush to code — forces understanding WHY/WHAT FOR/FOR WHOM before defining a solution,…
Manage task persistence across /clear sessions — disable/enable auto-restore, list prior sessions, inspect tasks from a specific session
Reprend une séquence de tâches multi-étapes après reset de contexte. Lit le fichier de progression du projet, identifie l'étape suivante, relance la commande correspondante.
Use when orchestrating parallel Claude Code instances across tmux panes with git worktree isolation — managing multiple concurrent development tasks visually
DEPRECATED — use `/taw` instead. This shim forwards to `/taw` with the BUILD branch (add-feature path). Kept for backward compatibility with earlier taw-kit versions.
税务申报综合执行 — 整合增值税 + 所得税 + 附加税 + 个税代扣代缴的月度申报全流程。 适用情形：每月固定时间（如次月 1-10 日）执行，完成所有须申报税种的 数据准备、核对、异常处理和申报确认，是税务申报的主入口 Skill。 核心：申报日历驱动的全税种覆盖 + 优先级排序 + 升级判断。
税务风险自检 — 核查金税系统预警 + 发票风险 + 申报异常，输出风险清单和整改建议。 适用情形：定期（每月/每季度）执行，从金税系统获取风险预警， 结合发票数据和申报数据，识别须关注的税务风险点，制定整改计划。 核心：系统预警核实 + 根因分析 + 分级整改。
个税扣缴审核 — 核查 [PAYROLL] 个税计算准确性，核查专项附加扣除、计税收入。 适用情形：月度个税申报时执行，从 [PAYROLL] 获取扣税数据， 核查计税收入、专项附加扣除、税率适用，输出申报数据审核报告。 核心：计税收入核查 + 扣除项核查 + 税率核查 + 申报准确性。
TCM constitution assessment and wellness management including body constitution identification, dietary recommendations, exercise suggestions, acupoint therapy, and herbal…
Use when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.
Decide the approach before any code is written. The design-author drafts the ~200-line design document, resolving its own open questions autonomously as recorded assumptions, then…
Import issues from GitHub, Jira, or Linear into the local backlog. Smart-splits larger issues into multiple frontend/dev todos based on body analysis.
Start een Agent Team voor jeugdontwikkelingsbeleid, scouting-rapportage en vaardigheidsraamwerk. Gebruik bij vragen over vaardigheden per leeftijd, beoordelingscriteria,…
Kwaliteitsteam voor de team-indeling app — code review, tests, build validatie en tech debt. Gebruik na feature development, als health check, of voor proactieve codebase sweep.
Outsource a backlog item or defined feature to a teammate by creating an issue in GitHub, Jira, or Linear.
Decompose a feature description, ticket, or issue link into the QRSPI Question artifacts (task.md, questions.md).
Break the reviewed design into vertical slices with verification checkpoints. Runs autonomously and advances to PLAN — no approval gate.
Long-form guided demo of the all-maw-verb team bootstrap pattern — walks step-by-step from blank tmux session → maw tile N → TeamCreate → maw run with team-flagged claude.exe →…
One-shot bootstrap of N maw-tile-spawned blank panes into a TeamCreate team — each pane cd's into a target oracle/repo and boots claude.exe with TeamCreate flags via `maw run`,…