Scaffolds a Claude Code custom subagent definition — a `.md` file under `.claude/agents/` with a routing-oriented description, an explicit `tools` allowlist sized to the workflow,…
Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.
Build the Observable Framework dashboard for a code-diligence target's warehouse, honoring the privacy gate on the working-pattern card.
Update properties or content across many pages in a Notion database with dry-run and error recovery
Bump a submodule pointer after its PR merges. Verifies the PR is merged, pulls latest main, stages the pointer, commits, and opens a PR in the parent repo.
Model burn rates, runway scenarios, break-even analysis, and cash flow projections for multi-product venture studios
Structure Indonesian SME feasibility assessments across market, technical, financial, legal, and risk aspects with consistent financial figures.
ビジネス・サービスのアイデアを「発散 → 深掘り → 評価」の 3 フェーズで練り上げる汎用スキル（業界・会社に依存しない。特定事業ドメイン前提の類似スキルとは異なり、任意のテーマで使える）。 検討過程は notes ファイルを正本として育て、セッション中断・再開に対応する。…
商业洞察主流程 — 整合专题分析、洞察生成、预警误报处理与分析质量控制。 适用情形：月度/季度业务复盘或专题分析时执行，整合 trend-analysis、 survey-analysis、insight-generation 和 insight-validation， 输出经过验证的商业洞察报告。 核心：数据收集 → 模式识别 → 洞察生成 → 交叉验证…
Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
Exit maintainer dev mode — restore orchestration, remove the dev marker, log the exit.
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.
Lightweight Q&A about the project — answer from context and return, no routing, no state change.
Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.
Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose.
Finish an already-merged branch — classify the leftover artifacts, return to a fast-forwarded default checkout, and delete the merged local branch.
Show the codeArbiter command catalog — the public command list and what each routes to.
Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.
Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized.
Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to $ca-fix, $ca-adr, or a no-action close.
Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized.
Maintainer override — suspend orchestration to edit codeArbiter itself. Env-gated (CODEARBITER_DEV=1), entry/exit logged to overrides.log.
Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only.
Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates.
Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store.
Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.
Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it.
Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.
Open a pull request the only sanctioned way — clear every BLOCK-level review finding, then stage the PR. Never a direct write to the default branch.
Zero-onboarding, read-only dry-run of the reviewer fleet against the current uncommitted diff. Predicts reviewers, runs the state-free secret scan, writes nothing.
SMARTS arbitration — reconcile architectural artifacts against the scaffold and prior decisions; every variance resolved by an explicit, user-attributed choice.
Cut a release the only sanctioned way — SemVer bump from the commit log, a CHANGELOG section, an annotated tag. The only path to a version tag.
Review the current diff with the reviewer fleet, funneled to one triaged verdict.
Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or $ca-feature.
Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.
Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.
Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.
The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark one done.
Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval.
Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.
build123d で 3D プリンタ向けの造形を「書く→診断→視認→調整」で反復する媒介スキル。嵌合較正 fit() でクリアランス/圧入を一点管理し、干渉/クリアランス/肉厚/オーバーハング/ビルドボリュームを自前診断し、シェーディング多視点 PNG で形を視認し、STEP/STL/3MF を出力する。Bambu A1 mini / X2D / H2D…
Generate a compliance report mapping the project's Cadence artifacts to industry standards (NIST SSDF v1.1 or ISO/IEC 25010:2023).
Scaffold the Cadence framework into the current repository. Use when the user runs /cadence-init or asks to set up the Cadence framework, install patterns, bootstrap…
Fill in the Cadence team launch template for a new feature, render the launch prompt, and optionally spawn four coordinated subagents (data engineer, feature engineer, tester,…
Calendario fiscal — genera el calendario de obligaciones tributarias por tipo de entidad y obligaciones configuradas.
Cancel calendar attendance in live Sanka. Use when the user explicitly invokes /sanka:cancel-calendar-attendance.
Generates paste-ready Power Apps Canvas App YAML. Invoke when the user wants to replicate a UI mockup, improve an existing Canvas app screen, or build a new screen from a text…
Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities, planning skill development, performing ontology expansion, or…
资本配置主流程 — 整合投资评估、资本预算、WACC 测算与股东回报管理。 适用情形：年度资本预算编制或重大投资项目评估时执行，整合 investment-evaluation、 wacc-calculation、roic-vs-wacc-comparison 和 scenario-analysis， 输出完整的资本配置决策包。 核心：投资回报测算 →…
Evaluate Indonesian SME investment projects with NPV, IRR, and payback using the deterministic npv and irr engines against a simple WACC.
Redigir o capítulo de Métodos de um projeto de pesquisa científica em português brasileiro. Usar quando o usuário solicitar "escrever métodos", "capítulo de métodos",…
Vangt bugs op met P1-P4 severity classificatie. Parkeert in docs/work/bugs/. P1 waarschuwt voor mogelijke werkonderbreking. P3/P4 parkeert stil.
Registreert technische chores. Bepaalt of een doc nodig is (klein=geen doc, groot=doc). Classificeert type en risico. Parkeert grote chores in docs/work/chores/.
Capture user intent as structured work requests without executing. Use when user describes work to be done. Separates intent from execution. Writes to do-work/requests/ queue.
AI job search command center -- evaluate offers, generate CVs, scan portals, track applications — from pushkarawat680/qwen-skills
Write actuals into an existing Excel budget workbook from Carta MCP — add/interleave Budget/Actual/Variance columns, a tag-view tab, or a vendor-view tab.
프로젝트를 전수 분석(스택+코드베이스)해 ① CLAUDE.md·AGENTS.md 설정 정합성을 검증·제안하고 ② 스택에 필요한데 없는 요소(하네스 규칙·외부 개발도구·설정 스캐폴딩)를 보강 제안하며 ③ 불필요한 구성을 prune한다.
Fallbearbeitung im deutschen Gutachtenstil (Obersatz – Definition – Subsumtion – Ergebnis). Lade diesen Skill bei Anfragen wie „bearbeite diesen Fall", „schreibe ein Guta — from…
Анализ решений арбитражных судов РФ (АС субъектов, Арбитражные апелляционные суды, АС округов, СКЭС ВС РФ, Президиум ВС РФ) по корпоративным вопросам.
现金流预测 — 滚动预测未来 1-3 个月现金流，识别资金缺口和融资需求。 适用情形：每月固定时间（如月末）执行，从 [ERP]/[OA]/[BK] 获取数据， 预测未来 1-3 个月资金流入和流出，识别资金缺口，输出融资计划建议。 核心：滚动预测模型 + 乐观/基准/悲观三情景 + 缺口时间点定位。