dr-explore が作った run（evidence.jsonl / sources）を検証・統合して、 レポート（report.md）と実装計画（implementation_plan.md）を作る。
Draft an offer letter with comp details and terms. Use when a candidate is ready for an offer, assembling a total comp package (base, equity, signing bonus), writing the offer…
Draft a professional customer-facing response tailored to the situation and relationship. Use when answering a product question, responding to an escalation or outage, delivering…
Проверка черновика в .claude/drafts/ на соответствие стандарту — frontmatter, структура, именование файла. Используй после создания или изменения черновика, перед коммитом.
Nightly memory consolidation — prunes stale entries, merges duplicates, resolves contradictions, rebuilds MEMORY.md index.
Управление вайб-код проектами. Протокол .drift/ для трекинга статуса, прогресса, заметок и целей по всем проектам.
Import one or more Google Drive folders as private repos into the local Forgejo dev-hub. Wraps the kei-drive-import bash wizard.
Internal development tool that tests whether skill descriptions trigger correctly for different user inputs.
This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple programs", "use dspy.MultiChainComparison", mentions "ensemble…
This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training…
This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_ma — from…
This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_ma — from…
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inf — from…
This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inf — from…
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mention — from…
This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mention — from…
This skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy to improve Haystack pipeline", mentions "Haystack…
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimi — from…
This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimi — from…
This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select best output", "use dspy.BestOfN", mentions "output…
This skill should be used when the user asks to "build a RAG pipeline", "create retrieval augmented generation", "use ColBERTv2 in DSPy", "set up a retriever in DSPy", mentions…
This skill should be used when the user asks to "create a DSPy signature", "define inputs and outputs", "design a signature", "use InputField or OutputField", "add type hints to…
Review a GitHub PR with two independent CLI reviewers (Claude Code and Codex) in parallel, then reconcile their findings into one evidence-backed consensus set.
Codebase-orientation session with the rubber duck — generate or refresh .claude/orientation.md with interactive exercises.
并购交易法律尽职调查 — 对目标公司进行全面法律调查，涵盖主体资格、 股权结构、重大资产、债权债务、劳动合规、诉讼仲裁等。 适用情形：用户说"帮我做尽职调查"、"核查目标公司法律风险"、 "尽调报告怎么写"、"法律尽调清单"。
Find and merge duplicate Linear issues — group reports of the same underlying bug, pick the survivor, and move the evidence across.
Уровень душноты (0-10) — насколько критично Claude челленджит твои решения. 0 = 'бро, делаем', 10 = полный душнила, ставит под сомнение всё. Алиас для /rigor на русском.
Calculate customs duties, taxes, MPF, HMF, and landed cost for imports using AskRosetta. Use when a user needs duty rates, tariff calculations, or total landed cost.
Auto-detect project type, structure, build commands, and AEM values. Updates .ai/config.yaml with project profile and substitutes real values into installed .claude/rules/.
Full pipeline from ADO story to executed code. Runs requirements, planning, execution, build, review, commit, and PR in sequence with optional human review checkpoints.
Implement code from an RE spec as the Dev Agent — read requirements, implement changes, run self-check (build/test/lint), fix failures, and commit.
Run the full bug fix workflow — triage, verify, and fix — all in one command. Fetches the bug from ADO, reproduces it in browser, generates and executes a fix, and creates a PR.
Generate a lightweight fix plan, execute it, run tests, and create a PR for a bug. Reads triage.md and verification.md, generates implement.md (2-5 steps), delegates execution to…
Run any question, decision, or artifact through a council of 3 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict.
Resolve which repos a work item touches, as a 3-tier cascade (explicit directive → simple-block routing → cross-repo table → LLM).
Generate technical documentation retroactively for completed stories — fetches ADO story, finds linked PRs, searches codebase, and produces wiki-ready docs without needing spec…
Check health of all dx workflow files — config, rules, scripts, seed data, MCP, settings. Detects installed plugins and checks each.
Validate Definition of Ready — fetch wiki checklist, evaluate story, post ADO comment. Use standalone at sprint start, in batch, or as part of /dx-req.
Eject all plugin assets into the consumer repo — copies skills, agents, rules, templates, shared files, hooks, and MCP config so the project works without plugins installed.
Extract design context, tokens, and screenshots from a Figma URL. Saves figma-extract.md and reference screenshots. Use after requirements phase when a Figma URL is in the story.
View and edit hub configuration — add repos, adjust terminal delay. Use to manage hub settings. Trigger on "hub config", "add repo to hub", "terminal delay".
Dispatch a ticket to multiple repos via VS Code terminals. Reads ticket, detects involved repos, opens independent Claude sessions in each repo.
Initialize a hub directory for multi-repo orchestration. Discovers sibling repos, merges configs, validates CLI compatibility. Use when setting up hub mode for the first time.
Show status of hub dispatches — which repos are running, done, blocked, or failed. Use to check multi-repo progress. Trigger on "hub status", "dispatch status", "what's running".
Set up the dx workflow for a new project. Detects your environment, asks a few questions, and generates .ai/config.yaml plus supporting files.
Scan completed tickets for recurring patterns and promote to cross-ticket knowledge. Run periodically or after completing several tickets.
Cross-check the implementation plan against requirements. Verifies every requirement has a step, no unrequested features snuck in, and dependencies flow correctly.
Create a pull request after all plan steps are complete. Verifies all steps are done, generates PR description from share-plan.md, pushes branch, and creates PR via ADO MCP tools.
Commit changes and optionally create an ADO pull request. Handles staging, commit messages with ADO work item IDs, rebasing onto the base branch, and PR creation via ADO MCP…
Review a PR — analyze code, present findings, optionally post comments and patches to ADO. Also supports standalone posting of saved findings (for automation pipelines).
Generate categorized reports for multiple PR reviews — lists reviewed PRs, generates a report for each, and posts all to ADO Wiki or Confluence.
Check Definition of Done compliance and auto-fix gaps — reviews PR, tasks, docs. Posts summary to ADO.
Deep project scan — discover conventions from actual code, customize rule files with real values, and generate seed data. Interactive. Run after /dx-init + /dx-adapt + /aem-init.
Apply a small AEM change (a11y label, color, spacing, copy, css-class, icon, focus trap, or other small behavior tweak) by splitting work into authoring (JCR writes) and code…
Code simplification — reduce complexity while maintaining exact behavioral equivalence. Applies Chesterton's Fence (understand before changing) and Rule of 500 (replace when…
Execute the next pending step — implement code, run tests, review against plan, and commit. Reads implement.md, finds the first pending step, implements it, tests, reviews,…
Autonomous execution loop — runs each plan step (implement + test + review + commit internally), with step-fix for failures.
Build and deploy to local dev environment, fix errors iteratively until the build passes. Use after code changes to verify everything compiles and deploys correctly.
Diagnose and fix a blocked step — compilation error, test failure, or review rejection. Tries direct fix first; if that fails, creates corrective steps in implement.md (heal).
Sync plugin updates to consumer repos — runs sync-consumers.sh with selected repos and options. Use when you say "sync plugins", "update consumers", "push to all repos".