Writing & Editing

Use when reviewing, writing or sizing a Thanos deployment (Helm values, manifests, component flags, alert rules, cache config) or diagnosing Thanos read path saturation - store gateway gate pinned, slow global queries, first query after idle endless, Receive OOM, compactor alerts that never or always fire, cache sizing for Redis, Memcached or Dragonfly.

>- Run the Mampu AI work loop on any work-shaped request — a bug to fix, a feature to build, a doc to write, a client ask to handle, an investigation, a PR to ship, a deploy. Finds or creates the team task, reads the matching internal records and help pages, opens the reply with the four-line status block, and closes the task out with a debrief. Not for a plain question or a read-only look.

>- Generates a UNIT TEST suite for embedded firmware .c/.h files, following Maurício Aniche's specification-based testing (partitions → boundaries → cases → coverage). Detects the environment: Zephyr uses twister + ztest + FFF on native_sim; ESP-IDF uses native Unity in a host build + gcovr; anything else follows the project's existing test framework (Unity, CMock, Ceedling, GoogleTest…) or stops and asks if there is none. ALWAYS use it when the user asks to generate/write/create unit tests for .c/.h modules — e.g. "write unit tests for motor_ctrl.c", "create unit tests for the uart_driver", "cover these .c/.h files with tests", "test this function with partitions/boundaries", "95% coverage on this module", or in Portuguese "gera os testes unitários de motor_ctrl.c", "cria unit test pro uart_driver", "cobre esses .c/.h com testes". Triggers without the word "skill" and without naming the framework. Do NOT use for integration, e2e, HIL, system or Robot Framework tests; nor to scan the project for targets (o...

Turns a repo's code review history into numbered coding standards, each rule with its why and the review comments behind it, then reviews diffs against them and keeps them lean. Use when writing or auditing coding standards or conventions from review history (mine, write), reviewing a diff, branch or pull request against standards (review), pruning standards that agents already follow unprompted (prune), or checking standards for drift, such as rules whose files are gone or prune data measured on an older default model (doctor).

把播客单集链接转成按章节整理的完整文字稿（本机 CapsWriter-Offline 语音识别，产出 chapters.md，非摘要）。用户给出播客/音频链接要求转录、转文字稿、整理成文，或问"那个播客转文字的 CLI 叫什么"时使用。本地音频文件（无链接）转写走 FunASR-Nano，见文内参考。

Write or revise school writing to the actual rubric. Use when Srijan has an essay, short answer, DBQ, lab write up, reflection, or any graded writing. Finds the prompt and rubric first (Canvas, handout, teacher slides), builds an outline that hits every rubric line, drafts in his voice, then grades the draft against the rubric before he sees it.

Pull what is due and what is coming from Canvas through the browser. Use when Srijan says "what's due", "canvas", "this week", "what do I have", "any tests coming", or at the start of a planning session. Reads the Canvas dashboard and each course's upcoming items through Claude in Chrome, lists them by date, adds test dates to Google Calendar, and writes the week into the notes.

Find and fix slow database queries with TableStudio, proving each fix with measurements, and check a database's overall health. Use when a query, page or endpoint is slow, when asked which queries are slow or what's wrong with the database, when adding, reviewing or dropping indexes, when an ORM query needs tuning, or when deciding whether a SQL rewrite is faster.

Set up and manage local development databases on the user's Mac through TableStudio. Use when a project needs a local Postgres, MySQL, ClickHouse or SQLite database, or a DATABASE_URL for one; when a local database refuses connections or is stopped (ECONNREFUSED, "connection refused", "could not connect to server", "Can't connect to MySQL server"); when the user wants a scratch or test database or a safe copy to experiment on; or when a PostgreSQL extension (pgvector, PostGIS, pg_trgm) needs installing.

How to read and change a project's database safely through TableStudio. Use for any task that touches a real database: querying or inspecting data, investigating a data bug, fixing or backfilling rows, seeding, adding or changing tables, columns, indexes or constraints, writing or reviewing a migration, or running SQL. Use it too whenever you'd otherwise reach for psql, mysql, sqlite3, wrangler d1 execute, a DATABASE_URL or a one-off script that opens its own connection.

Конкурентная запись в PostgreSQL без потерянных обновлений и write skew: условие в UPDATE, SELECT FOR NO KEY UPDATE против FOR UPDATE, exclusion-ограничения против пересечения интервалов, serializable и повтор при 40001/40P01/55P03, очередь задач на SKIP LOCKED, lock_timeout и NOWAIT, advisory-блокировки, разбор зависаний. Примеры — Go (pgx и go-transaction-manager), правила — про сам PostgreSQL. PostgreSQL concurrency: lost updates, write skew, row locks, exclusion constraints, isolation and retries, SKIP LOCKED queues, advisory locks.

Работа с PostgreSQL в Go через pgxpool (pgx v5) и avito-tech/go-transaction-manager: пул и устойчивый старт, структуры с тегами db и CollectRows, репозиторий через DefaultTrOrDB, транзакции через Do, propagation и savepoint, повтор транзакции при 40001/40P01/55P03, защита от SQL-инъекций, классификация ошибок и ON CONFLICT, batch и CopyFrom. Конкурентная запись и блокировки — скилл postgres-concurrency. PostgreSQL in Go via pgxpool and go-transaction-manager: pool, repositories, transactions, retries, errors, bulk loads.

Write a commit message for the currently staged changes. Use when the user asks for a commit message.

Web research with DeepSeek's Search & Fetch APIs. Use whenever the user asks to research something, look up or look into a topic, search the web, find sources, check current facts, numbers or prices, compare options with up-to-date info, fact check a claim, or do deep research / write a research report. Quick mode answers in chat with numbered citations; advanced (deep) mode runs a planner, researchers, fact-checker, reviewer and writer and builds a self-contained HTML report.

Set up or repair GitNexus in a repository so it never causes churn — no "index is N commits behind" after every commit and no CLAUDE.md/AGENTS.md rewrites from `gitnexus analyze`. Use when adding GitNexus to a repo, when the index reports itself stale/behind, when `gitnexus analyze` dirties CLAUDE.md/AGENTS.md/.claude/skills, or when asked to "apply the gitnexus no-churn pattern". Works with husky, lefthook, pre-commit or plain git hooks, any language.

Runs one Proof of Agent (minepoa.com) mining cycle using poa-agent-kit. Checks account & epoch status, writes and pre-flight checks an original 120-600 char Grade-3 Sybil-resistance answer if unanswered, submits, mines peer attestations, and reports. Schedule hourly around :20 past the hour.

Deep-research a non-fiction book, write a structured summary plus personal reflection, cross-check it against 2-3 independent summaries, save as a markdown file. Works on any book the user names. Use when the user asks for a "book summary", "deep book research", "summary of <book>", or invokes this skill by name. Default output path is ~/notes/books/<slug>.md.

Use when the user shares a draft (tweet, article, essay, story, bio) or asks for help writing one, to coach it toward plain, conversational, useful writing.

Builds copy-and-paste prompts for any task. Use whenever this plugin is invoked or the user asks for a prompt, a reusable prompt, or help improving one.

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.

Translate a Subtitlarr item by hand (Claude itself doing the translation) instead of a configured LLM provider — for items no cloud engine can handle (content-filter refusals, dead credentials, exhausted quota) or where Claude's own translation quality is wanted specifically. Use when the user asks to "translate this one yourself", mentions an item Gemini/another engine keeps refusing or failing on, or wants Claude to work through failed items directly.

Write this week's growth plan for the product linked in .zooi/project.json and submit it to zooi.ai for the person's approval. Use when the person asks to plan the week with zooi, or when /zooi:run reaches planning.

Write code whose purpose is to refuse: hook, guard, validator, permission check, lint rule, CI gate. Use when adding or changing any control that decides pass or fail. Make sure to use it whenever a check can be bypassed or fail to run, even if it is called a wrapper or a policy.

Branch, commit and open pull requests in this repo. Use whenever creating a branch, writing a commit message, pushing, opening or updating a PR, or when CI fails on a PR.