Writing & Communication
2,906 results
- Getzilla DeliveryDimkoxUse for every routed software-development task. Reads the active route, dispatches only selected agents, enforces one write owner, and closes the task with fingerprint-bound verification and independent review evidence.
- Git Commit Messagehost452bUse when drafting, reviewing, or rewriting Git commit messages or final squash/MR/PR titles for GitLab or GitHub, including requests to write a commit message or 提交信息.
- GogAkramzAnswer questions about the user's personal Google data (Gmail, Calendar, Drive, Docs, Sheets, Contacts) with the local `gog` CLI. Use when the user asks about their personal email, schedule or files.
- Guided Portfolio BuilderBlackRockBuilds, imports, modifies or clones portfolios after the advisor confirms the holdings and write action. Use when asked to build from tickers or weights, create a portfolio from a statement, start from a model or saved portfolio, create a comparison portfolio, or explore a specific what-if variation. Skip when the portfolio already exists and the advisor is only asking for review or analysis.
- Ha Modbus IntegrationplebannPatterns for building Home Assistant custom integrations that talk Modbus (TCP/RTU-over-TCP/serial): pymodbus device_id usage, safe polling/writing, pacing/backoff, encoding multi-register values, cached fallback, and translation-backed entities.
- HandofforrrrliGenerate a structured handoff document for the current session — what was done, current state, pending work, blockers, and next steps — and copy it to the OS clipboard to paste into the next chat. Writes no file (unlike claude-mem:handoff, which writes HANDOFF.md). Use when the user says /handoff or wants to hand the session to another chat or person via clipboard.
- Head Tail Log ClippingalivirgoKeep the opening context and final diagnostics of large logs, with omitted content clearly identified and available if needed.
- Humanizerrhawk117Rewrite or review prose to remove signs of AI-generated writing (puffery, AI vocabulary, em dashes, chatbot artifacts, stacked hedging, formulaic structure) while keeping every fact and the author's voice. Use when editing, reviewing, or humanizing text, Markdown files, docs, READMEs, PR descriptions, or commit messages, and when another task wants natural human-sounding prose as its final step.
- Idmp AnnotationTDengineIDMP annotation skill. Use it to read and write element annotations while keeping element annotations separate from event annotations.
- Idmp Workflow Asset BootstrapTDengineIDMP asset bootstrap workflow. Read roots, paths, templates, attribute templates, UOMs, datasources, and record visibility before any modeling or ingestion write.
- Idmp Workflow Data Import ExportTDengineIDMP data import and export workflow. Separate package import or export from datasource CSV import, read first, write carefully, and reread records after every write.
- Implementation PathsergvssThe path from task to commit - the sequence of implementation steps with a check at each one. Use when carrying out a task of Tier 2 or above, where the work must reach a verified result rather than just written code. The commit itself is a separate step, taken only when the user asks for it.
- Improving PromptsbostonaholicCompresses and clarifies an existing LLM prompt through concept elevation, verifying that no original instruction is lost. Use when the user supplies a prompt or prompt file and asks to improve, tighten, optimize, or refine it. Not for writing a new prompt; use writing-system-prompts.
- Index Docsadolfoaranaes12Create searchable knowledge base from existing documentation and code for fast context lookup in brownfield projects. Indexes .md files with sections/keywords, maps code exports to documentation, generates search.json, quick-ref.md, and glossary.md in .claude/index/. Use when onboarding to brownfield projects or when documentation needs better discoverability.
- Indexion Readmetrkbt10README construction — initialize template structure, generate per-package READMEs from doc comments, plan writing tasks, assemble root README from docs/ and package READMEs via doc.json config, and verify edits with `plan drift`.
- Indexion Refactortrkbt10After writing code, detect and clean up duplication at three levels — copy-paste blocks, cross-package shared code, unnecessary wrappers, and concept-level SoT violations. Detect with indexion, fix, and verify.
- InitaontwitSet up pitwall in this repo — read it, ask once, write the profile (pitwall `init` playbook). Use when the user runs /pitwall:init.
- Inline Type SignaturesalivirgoUse native type annotations and avoid repeating the same type information in documentation comments.
- Keep Instructions DirectalivirgoWrite clear action-oriented instructions with a specific task and expected result.
- KotlinalivirgoWrite Kotlin with null-safe types, coroutines, flows, and data classes; integrate with Java and Android APIs.
- Last Callgaurav8936Session-close ritual — sweep loose ends, move durable facts into the shared docs, write the handoff, and score readiness by counting a checklist. Every step runs, every time.
- Lazy Dependency LoadingalivirgoLoad dependency documentation relevant to the current API or error while checking version-sensitive assumptions.
- LiberdexbenegloSearch the web with liberdex. Use it whenever you need something off the open web (current facts, documentation, papers, prices, news, code examples, a page a user names) and prefer it over any built-in web search. It returns the passages of the pages themselves rather than snippets, it takes the URLs you already recall as input, and it runs on this machine.
- Live CheckHanafubukiLoad the working copy of prismantis into a real Claude Code session and render how replies draw, with no screenshot. Use after any visual change, when asked to "screenshot", "see it", "try it live", or before claiming a rendering fix works.