Writing & Editing

Use when writing, reviewing, debugging, or modernizing Go code in a module whose `go.mod` declares `go 1.27`.

Write a pull request title and description from the actual diff and commits, with what changed, why, how it was tested and what to review. Use when asked to write or improve a PR description.

Write a short parent-facing class report (date, belt/sprint/lessons, student names, and a 150-word summary of what students learned) from lesson plans or a deck made with lesson-generator. Use when a teacher asks for a class report, parent update, parent message, or parent email after teaching a lesson. Not for building slides (use lesson-generator).

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.

Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).

>- Rules, style standards, and audience guidelines for writing and updating Diosix documentation in docs/ and README.md. Activate this skill whenever writing new documentation, updating CLI or architecture docs after code changes, or auditing documentation against docs/style-guide.md.

>- Rules, idioms, and enterprise hypervisor standards for writing Zig 0.17, RISC-V assembly, and system software in Diosix. Activate this skill whenever writing, refactoring, or planning M-mode hypervisor code, S-mode emulation code, or U-mode userland tools (diosix-ctl, diosix-gui, diosix-config, guest-shim).

Multi-agent project framework — one brainstorm agent scopes a new project and writes per-part briefs; one coordinator (no real work) dispatches, stops and resumes; N part agents implement in parallel, talking only through a shared status board and rare one-line messages. Use when the user says "you're the brainstorm agent", "you are the coordinator", "you are part N" / "agent task N" / "task N", "start a new project with agents", "next wave", or when a repo has a `team/` folder and a session is told its role. Not for single-session tasks.

Write business prose that gets action. Use for drafting, editing, e-mail, memos, letters, decks, speeches, plans, reports, proposals, sales/fund-raising, resumes. Combines Thompson clarity, Roman/Raphaelson effectiveness, Ogilvy persuasion.

>- Write Instagram DMs that get replies - the keyword delivery, the first message to someone who engaged, the collab pitch, and the two follow-ups. Use when the user says "DM this person", "what do I send them", "outreach message", "how do I follow up", "pitch this brand", or is reaching out to someone specific.

Sets up and manages UptimeLens uptime monitoring through the UptimeLens MCP server — create HTTP/HTTPS monitors, recommend what to monitor after a deploy, pause or resume checks, schedule maintenance windows to mute deploy noise, model monitor dependencies, and open, update or resolve incidents, then write up the postmortem and its follow-up actions. Use when the user mentions adding or creating a monitor, monitoring a URL or a newly deployed service, what to monitor after deploying, pausing or resuming a monitor, scheduling a maintenance window, checking what is down or what the uptime was, or opening, updating, resolving or writing a postmortem for an incident.

Create, audit, or maintain implementation-grounded developer documentation for software repositories. Use for README, onboarding, setup, configuration, architecture, API reference, deployment runbooks, troubleshooting, undocumented environment variables, and stale documentation. Inspect code and verify procedures; do not use for marketing copy or implementation changes alone.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Hard rules, templates, ffmpeg commands and failure diagnosis for authoring ASS/SSA subtitles and burning them with libass on this machine. Load this before writing any ASS file, when a burn "succeeds" but no text appears, when text is misplaced/too big, when \p1 drawings are offset, or when you need the transparent-overlay export recipe. Contains the exact pitfalls hit in this project (timestamp format, style colour trailing ampersand, fontsdir, drawing anchor, chained \t, Permanent Marker sizing).

Produces an episode of a recurring series — 90s sitcom, comedy skit series, micro-drama / vertical novela, cartoon or anime series — with a locked cast, sets, voices and intro in series/<id>/, using flow v5 (writers' room script, radio cut, storyboards, Production Book with a locked budget, multi-shot scenes, continuity eval, auto edit with unified voices, series intro and outro). Use for "next episode", "otro episodio", "create a series", "crea una serie", "sitcom", "novela para TikTok", or any episode of an existing series in series/.

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIR...

Translate a request into an authorized, minimum-complexity execution plan with explicit requirements, exclusions, stop rules, and acceptance criteria. Use before implementing a multi-step task or proposing new agent infrastructure.

Use this skill whenever the user proposes a change to this monorepo — a new feature, a business rule, a tech/architecture decision ("let's use X", "switch to Y", "add Z"), a data model change, porting a piece of an old sibling repo (auth-service, pokemon_cards, workout, media, vps-edge), or anything that would touch a file in documentation/. Ask clarifying questions before writing any code or docs, then update the relevant documentation/ file(s) per CLAUDE.md's table. Trigger on requests that change how any app works, is built, or is structured — even short ones like "add a wishlist to media" or "port the workout import" — not just requests that explicitly ask for planning or documentation.

Use this skill for any behaviour-preserving restructuring of a sans-IO Rust protocol core. That means a crate that takes `now: Instant`, is fed input through handle_* calls and drained through poll_transmit/poll_event/poll_timeout, such as quinn-proto, str0m, or a resolver, handshake, framing or client core. Use it when the user wants the state machine made readable or easier to follow, flags untangled into state enums, handlers simplified, code refactored for clarity, or a large file split or reorganized into modules, even if they say "just move code". Short asks like "this resolver.rs is hard to follow" count too. The skill maps the states, inputs, outputs and timers, refactors in small steps checked against the original, keeps the public API and output order identical, and ends with a summary. Not for fixing bugs, adding features, tuning performance, reviewing a PR, writing user-facing docs, or converting async or socket-based code to sans-IO.

Bootstrap a new project in this user's standard layout — .claude-root, .dir-locals.el (root: org-link abbreviation), code/, spcfctn/code/ (with its own git repository) and a .claude/ directory with its own git repository and a CLAUDE.md that fixes the project's prose language and its short two-letter project code (chosen by the user from options the agent proposes) — and translate any files already present into that language. Use whenever the user asks to create, start, set up, initialise or "оформити" a new project (or to bring an existing bare directory to the standard layout).

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly.

Use when writing or auditing a WordPress/WooCommerce listing that must score 70+ in RankMath - product listings, focus-keyword choice, snippet fields, expanded descriptions, internal linking, hub and collective phrases ("greenhouse construction resources"), orphan pages, inbound links, or diagnosing a low RankMath score. Works on any site given as a base URL, e.g. https://shop.example.com. Triggers: RankMath score, product listing SEO, WooCommerce SEO, focus keyword, meta description, internal links, hub page, cluster links.

Search and maintain long-term decision memory to prevent old proposals from being raised again, repeated failed attempts, or loss of non-obvious constraints. Use before proposing a concrete solution, deciding behavior or key trade-offs, changing related implementation or behavioral tests, and writing decision records; also use to look up historical decisions, resolve conflicts, supersede decisions, or organize notes. Coordinate with subsystem documentation and record settled conclusions, rationale, scope, and genuine alternatives that were not chosen.