Writing & Editing

Draft X long posts, threads, and X Articles when an idea needs more than one short post. Chooses the format, structures it, and writes titles and openings. Does not publish.

Fill a ticket's technical post-mortem - write the whole root cause + fix into one tracker field (no restating the initial symptom), then point the other analysis fields at it ("see dev notes"). Tracker, fields, language and headings come from the config. Invoke for a given ticket or the fix in progress. Triggers - "analyse des causes", "analyse technique", "root cause", "cause racine", "solution apportée", "/analyse-causes".

Check whether the repo's own docs still describe the code after recent changes, and update the ones that went stale. Scopes itself to the last merged branch, the last commit, this session's work, or a full sweep. Use when asked to 'update the docs', 'check the docs', 'are the docs still accurate', 'docs sweep', 'refresh the documentation', or '/docs-update'. Every line it writes goes through the unslop skill. Run it before cutting a release or merging a feature, so docs ship with the change instead of trailing it.

Write or rework a skill using the four-check method - trigger, structure, steering, pruning.

Write focused, verifiable code changes or perform a defect-first review of a diff, commit, or pull request. Use for implementation discipline, refactoring, and code review; choose review mode only when requested. New names stay short and readable; comments explain why, not what.

Copy or cut conversation context between Codex, Pi, DeepSeek Harness, OpenCode, Qwen Code, Claude Code, WorkBuddy, Antigravity CLI (agy) and desktop IDE with the local agent-session-bridge CLI. Supports a transcript, exact session ID or project batch, including native database indexes; excludes credentials and agent configuration.

Audits a blog post draft or page copy for content-level SEO: search intent fit, focus keyphrase placement, E-E-A-T signals (experience, expertise, authoritativeness, trustworthiness), helpfulness and originality, content freshness, and internal linking. Use when the user asks "will this rank", "SEO check this post", "content SEO audit", or "optimize this post for search" — or proactively after a readability pass on a post that's meant to rank. For how the prose reads, use the `readability-check` skill; for titles and meta descriptions, use `metadata-check`; for site-wide technical SEO (sitemaps, structured data, canonicals), use `astro-seo` or `static-seo`.

How to write JSDoc (/** */) and inline (//) comments in the Astro codebase, for contributors reading the source — not end users. Use whenever writing or editing comments in .ts/.js source, including comments added incidentally while fixing bugs or building features. Does not cover the @docs-generated config/error reference.

Build and run a full email marketing channel — list building, deliverability, segmentation, newsletter strategy, campaign types, A/B testing, and email design. Use when the user says "email marketing", "email strategy", "email list", "newsletter", "email campaigns", "email list building", "email deliverability", "email open rates", "email segmentation", "email design", "email calendar", "grow my email list", "email marketing plan", "broadcast emails", "email engagement", or wants to use email as a primary owned marketing channel beyond just automated flows.

Investment master methodology distillation. Extract core principles from 15 top fund managers (Buffett, Dalio, Simons, Soros, Marks, Lynch, Druckenmiller, etc.), read dated public filings when supplied or retrieved, compare philosophies, and map insights to your own strategy. Use when: learning investment frameworks, analyzing a master's approach, checking institutional holdings, writing investment research, comparing risk management styles. Triggers on: "what would Buffett think", "Dalio's risk parity", "13F holdings Bridgewater", "compare Buffett vs Soros", "investment masters", "hedge fund strategy", "Ackman's thesis approach", "Howard Marks cycle

Academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing with strict academic standards.

Use when preparing the data-availability statement and the data/code archive for a Conservation Biology manuscript. The journal (Wiley/SCB) requires a data-availability statement for research/synthesis articles, encourages data sharing, and requires sensitive species data to be protected. Prepares the package; it does not waive requirements.

Repurpose existing content into a native X (Twitter) post or thread. Take a LinkedIn post, blog, YouTube script, or newsletter and rewrite it for X: re-hook for the no-fold first line, refit to 280 chars or a thread, strip off-platform artifacts, run the humanizer, publish via Publora on approval. Not for writing from scratch (use x-post-writer or x-thread-builder), not for auditing a draft (use x-humanizer --mode audit).

Take 1 blog post or article and generate 15-30 platform-native micro-content pieces. Not reformatting — re-contextualizing for each platform's culture. Triggers on: "atomize this content", "repurpose my blog post", "turn this into social posts", "content atomizer", "pillar content", "one to many content", "repurpose content", "multiply my content", "content explosion", "turn article into posts", "break down this article", "micro content from blog", "content pillar strategy", "10x my content", "platform-native content", "atomize", "content multiplication".

Repurpose existing content into a native Facebook Page post. Take a LinkedIn post, X thread, blog, or newsletter and rewrite it for a Page: warm the tone, lead with a standalone claim before the \"See more\" fold, move links to the first comment, strip off-platform artifacts (hashtag walls, \"link in bio\", @-handles), then humanize and publish via Publora on approval. Not for writing from scratch (use fb-post-writer), auditing a draft (use fb-humanizer), or comment replies (use fb-engagement-drafter).

>- Write a kolu blog post grounded in the real build history — mine the Claude Code session logs behind a feature for the actual story (for large efforts, fan out over the transcripts with an ultracode workflow), draft it in the author's voice, and wire it into the Astro site. Use when asked to write a blog post or engineering essay about something that was built, especially one that should read as a narrative of what actually happened rather than invented marketing copy.

Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs health check", "what should we document next".

Create, configure, manage, and validate Google Antigravity customizations including skills, rules, MCP servers, lifecycle hooks, plugins, and custom JSON configs. Use when adding new capabilities to Antigravity, configuring MCP servers, writing rules, creating skills, setting up hooks, or modernizing legacy workflows.

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

AMBIENT BACKGROUND TASK — FIRE ON EVERY SUBSTANTIVE TURN. The user does NOT need to ask. When the user mentions ANY domain (drafting, building, writing, composing, researching, planning, comparing options, exploring, deciding, learning, debugging, designing, refactoring, configuring — ANY domain engagement), you MUST side-effect a `.cues/CUES.md` predicting the vocabulary, knowledge, and prose alternatives they will reach for next. This is NOT optional and NOT triggered by phrases like "use the cues skill". Treat the cue file write as a structural requirement of the turn alongside your chat reply. If you find yourself thinking "should I fire the skill?" — the answer is yes. Skip only when (a) there is no domain signal at all (user said "thanks" or "ok"), (b) the user is asking about the cues system itself rather than working in a domain, or (c) the user explicitly said stop. Pivots (e.g. user switched from Express API to Next.js site) MUST trigger a fresh CUES.md write covering the new domain. Coding, desi...

Makes your agent write in ASD-STE100 Simplified Technical English.

Write full long-form copy drafts in the distinct style of history's greatest direct-response copywriters. Use this skill whenever a user asks to write sales copy, sales letters, landing page copy, advertorials, direct mail, email sequences, VSL scripts, or any persuasive long-form content. Also trigger when users ask to "write like [famous copywriter]", want copy that "actually sells", or describe wanting copy with a "direct response" feel. Always use this skill before writing any long-form persuasive copy — do not attempt to write it without consulting this skill first.

Master controller for the lit-review pipeline, driven by a document. Give it a .tex or .docx file describing an article — a full manuscript, an abstract, or a proposal — and it extracts a search plan, runs an Undermind deep search (through the Undermind MCP server) and Google Scholar (SearchAPI.io), then merges, deduplicates, and screens the results. Only use this skill when explicitly requested — e.g., the user says "run lit-review-orchestrator", "lit-review-orchestrator", or "/lit-review-orchestrator". Do NOT auto-trigger on general literature review requests.

Pick the audience and the role before writing or editing anything a human reads or hears — web copy, slides, proposals, READMEs, docs, email, posts, scripts. Use when drafting from scratch, when rewriting or editing existing prose however small the edit, and when writing lands in the wrong register.