Writing & Editing

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).

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.

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.

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.

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.

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.

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".

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 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).

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).