agentsclimarketplace

Docs & writing

16,632 rows, by stacks then stars

3,030 of these skill files have been read, by 1,951 distinct authors, and what they tell an agent counted. What Docs & writing authors agree on, and what they forbid

  • Ceo people update drafter

    trycomp-io/comp-skills/skills/ceo-people-update-drafter Skill

    2★ repo

    Gera o update CHRO → CEO (mensal/trimestral) em formato 1-pager. Estruturado em resumo executivo, métricas-chave (com trend e contexto), principais movimentações (hires/promoções/exits), wins, riscos (com mitigação+owner) e asks pro CEO. Output: HTML + Markdown editável. Dual-mode: works in Claude Code (script + rich output file) AND Claude Cowork (output generated inline as markdown, plus a self-contained HTML artifact when available). Trigger em "update pro CEO", "people update", "report mensal de RH", "update trimestral de people", "report do CHRO". Mantida pela Comp.

  • Chro chief of staff

    trycomp-io/comp-skills/skills/chro-chief-of-staff Skill

    2★ repo

    Chief of Staff conversacional do CHRO. Mantém contexto (stakeholders, cadências, calendário, open loops) e ajuda com pré-meeting briefs, visão semanal, drafts de comunicação (email/Slack/IM em PT-BR ou EN), strategic prompts baseados em cadência, e orquestração com os outros skills da Comp (paygap, attrition, comp-ratio, board-slide, decision-memo, etc.). Dual-mode: works in Claude Code (contexto persistente em ~/.comp-skills/chro-context.json via script) AND Claude Cowork (contexto na conversa ou num Project do Cowork; todo output gerado inline em markdown). Trigger em "brief pra reunião X", "como tá minha semana", "drafta um email pro CEO/CFO/board", "o que devo estar fazendo agora", "minha CoS", "open loops", "adicionar action item". Mantida pela Comp.

  • Comp ratio analyzer

    trycomp-io/comp-skills/skills/comp-ratio-analyzer Skill

    2★ repo

    Analisa compa-ratio (salário ÷ mediana da banda) de roster contra tabela salarial. Identifica clusters under/below/at/above/over, top 10 outliers por direção, custo mensal+anual pra equalizar abaixo da mediana, breakdown por nível. Output HTML executivo. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "comp ratio", "análise de posicionamento salarial", "quanto custa equalizar salários", "outliers salariais", "compa ratio". Mantida pela Comp.

  • Decision memo generator

    trycomp-io/comp-skills/skills/decision-memo-generator Skill

    2★ repo

    Gera memo estruturado de decisão pra qualquer people topic crítico que precisa ser comunicado/defendido. Estrutura: problema, contexto, opções (com prós/cons), recomendação com rationale, riscos, ask. Output HTML + MD editável. Trigger em "decision memo", "memo de decisão", "estruturar decisão de people", "documento de decisão", "memo pro CEO/board". Mantida pela Comp.

  • Engagement deep dive

    trycomp-io/comp-skills/skills/engagement-deep-dive Skill

    2★ repo

    Analisa CSV de pesquisa de engajamento (eNPS, survey de cultura, pulse) e segmenta por tenure / área / manager / nível. Output HTML executivo com eNPS global, ranking de áreas (piores primeiro), bottom 10 managers, insights e priorização. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "análise de engajamento", "engagement deep dive", "eNPS por área", "segmentar survey", "drivers de engajamento", "diagnóstico de cultura". Mantida pela Comp.

  • Flight risk forecast

    trycomp-io/comp-skills/skills/flight-risk-forecast Skill

    2★ repo

    Scoring EXPLICÁVEL de risco de saída (flight risk) por colaborador a partir de um roster CSV. Não é caixa-preta: cada ponto de risco é atribuído a um fator transparente (comp abaixo da mediana, estagnação de carreira, baixo engajamento, janela de churn, gestor com saídas altas). Devolve lista priorizada, breakdown por fator, distribuição por banda (Baixo/Médio/Alto/Crítico), flag de risco lamentável (regretted = alto risco + alto desempenho), áreas/gestores mais quentes e alavancas de retenção sugeridas. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "risco de saída", "flight risk", "quem está pra sair", "previsão de turnover", "retention risk", "forecast de attrition", "quem está em risco de pedir demissão". Maintained by Comp, free skill for HR & People leaders.

  • Hr data maturity assessment

    trycomp-io/comp-skills/skills/hr-data-maturity-assessment Skill

    2★ repo

    Gera um assessment HTML interativo de maturidade de dados de RH em 5 níveis (Ad-hoc, Operacional, Reporting, Analytics, AI-native) × 5 dimensões (Coleta, Governança, Reporting, Análise, Tech & AI). 15 perguntas, ~5 minutos, output com nível por dimensão + roadmap personalizado pra avançar. 100% client-side. Dual-mode: works in Claude Code (interactive HTML assessment via script) AND Claude Cowork (conversational assessment + markdown scorecard, plus a self-contained HTML artifact when available). Trigger em "maturidade de dados de RH", "HR data maturity", "diagnóstico de people analytics", "qual o nível do meu RH em dados", "avaliação de people ops", "como estamos em analytics". Mantida pela Comp.

  • Manager effectiveness scorecard

    trycomp-io/comp-skills/skills/manager-effectiveness-scorecard Skill

    2★ repo

    Diagnóstico de eficácia por gestor cruzando múltiplos sinais (span de controle, atrito do time, engajamento médio, taxa de promoção) num score composto 0-100 com bandas (At-risk/Developing/Solid/Exemplar) e flags acionáveis (gestor em risco, sobrecarregado, subutilizado). A partir de um roster CSV (opcionalmente eventos de saída). Regra de confidencialidade: gestores com menos de 3 directs ficam fora de rankings e médias. Output HTML executivo com ranking, scorecard por gestor, distribuição e outliers. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "eficácia de gestores", "scorecard de gestores", "quais líderes estão em risco", "manager effectiveness", "manager scorecard", "quais gestores têm mais atrito", "qualidade da liderança". Maintained by Comp, free skill for HR & People leaders.

  • Paygap analysis generator

    trycomp-io/comp-skills/skills/paygap-analysis-generator Skill

    2★ repo

    Generates a gender pay-gap HTML report from any HR roster (CSV or Excel). Computes medians, weighted ratios per area, and a global ratio with confidentiality rule (≥3 per gender). Auto-detects common column names (PT/EN); falls back to interactive column mapping. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger on phrases like "análise de pay gap", "gender pay gap", "equidade salarial por gênero", "relatório de equidade", "diagnóstico de gap salarial", "pay equity report", "diferença salarial entre gêneros". Maintained by Comp, free skill for HR & People leaders.

  • People scorecard

    trycomp-io/comp-skills/skills/people-scorecard Skill

    2★ repo

    Gera o pacote canônico mensal de People analytics a partir de um roster CSV (+ eventos opcional). Calcula headcount (total, por área, por nível), attrition anualizada (split lamentável se houver flag), tenure médio + distribuição, span of control (médio + distribuição), mobilidade interna (promoções), representatividade de gênero geral E em liderança com regra de confidencialidade (grupos < 3 suprimidos), taxa de novos contratados/crescimento, e tendência do período se os eventos tiverem datas. Output: scorecard executivo de uma página, o pacote que você entrega pro CEO. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "people scorecard", "pacote de people analytics", "dashboard de RH", "scorecard de pessoas", "people metrics", "indicadores de RH pro board", "headcount e attrition". Maintained by Comp, free skill for HR & People leaders.

  • Promotion equity analyzer

    trycomp-io/comp-skills/skills/promotion-equity-analyzer Skill

    2★ repo

    Analisa equidade de promoções por gênero. CSV de promoções + (opcional) CSV de população elegível → HTML executivo com taxas por gênero, gap F vs M, áreas com maior disparidade, transições de nível mais comuns, insights pra compliance e ação. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "equidade de promoção", "promotion equity", "gap de promoção por gênero", "análise de promoções", "disparidade de promoção". Mantida pela Comp.

  • Recruiting funnel analytics

    trycomp-io/comp-skills/skills/recruiting-funnel-analytics Skill

    2★ repo

    Analisa a efetividade de aquisição de talentos a partir de um CSV de pipeline de candidatos. Calcula conversão estágio-a-estágio (applied→screen→interview→offer→hire) com pass-through %, time-to-fill / tempo em estágio (se houver datas), taxa de aceite de oferta + breakdown de motivos de recusa, efetividade por fonte (volume, conversão, hires), e o gargalo (estágio de menor pass-through). Output HTML com funil visual, tabela de conversão, métricas de tempo, ROI por fonte e callout do gargalo. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "funil de recrutamento", "conversão do recrutamento", "time-to-fill", "taxa de aceite de oferta", "efetividade por fonte", "recruiting funnel", "where do candidates drop off", "gargalo do recrutamento". Maintained by Comp, free skill for HR & People leaders.

  • Regretted attrition analyzer

    trycomp-io/comp-skills/skills/regretted-attrition-analyzer Skill

    2★ repo

    Analisa CSV de desligamentos e identifica padrões em regretted vs unregretted: top correlated factors (área, gestor, tenure, performance, nível), motivos declarados, insights pra ação. Output HTML executivo defensável pra CHRO levar pro CEO. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "análise de regretted attrition", "padrões de turnover", "por que estamos perdendo gente", "investigar desligamentos", "regretted vs unregretted", "diagnóstico de turnover". Mantida pela Comp.

  • Representation dei funnel

    trycomp-io/comp-skills/skills/representation-dei-funnel Skill

    2★ repo

    Analisa diversidade ao longo do ciclo de vida (além de pay): representatividade por recorte demográfico em cada estágio (headcount geral, liderança, contratações, promoções, saídas) pra revelar onde a representatividade vaza. Mostra gap de liderança vs geral, taxas de promoção e saída por grupo, e pontos de vazamento. A partir de um roster CSV (+ eventos opcionais). Regra de confidencialidade: células com menos de 3 pessoas são omitidas, nunca expõe indivíduos. Output HTML com barras empilhadas por estágio. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "funil de diversidade", "representatividade na liderança", "onde perdemos diversidade", "DEI funnel", "representation analysis", "diversidade por estágio", "gap de liderança". Maintained by Comp, free skill for HR & People leaders.

  • Research digest

    trycomp-io/comp-skills/skills/research-digest Skill

    2★ repo

    Curates a rolling 12-week digest of high-signal papers, working papers, and publications on Org Design, Workforce Planning, and AI impact on the workforce. Sources include academic (OpenAlex, arXiv) and practice (top consultancies, thought leaders). Produces a translated PT-BR executive report. Dual-mode: works in Claude Code (multi-source script + rich HTML report) AND Claude Cowork (web-search curation + markdown digest, plus a self-contained HTML artifact when available). Trigger on phrases like "digest de pesquisa", "radar de papers", "novidades em org design", "research review RH", "panorama academico de workforce planning", "atualizacao de pesquisa sobre IA no trabalho", "leituras sobre future of work". Maintained by Comp, free skill for HR & People leaders.

  • Skills gap analysis

    trycomp-io/comp-skills/skills/skills-gap-analysis Skill

    2★ repo

    Analisa lacunas de capacidade da força de trabalho contra um conjunto de capacidades-alvo e recomenda build/buy/borrow por gap. Calcula cobertura por skill (pessoas no nível requerido ÷ headcount necessário), magnitude do gap, prioridade (criticidade × gap) e gera heatmap (skill × criticidade), lista priorizada de gaps e resumo de implicações de hiring/training. Output HTML executivo. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "skills gap", "análise de lacunas de competências", "build buy borrow", "gap de capacidade", "matriz de competências", "workforce capability gap", "skills inventory". Mantida pela Comp.

  • Span of control diagnostic

    trycomp-io/comp-skills/skills/span-of-control-diagnostic Skill

    2★ repo

    Diagnóstico de Span of Intelligence, evolução do span of control tradicional. Lê CSV/XLSX da org (employee, manager, opcionalmente ai_agents + automation_pct) e gera relatório HTML com classificação dos gestores em Tradicional / Híbrido / Orquestração / Subutilizado / Sobrecarregado-sem-IA. Recomendações reframed (em vez de "quebre time grande", sugere "automatize ou senior-ize"). Baseado no artigo Comp na Cajuína. Dual-mode: works in Claude Code (Python script + rich HTML report) AND Claude Cowork (inline analysis + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "span of control", "span of intelligence", "diagnóstico organizacional", "análise de org", "estrutura organizacional", "camadas", "manager-to-IC ratio", "layers". Mantida pela Comp.

  • Documentation writer

    rudrathegreat/Astronomy-AI-Toolkit/skills/software_engineering/documentation_writer Skill

    no license2★ repo

    Write scientific Python documentation, docstrings, READMEs, and reference material.

  • Manuscript writing

    jeonnoin-alt/Eureka/skills/manuscript-writing Skill

    2★ repo

    Use when writing a research manuscript — guides section-by-section writing with prerequisite gates, citation discipline, number traceability, and per-section subagent review. Activated after experiment results are reviewed and before claims-audit.

  • Research journal

    jeonnoin-alt/Eureka/skills/research-journal Skill

    2★ repo

    Use when finishing a research work session, after making a significant methodological decision, after a failed experiment or unexpected result, before a phase transition, or when the user explicitly asks to log/memo/remember the session — appends a structured narrative entry to docs/eureka/journal/ capturing decisions, failures, surprises, blockers, and next-session starting points

  • Repo wayfinder

    Wang-Cankun/cankun-skills/skills/repo-wayfinder Skill

    2★ repo

    Index of my agent skills — each skill lives in its own repo

  • Use docs cockpit

    Guohao1020/docs-cockpit/plugins/docs-cockpit/skills/use-docs-cockpit Skill

    2★ repo

    Entry/router for the docs-cockpit skill ecosystem. Loaded by default in any project that has a docs-cockpit.yaml. Tells the agent: this project uses docs-cockpit; cognition lives in skills, python only renders; route to docs-cockpit-build (create/extend association), docs-cockpit-rebuild (refresh/diagnose/read-status/health checkup), or CLI docs-cockpit render (just regenerate HTML).

  • Docs cockpit build

    Guohao1020/docs-cockpit/skills/docs-cockpit-build Skill

    2★ repo

    Build or set up docs-cockpit from 0→1: create docs-cockpit.yaml, wire modules to specs/plans, add anchors, draft missing docs, and render the dashboard.

  • Docs cockpit rebuild

    Guohao1020/docs-cockpit/skills/docs-cockpit-rebuild Skill

    2★ repo

    Refresh an existing docs-cockpit: diagnose stale anchors, re-sync changed specs, answer status/progress questions, run health checks, and render fixes.

  • Use docs cockpit

    Guohao1020/docs-cockpit/skills/use-docs-cockpit Skill

    2★ repo

    Entry/router for the docs-cockpit skill ecosystem. Loaded by default in any project that has a docs-cockpit.yaml. Tells the agent: this project uses docs-cockpit; cognition lives in skills, python only renders; route to docs-cockpit-build (create/extend association), docs-cockpit-rebuild (refresh/diagnose/read-status/health checkup), or CLI docs-cockpit render (just regenerate HTML).

  • Content and copy

    rampstackco/claude-skills-starter/skills/content-and-copy Skill

    2★ repo

    Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog post, draft an article, write copy for, edit this, rewrite this, write content, write a guide, draft a how-to, write web copy. Also triggers when content has been outlined and now needs to be written, or when existing content needs voice or clarity edits.

    The same file is in 2 other repositories

  • Pm spec writing

    rampstackco/claude-skills-starter/skills/pm-spec-writing Skill

    2★ repo

    Translate ideas, feature requests, or vague concepts into specific, actionable dev briefs. Use this skill whenever the user has an idea they want to build, a feature to spec out, a bug to file, a project to scope, or needs to convert a half-formed idea into a clear implementation brief. Triggers on I want to add, we should build, can we make, what is the plan for, how do we implement, dev brief, feature spec, PRD, user story, acceptance criteria, scope this, prioritize. Also triggers when the user has a list of things they want to build and needs help converting them into well-formed tasks.

    The same file is in 2 other repositories

  • Paper write

    raja21068/AutoResearch/skills/aris/paper-write Skill

    2★ repo

    Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

  • Paper writing

    raja21068/AutoResearch/skills/aris/paper-writing Skill

    2★ repo

    Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → figure-spec/paper-illustration/mermaid-diagram → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished PDF. At `— effort: max | beast` (or explicit `— assurance: submission`), Phase 6 gates the Final Report on `tools/verify_paper_audits.sh`; the PDF is labelled `submission-ready` only when the external verifier is green. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

  • Proof writer

    raja21068/AutoResearch/skills/aris/proof-writer Skill

    2★ repo

    Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.

    The same file is in 2 other repositories

  • Paper write

    raja21068/AutoResearch/skills/aris/skills-codex-claude-review/paper-write Skill

    2★ repo

    Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

    The same file is in 1 other repository

  • Paper write

    raja21068/AutoResearch/skills/aris/skills-codex-gemini-review/paper-write Skill

    2★ repo

    Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.

    The same file is in 1 other repository

  • Paper writing

    raja21068/AutoResearch/skills/aris/skills-codex-gemini-review/paper-writing Skill

    2★ repo

    Workflow 3: Full paper writing pipeline. Orchestrates paper-plan \u2192 paper-figure \u2192 paper-write \u2192 paper-compile \u2192 auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says \"\u5199\u8bba\u6587\u5168\u6d41\u7a0b\", \"write paper pipeline\", \"\u4ece\u62a5\u544a\u5230PDF\", \"paper writing\", or wants the complete paper generation workflow.

    The same file is in 1 other repository

  • Paper write

    raja21068/AutoResearch/skills/aris/skills-codex/paper-write Skill

    2★ repo

    Draft LaTeX paper section by section from an outline. Use when user says \"\u5199\u8bba\u6587\", \"write paper\", \"draft LaTeX\", \"\u5f00\u59cb\u5199\", or wants to generate LaTeX content from a paper plan.

    The same file is in 1 other repository

  • Paper writing

    raja21068/AutoResearch/skills/aris/skills-codex/paper-writing Skill

    2★ repo

    Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → figure-spec/paper-illustration/mermaid-diagram → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished PDF. At `— effort: max | beast` (or explicit `— assurance: submission`), Phase 6 gates the Final Report on `tools/verify_paper_audits.sh`; the PDF is labelled `submission-ready` only when the external verifier is green. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

  • Proof writer

    raja21068/AutoResearch/skills/aris/skills-codex/proof-writer Skill

    2★ repo

    Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, \u8865\u5168\u8bc1\u660e, \u5199\u8bc1\u660e, \u8bc1\u660e\u67d0\u4e2a\u547d\u9898, or determine whether a claimed proof can actually be completed under the stated assumptions.

    The same file is in 4 other repositories

  • Specification writing

    raja21068/AutoResearch/skills/aris/skills-codex/specification-writing Skill

    2★ repo

    Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

    The same file is in 1 other repository

  • Writing systems papers

    raja21068/AutoResearch/skills/aris/skills-codex/writing-systems-papers Skill

    2★ repo

    Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.

    The same file is in 1 other repository

  • Specification writing

    raja21068/AutoResearch/skills/aris/specification-writing Skill

    2★ repo

    Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

    The same file is in 1 other repository

  • Writing systems papers

    raja21068/AutoResearch/skills/aris/writing-systems-papers Skill

    2★ repo

    Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.

    The same file is in 1 other repository

  • Paper orchestra

    raja21068/AutoResearch/skills/paper-pipeline/paper-orchestra Skill

    2★ repo

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines, optional figures) into a submission-ready LaTeX manuscript and compiled PDF. TRIGGER when the user asks to "write a paper from my experiments", "turn this idea and these results into a paper", "generate a conference submission", "run paper-orchestra on X", or otherwise wants the end-to-end paper-writing pipeline. Coordinates the outline-agent, plotting-agent, literature-review-agent, section-writing-agent, and content-refinement-agent skills.

    The same file is in 1 other repository

  • Paper writing bench

    raja21068/AutoResearch/skills/paper-pipeline/paper-writing-bench Skill

    2★ repo

    Reverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build a benchmark case for evaluating paper-writing pipelines. Replicates the PaperWritingBench dataset construction procedure from arXiv:2604.05018 §3 / App. C. TRIGGER when the user asks to "build a benchmark case from this paper", "reverse-engineer raw materials", or "evaluate my pipeline against PaperWritingBench".

    The same file is in 3 other repositories

  • Section writing agent

    raja21068/AutoResearch/skills/paper-pipeline/section-writing-agent Skill

    2★ repo

    Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimental_log.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges everything into the template that already contains Intro + Related Work from Step 3. TRIGGER when the orchestrator delegates Step 4 or when the user asks to "write the methodology and experiments sections" or "fill in the rest of the paper".

    The same file is in 3 other repositories

  • Managing agents md

    oryanmoshe/agent-skills/skills/managing-agents-md Skill

    no license2★ repo

    Creates and maintains AGENTS.md documentation files that guide AI coding agents through a codebase. Use when adding a significant new feature or directory, changing project architecture, setting up a new project or monorepo, noticing a codebase has no AGENTS.md, or after major refactors that change project structure. Also triggers on "document this for agents", "update agents.md", or "create agents.md".

    The same file is in 2 other repositories

  • Writing skills

    oryanmoshe/agent-skills/skills/writing-skills Skill

    no license2★ repo

    Guides creation and editing of SKILL.md files following Anthropic best practices and this repo's conventions. Use when creating a new skill, editing an existing skill, porting a skill from another source, or reviewing skill quality. Triggers on "create skill", "new skill", "write skill", "edit skill", "improve skill", or any work that adds or modifies files under skills/.

  • Bug report writer

    ShreyasBh02/AI-Skills-Collection/bug-report-writer Skill

    no license2★ repo

    Converts rough notes, casual descriptions, console errors, or quick observations into professional, complete bug reports — exported as a formatted Excel (.xlsx) file ready for Excel, Google Sheets, Jira, or Azure DevOps. Use this skill whenever the user mentions: "write a bug report", "log a bug", "report this issue", "found a defect", "something is broken", "create a bug ticket", "fill bug report", "document this bug", "file a ticket", "issue log", "defect report", "bug tracker", "something's wrong with", or pastes rough notes, console errors, or stack traces about unexpected behavior. Always trigger even for vague inputs like "the button doesn't work" or "this is broken" — the skill will infer details via smart assumptions and produce a professional output regardless. Trigger for single bugs AND multiple bugs described in one message.

  • Log to bug report converter

    ShreyasBh02/AI-Skills-Collection/log-to-bug-report-converter Skill

    no license2★ repo

    Parses error logs, stack traces, and test failures into production-ready bug reports.

  • Write a prd

    CookiesHaha/ash-claude-skills/plugins/ash-workflow/skills/write-a-prd Skill

    2★ repo

    PRD 写作工作流:从功能大纲同时生成本地 Markdown PRD 与飞书云文档 PRD 骨架,按统一章节规范(§1 版本信息 / §2 变更日志 / §3 整体说明 / §4 需求详细设计 / §5 功能清单 / §6 Open Questions / §7 附录)输出,便于后续用 lark-workflow-prd-sync 同步、lark-workflow-prd-to-userstory 拆成 User Story。当用户需要创建新 PRD、写 PRD、PRD 初稿、PRD 骨架、write-a-prd、起草产品需求文档时使用。

  • Lark to wechat mp

    CookiesHaha/ash-claude-skills/plugins/lark-prd-workflow/skills/lark-to-wechat-mp Skill

    2★ repo

    Use when syncing a Feishu (Lark) document or Wiki page to a WeChat Official Account (微信公众号) draft box. Handles Feishu CDN image migration to WeChat CDN, Markdown-to-WeChat HTML conversion (inline styles, callout blocks), and cover thumbnail creation. Requires WeChat AppID/AppSecret pre-configured.

  • Write a prd

    CookiesHaha/ash-claude-skills/plugins/lark-prd-workflow/skills/write-a-prd Skill

    2★ repo

    PRD 写作工作流:从功能大纲同时生成本地 Markdown PRD 与飞书云文档 PRD 骨架,按统一章节规范(§1 版本信息 / §2 变更日志 / §3 整体说明 / §4 需求详细设计 / §5 功能清单 / §6 Open Questions / §7 附录)输出,便于后续用 lark-workflow-prd-sync 同步、lark-workflow-prd-to-userstory 拆成 User Story。当用户需要创建新 PRD、写 PRD、PRD 初稿、PRD 骨架、write-a-prd、起草产品需求文档时使用。

  • Copilot docs

    Makiya1202/ai-agents-skills/skills/copilot-docs Skill

    no license2★ repo

    Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instructions, copilot-instructions.md, GitHub Copilot config.

  • Mongodb

    Makiya1202/ai-agents-skills/skills/mongodb Skill

    no license2★ repo

    Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.

  • Show notes writer

    SkillMedev/creator-studio/skills/show-notes-writer Skill

    2★ repo

    Produces complete podcast show notes from a transcript or episode outline - a standalone summary block, timestamped chapters that name what happens, screenshot-worthy key takeaways, guest bio, curated links, and keyword placement for search. Use when someone says "write show notes for this episode", "turn this transcript into an episode description", "add chapters and timestamps", or "make this episode findable on Google". Do NOT use to fan the episode out into clips, quote cards, and social posts - use content-repurposing instead; do NOT use to write burned-in video captions from the transcript - use captions-from-transcript instead; do NOT use to pitch the show to other podcasts - use podcast-pitch instead.

    The same file is in 1 other repository

  • Thumbnail concept

    SkillMedev/creator-studio/skills/thumbnail-concept Skill

    2★ repo

    Produces three distinct high-CTR YouTube thumbnail concepts per video - each a full spec with focal point, precise facial-expression direction, text overlay copy, color and background direction, and two paired title variants. Use when someone says "I need a thumbnail idea", "why is my CTR low", "help me pick a thumbnail and title", or is planning a video before filming and wants the click package designed first. Do NOT use for the spoken and visual opening seconds of the video itself - use video-hook-writer instead; do NOT use to write the full video - use youtube-script-writer instead; do NOT use for cropping, captioning, or exporting finished video files - use social-video-formatter instead.

    The same file is in 1 other repository

  • Video hook writer

    SkillMedev/creator-studio/skills/video-hook-writer Skill

    2★ repo

    Writes the spoken line plus visual frame combination for the first 3 seconds of a short-form video, delivering labeled variants built from six proven hook formulas and matched to TikTok, Reels, or Shorts. Use when someone says "write a hook for this video", "my Shorts die in the first seconds", "give me openers for this TikTok", or "how should this Reel start". Do NOT use for the first line of a written post, thread, or caption - use social-hook-generator instead; do NOT use to build the full thread after the opener - use tweet-thread-builder instead; do NOT use for the 30-second intro of a long-form YouTube video - use youtube-script-writer instead; do NOT use to design the clickable image for a video - use thumbnail-concept instead.

    The same file is in 1 other repository

  • Youtube script writer

    SkillMedev/creator-studio/skills/youtube-script-writer Skill

    2★ repo

    Writes retention-engineered long-form YouTube scripts on a hook/body/payoff architecture - a first-30-seconds hook that survives the retention cliff, a beat-sheet body with mini-hooks and bridges, timed pattern interrupts, and a payoff that over-delivers - with B-roll and editing cues marked inline. Use when someone says "script my next video", "my retention graph dies at the start", "tighten this draft", or "outline a video on X". Do NOT use for the 3-second opener of TikTok, Reels, or Shorts - use video-hook-writer instead; do NOT use for spoken voiceover synced to on-screen tutorial actions - use narration-script instead; do NOT use for a sales demo built on a buyer's discovery notes - use demo-script instead; do NOT use to design the thumbnail and title - use thumbnail-concept instead.

    The same file is in 1 other repository

  • Write application

    palashjain95/jobhunter/.claude/skills/write-application Skill

    2★ repo

    This skill should be used when the user asks to "write a cover letter", "draft outreach", "LinkedIn message", "referral ask", "write my essay", "answer this application question", or "help me apply to [company]". Produces all written application materials in one flow.

  • Property report

    paulieb89/bouch-plugins/plugins/foundations/skills/property-report Skill

    no license2★ repo

    UK property analysis: comparable sales, EPC ratings, rental yields, stamp duty, market context, and a BUY/WATCH/PASS verdict for a named address or postcode. Use to analyse a property, value a house, check what a place is worth, compare area prices, assess rental yield, or pull a full investment report. British spelling, UK stamp duty bands, real Land Registry and Rightmove data via the BOUCH property MCP.

  • Property report

    paulieb89/bouch-plugins/plugins/property/skills/property-report Skill

    no license2★ repo

    UK property analysis: comparable sales, EPC ratings, rental yields, stamp duty, market context, and a BUY/WATCH/PASS verdict for a named address or postcode. Use to analyse a property, value a house, check what a place is worth, compare area prices, assess rental yield, or pull a full investment report. British spelling, UK stamp duty bands, real Land Registry and Rightmove data via the BOUCH property MCP.

  • Data storytelling

    the-hugin/RSIm/skills/data-storytelling Skill

    no license2★ repo

    Transform raw data into persuasive business narratives using Setup→Conflict→Resolution framework. Templates for problem-solution, trend analysis, and comparison stories. Use when presenting data to stakeholders or building data-driven reports.