Docs & Writing

everyinc Skill

Revise prose at the sentence and word level while preserving voice, meaning, source accuracy, and useful weirdness. Use when the structure is stable and the user asks for a line edit, polish, tightening pass, or usable rewrite.

getnao Skill

Detect user-facing features in recently merged PRs and open a PR in the docs repo adding the missing documentation.

getnao Skill

Customer Report (360)

handoffacademy Skill

Designs and guides buildout of the home base of the member's AI hub — their Notion workspace by default, or the tool they chose instead. It covers the page structure, the databases or files a beginner actually needs, the private destination each scheduled task writes into, the dashboards, and the conventions that make something findable later. Use it whenever someone wants their hub, workspace, or home base designed or built out, in Notion or in whatever they use in its place. Verifies what that tool's connection can currently do against its own documentation inside the session, establishes every parent's privacy from evidence before creating anything, and builds only with the member watching.

handoffacademy Skill

Turns the owner's plain-language corrections about an output into concrete, durable settings in their Task Settings file, and narrows where an action applies or switches it off, always showing the exact before and after. Use whenever the owner says a brief is too long, the wrong things are being flagged, drafts sound wrong, an action is reaching mail it should leave alone, or anything in the daily brief, the follow-through queue, or the upkeep report should be different from now on.

handoffacademy Bundle

Interviews a non-technical business owner about one repetitive task and designs a single safe Scheduled Task that reads bounded information and prepares a private review. Verifies every capability against the tools actually visible and against current official documentation instead of memory.

handoffacademy Bundle

Read and report Inbox Assistant connections, action controls, scheduled work, run history, and outstanding problems without changing anything. Use when the user types /inbox-assistant:status, asks whether Inbox Assistant is working, or wants to verify a migration between Claude, ChatGPT, or Codex.

handoffacademy Skill

Explains Zapier limits, cost tradeoffs, and safer alternatives in plain language, always verifying current pricing, task usage, and per-app rules against live Zapier and third-party documentation instead of memory.

handoffacademy Skill

Works out Zapier limits, cost, and safer alternatives before scheduling an Automation Builder task, always verifying current pricing, task usage, and per-app rules against live Zapier and third-party documentation instead of memory. Use this as the cost step of an Automation Architect design, not as general Zapier account support.

jovd83 Bundle

Coverage-maintenance skill for Cypress planning and documentation. Use when Codex needs to synchronize coverage plans, scenario IDs, traceability links, and summary counts after tests, requirements, or narrative test documents change.

jovd83 Bundle

Failure-analysis skill for Cypress runs. Use when Codex needs to investigate a failing test, distinguish likely product bugs from test issues, and produce a concise developer-focused root-cause report backed by evidence.

jovd83 Bundle

Use when you need the legacy Cypress session-state entrypoint path; record session state in the canonical Cypress handover workflow.

jovd83 Bundle

Legacy Cypress-specific alias for BDD case formatting. Prefer the standalone `test-artifact-export-skill` skill for Gherkin, BDD, and export-ready case rendering, and use this only when Cypress-local conventions must be preserved explicitly.

jovd83 Bundle

Legacy Cypress-specific alias for TDD-style case documentation. Prefer the standalone `test-artifact-export-skill` skill for formatting approved test cases or building export-ready artifacts, and use this only when Cypress-local conventions must be preserved explicitly.

jovd83 Bundle

Legacy Cypress-specific alias for plain-text case formatting. Prefer the standalone `test-artifact-export-skill` skill for lightweight narrative case output, and use this only when Cypress-local conventions must be preserved explicitly.

karim-bhalwani Bundle

Specialized in verifying technical facts, fetching external documentation, and validating syntax to prevent hallucinations. Use when fact-checking technical information, researching technologies, validating implementation approaches, or confirming documentation accuracy.

karim-bhalwani Bundle

Explore user intent, requirements, and design before implementation. Use when turning ideas into designs, validating requirements through dialogue, exploring multiple approaches, or creating design documentation for features, components, and functionality changes.

karim-bhalwani Bundle

Initialize project infrastructure, generate context files, and maintain the Single Source of Truth. Use when setting up new projects, auditing project environments, generating context documentation, maintaining project memory, or ensuring consistency across the codebase.

konradcinkusz Bundle

Use when a repository produces measurements, benchmarks or experiments that need writing up as research rather than as a guide, or when any document in it has to be authored in LaTeX and compiled to PDF. What counts as research and what does not, the docs/research layout, the shape of a study document, the evidence rules (every number traceable, reproduction stated as a command, validate the instrument before trusting its readings, negative results get written up), when a study graduates to a LaTeX paper or a Beamer deck, how a non-study document borrows the house style without claiming to be research, how Mermaid diagrams reach a PDF from a single source, how a second language edition is published, and the shape of the GitHub Actions workflow that builds any of them. Bundled assets: the study template, the paper template and the Beamer theme.

ldm2060 Bundle

Use when the user asks to de-AI English LaTeX prose, humanize it, or remove the mechanical / chat-bot patterns. Triggers on: "去AI味", "de-AI", "remove AI patterns", "humanize", "去机械化". Rewrites at the same word count — does not add or delete content. Do NOT use for translation, expansion, or shortening — those have their own skills.

ldm2060 Bundle

Use when the user wants a top-conference reviewer perspective on paper quality, with a severe-but-constructive tone. Triggers on: "审稿", "review", "reviewer", "peer review", "评审". Outputs a review report + strategic author advice. Do NOT use for pre-submission sanity check (paper-sanity-check) or polish (paper-polish).

ldm2060 Bundle

Use when the user asks to '审一下这篇 PDF', '自动审稿', '给我 review', or wants a manuscript / PDF reviewed in Copilot with structured feedback. Triggers on: 'review this manuscript', 'auto-review'. Copilot-native — no workspace review script call.

ldm2060 Bundle

Use when the user asks to '开始写论文', '生成 PDF', '整理成论文', or wants LaTeX / Markdown drafted directly in Copilot from experiment artifacts. Triggers on: 'write the paper', 'generate PDF', 'compile to paper'. Copilot-native — no workspace writeup script call. Do NOT use for review (scientist-review) or plotting (scientist-plotting).

ldm2060 Bundle

Use when the user has a workshop / topic Markdown and wants it turned into an AI-Scientist-format ideas JSON, generated directly in Copilot. Triggers on: '生成 ideas', 'topic 变成想法', 'AI Scientist 出点子', 'generate ideas from topic'. Copilot-native — no workspace ideation script call.

mikechongcan Skill

Launch the Fava web UI for visual exploration of your Beancount ledger. Interactive charts, account views, queries, and reports in the browser. Use when you want to visually explore your financial data. CLEAR step: R (Report)

mikechongcan Skill

Generate financial statements: Income Statement (P&L), Balance Sheet, Cash Flow. Custom queries via BQL. Trend analysis and period comparisons. Use to see your financial picture clearly. CLEAR step: R (Report)

mikechongcan Skill

Financial health assessment, FIRE planning, net worth tracking, and scenario modeling. Use when you want the big picture of your financial life. CLEAR step: R (Report)

hoangsonww Skill

Emit a Markdown weekly digest of briefing quality scores (coverage, composite stats, axis medians, per-day table). Use when the user asks for a "weekly report", "eval summary", or "quality digest" for a specific date range.

cai-aa Bundle

Evidence-first LAMMPS molecular-dynamics workflow for input decks, potentials, minimization, equilibration, deformation, thermo logs, trajectories, restart/data files, stress-strain extraction, and reproducibility checks. Use when Codex must prepare, run, diagnose, or report a LAMMPS materials simulation or hand its trajectory to OVITO without overstating nanoscale demo results as calibrated macroscopic properties.

j5ik2o Bundle

references/taktサブモジュール更新時に、takt-*スキル群（takt-task-builder, takt-workflow-builder, takt-facet-builder, takt-analyzer, takt-optimizer）を最新のtaktバージョンに追従させるスキル。 TypeScriptスキーマ（taskRecordSchemas.ts / taskExecutionSchemas.ts）、ワークフローYAML、ファセットMarkdownの差分を検出し、 SKILL.md・参照ドキュメント（task-schema.md等）を体系的に更新する。 トリガー：「taktスキルを更新」「takt-*スキルの鮮度チェック」「taktバージョンアップ対応」 「スキルが古くないか確認」「takt skill updater」

spec-kitty Bundle

Open or report the Spec Kitty dashboard. Use for dashboard URL, localhost daemon metadata in .kittify/.dashboard, --open, --kill, or status views.

allura-ecosystem Skill

Carlos Guidelines documentation discipline. Six required docs (BLUEPRINT, SOLUTION-ARCHITECTURE, DESIGN-*, REQUIREMENTS-MATRIX, RISKS-AND-DECISIONS, DATA-DICTIONARY) with AI disclosure, B#/F# traceability, and cross-references. Load BEFORE writing any code in the Mortgate project.

carlitose Bundle

Diagnose one bug by reproducing it, testing hypotheses, locating the root cause, and returning an evidence-backed diagnosis report. Use when the user wants root-cause analysis before implementation, or when triangulate-diagnosis delegates an independent diagnostic pass.

carlitose Bundle

Research a factual, codebase, product, or external-documentation question using primary sources and return an evidence-backed answer. Use when the user asks to investigate, compare docs, find current behavior, answer a research ticket, or gather facts before a spec, prototype, or implementation.

vahagn-madatyan Bundle

Cisco IOS-XE device health check and triage procedure. Use when troubleshooting Cisco IOS-XE routers or switches, checking CPU utilization, memory usage, interface error counters, routing table health, or performing rapid device triage during an outage. Covers show commands, threshold interpretation, escalation decision trees, and structured report output for handoff.

edloidas Bundle

Attack a code change and report what survives. Dispatches independent reviewers in parallel, each with a single job and no access to the implementer's reasoning: one hunts correctness bugs blind to the issue, one hunts requirement gaps against the issue text, one runs outside the process entirely. Optionally re-attacks its own findings, then synthesizes what is left. Returns findings and changes nothing — no tooling, no autofix, no edits. On request it publishes to the author, gated on demonstrated evidence. Every phase is configurable.