Docs & Writing

petar-djukic Bundle

Sweep anchor selections over a writing-voice corpus and report which tag query produces the best register outcome. Runs match-voice then tighten-style over (article × arm) combinations, ranks arms on the four-axis register composite, and optionally verifies the top candidates with an external detector. Triggers: tune anchors, sweep anchors, which anchors should I use, calibrate writing-voice, onboard corpus.

petar-djukic Bundle

Paragraph and sentence-level style metrics for a research corpus. Computes quantitative profiles (sentence/paragraph distributions, burstiness as coefficient of variation of sentence length, passive voice, hedging, word/phrase/idiom frequencies, per-section metrics), corpus aggregation, term over/underuse comparison, and a plagiarism similarity guard (n-gram shingling with baseline exclusion). Provides voice anchor retrieval from writing-voice exemplars via tf-idf. The section-level driver (compare, blueprint, rewrite) moved to match-outline. Triggers: style profile, quantitative metrics, sentence stats, frequency tables, plagiarism check, similarity check, voice anchors, corpus profile, word frequency, burstiness, sentence length variance.

dongzhigang13305312738-art Bundle

当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料，输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录，必须暂停并先要求其指定。⚠️ 不适用：用户只是想了解预算原则；用户仅要预算表数字而不写说明书；或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。

dongzhigang13305312738-art Bundle

根据 LaTeX 论文项目撰写、修订和润色 SCI 期刊论文，默认 AI 自主模式，也支持人机协作仅输出审查计划；提供作者风格化写作、数字事实核验、逻辑树多轮审查与 PDF/Word 渲染闭环。⚠️ 不适用：仅改格式/样式参数、纯参考文献管理、图片处理、非论文写作任务。

dongzhigang13305312738-art Bundle

当用户给出期刊/杂志名并希望了解投稿要求、投稿形式/格式清单、期刊官网信息、社区评价、审稿速度、费用、文章类型、格式细节或“这个 journal 怎么投/是否靠谱/投稿指南调研”时必须使用。联网核验期刊官网与社区评测，默认把全部中间文件隔离到当前工作目录的 `.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/paper-know-journal/`，最终只交付 `KnowJournal-{杂志名}.md`。⚠️ 不适用：用户要根据 manuscript 选择投稿期刊（用 paper-select-journal）、写论文正文、下载全文 PDF，或只问一个无需成稿的简单事实。

dongzhigang13305312738-art Bundle

解读论文 Figure 的含义并输出一份“教会人类如何读图”的高可读性 Markdown 报告；支持输入 1 个或多个 figure 文件绝对路径与人工解读，自动尝试从图附近检索生成该图的源代码，并采用类似 parallel-vibe 的方式通过 `codex exec`/`claude -p` 以进程级隔离解读每张图（并发上限默认 3，可在 config.yaml 调整）。⚠️ 不适用：用户只是想改图尺寸/裁剪/改格式；或要求直接修改图片/源代码（本 skill 对图片与源代码全程只读，严禁修改）。

dongzhigang13305312738-art Bundle

当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"、"运行 research-citation-check"，或要求使用旧名 check-review-alignment skill 时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合，只在发现致命性引用错误时对"包含引用的句子"做最小化改写，并优先复用 `research-literature-review` 的渲染脚本输出 PDF/Word，过渡期允许 fallback 到旧名 systematic-literature-review。核心原则：不为了改而改，无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用：用户只是想生成系统综述正文（应使用 research-literature-review）；用户只是想新增/核对 BibTeX 条目（应使用专门的 bib 管理流程）。

dongzhigang13305312738-art Bundle

当用户明确要求"从文件/图片/网页/描述中提取综述主题"、"生成主题+关键词+核心问题结构化输出"，或要求使用旧名 get-review-theme skill 时使用。支持文件（PDF/Word/Markdown/Tex）、文件夹、图片、自然语言描述、网页 URL 等多种输入源，自动识别输入类型并提取内容，生成可直接用于 research-literature-review 及其他文献综述技能的结构化输出。

ceilf6 Bundle

可配置地自动生成并创建个人或团队工作日报/周报。用于写日报、生成日报、今日工作总结、代码提交日报、学城日报、日报创建、本周总结、周报、weekly report 等场景；按 references/config.yaml 中的用户画像、学城目录和群通知配置，日报从学城最近编辑、dev.sankuai.com commit/PR、ONES、TT、日历和用户显式输入中采集当天工作，周报默认基于一周日报聚合工作线和趋势，并通过 citadel 创建、授权或通知。

ceilf6 Bundle

当需要分诊 GitHub issue、评估 issue 质量、分析 bug report 或 feature request 的完整性、清晰度和可执行性，或给报告者提供结构化反馈时使用。

ceilf6 Bundle

Use when exporting or migrating multiple KM/XueCheng/Citadel documents, especially parent directories, collabpage/page links, daily-report folders, or document lists that need local Markdown files for Notion, docs, archives, or downstream import. Trigger on 批量导出学城, 导出 KM 文档, 学城文章迁移, collabpage 批量, XueChengCopyPlugin, Notion migration from KM.

gupsammy Skill

This skill should be used when the user asks to "convert this page to markdown", "extract this webpage", "save this article", "grab content from URL", "get markdown from this link", "scrape this page", provides a URL to extract, or wants clean web content without ads and clutter.

lythos-labs Bundle

Human-first documentation writer and reviewer. Reviews README, wiki, ADR, daily handoff, showcase, and reference docs for information density, structural rhythm, and anti-template patterns. Ensures human readers get clear prose, not AI-flavored filler.

wachawo Bundle

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from a PDF, merging or combining multiple PDFs into one, splitting a PDF into parts, rotating pages, adding watermarks, creating new PDFs, filling out PDF forms, encrypting/decrypting PDFs, extracting images, and OCR-ing scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to create one, use this skill.

wachawo Skill

Walk the user through a structured collaborative documentation workflow. Use when the user wants to write documentation, proposals, technical specs, decision documents, or similar structured content. The workflow helps users transfer context efficiently, refine content iteratively, and verify the document works for its readers. Triggers when the user mentions writing documentation, drafting proposals, sketching specs, or similar documentation tasks.

guillaumelessard Skill

Teaching and documentation content for quantum error correction with QECTOR: beginner-to-advanced tutorials, ELI5 explanations of syndromes / decoders / parity checks, Tanner-graph visual explanations, and local Markdown teaching material. Load for explanations, course material, or documentation generation.

guillaumelessard Skill

Logical error rate (LER) methodology for QECTOR. Covers the Wilson 95% score interval, the chapter 22.3 required-artifact metadata block, the code_capacity / circuit_level tagging rule, safe / unsafe wording, and the screening-estimate caveat. Load for any LER report, threshold sweep, or competitive comparison.

a-v-ershov Skill

Produce a project's initial documentation end to end, from a raw idea to a buildable spec. Use when starting a new project or a major new initiative and you want the full guided flow rather than running each step by hand. Orchestrates gather-context, validate-idea, define-product-requirements, create-user-flows, define-design-decisions, design-architecture, define-code-style and design-dev-architecture — each phase researching real-world facts within a fixed budget, running an adversarial review whose findings it applies in place, and emitting a research doc plus a short human summary. Works on an empty repo or one that already has code.

ainova-systems Bundle

Scaffolds the in-repo docs substrate for spec-driven work and migrates existing documentation into it. Runs once, before the first spec.

alawein Skill

Use when you want to drive an artifact to clean, where clean means zero blockers and zero majors after a full check run. Fix and re-run until clean or a round cap, then report honestly, confirmed minors included. A fix-until-clean loop over lint, tests, review, and scrutiny.

alawein Skill

Use when writing a named coding artifact (a README, a findings note, a report) in the house voice from a supplied template. Produces a findings-first document with the right structure for its kind, plain words, and no padding.

camunda Bundle

Generate a health report for scheduled GitHub Actions workflows in this monorepo. Use when asked about scheduled workflow health, nightly build failures, flaky CI, or workflow ownership.

mqmalagris Bundle

Maintain a canonical master CV in Markdown and produce tailored, ATS-friendly resumes and recruiter-screen prep packs from job descriptions. Supports four modes — bootstrap (build master from scratch via interview), sync (import existing resume in any format into master, with optional standalone rewrite output), tailor (generate CV matched to a JD), and screen-prep (draft answers for first recruiter-call questions). Use when the user asks to update their CV/resume, rewrite an existing CV, tailor a resume to a job posting, prepare for a recruiter screen, import a resume PDF/docx into Markdown, or runs /cv-craft.

mqmalagris Bundle

Babysit a GitHub PR from review all the way to MERGED. Fetches all feedback (human + bot reviews like Copilot/Qodo/CodeRabbit, inline review threads, top-level reviews, issue comments, and CI check status), triages each item for validity, fixes the valid ones, posts a per-item fix report referencing the commit, resolves the addressed threads, then self-schedules the next pass (its own loop, no /loop prefix needed) and keeps going until the PR is merged. Use when the user says "babysit this PR", "watch the PR", "address the PR feedback", "keep checking the PR until it's merged/good", "handle the review comments", or runs /babysit-prs. Stack-agnostic — any gh-based repo, any language.

mqmalagris Bundle

Generate a work report tunable to audience (dev / pm / client) and deliver it as a copy-ready channel block or a written doc. Two modes: `quick` (git-only, zero-config — prose + bullets from the current repo) and `standup` (multi-source — GitHub PRs/reviews/comments + git across repos + deploys + optional tracker, framed as an impact narrative). Use when the user asks for a standup, status update, work summary, "what did I ship today", commit recap, end-of-day report, PM/client update, a report to paste into a channel, or a standup doc — or runs /commit-report. Triggers on "write a report", "summarize commits", "standup", "report for the PM", "update for the client", "send a report", "what did I do today/yesterday". Default delivery is a copy-ready block; `--doc` writes the full report to a file; `--metrics` appends flow metrics (human review coverage, rework depth, artifact lag, spec churn, caught-vs-escaped defects, recurring fix classes) derived from git and gh. Quick mode default scope = `--since-mine` (c

mqmalagris Bundle

Sync the current project into a central project-portfolio Markdown archive — a comprehensive log of every project the user has worked on (stack, role, scope). Path-agnostic: the user picks where the archive lives, the skill remembers it. Gathers project signals (git log, manifests, README, structure), matches existing entries by folder name, proposes add/amend for user confirmation before writing. Use when user asks to update their portfolio, log a project, sync the archive, document the current project, or runs /portfolio-sync. Distinct from cv-craft (which produces actual CVs from this archive as source).

puukis Skill

Writes accurate documentation by reading source first — never invents API signatures

kovrichard Bundle

Convert markdown files into a styled PDF. Use when creating a PDF from existing markdown files, combining markdown into a report, or converting .md to .pdf.

kovrichard Bundle

Download and analyze PDF files from URLs or local paths — extract text, answer questions, summarize content. Use when analyzing, reading, or extracting information from a PDF.

miketromba Skill

Bun JavaScript runtime, bundler, package manager, and test runner documentation and guidance. Use when working with Bun - an all-in-one toolkit for developing JavaScript/TypeScript applications. Triggers on questions about Bun runtime, bun install, bun test, bun build, Bun.serve, Bun.file, Bun.spawn, bunfig.toml, Bun APIs, SQLite, S3, Redis, WebSockets, HTTP server, bundler configuration, hot reloading, macros, plugins, or ANY Bun-related development tasks.

miketromba Skill

Drizzle ORM TypeScript documentation and guidance. Use when working with Drizzle - a lightweight, type-safe TypeScript ORM for PostgreSQL, MySQL, SQLite, SingleStore, and MSSQL. Triggers on questions about Drizzle schema, migrations, drizzle-kit, queries, relations, joins, transactions, RLS, column types, database connections, or ANY Drizzle-related development tasks.

miketromba Skill

Supabase backend-as-a-service platform documentation and guidance. Use when working with Supabase - an open-source Firebase alternative providing Postgres database, authentication, real-time subscriptions, edge functions, storage, and vector embeddings. Triggers on questions about Supabase setup, database, auth, RLS, edge functions, storage, realtime, pgvector, migrations, CLI, self-hosting, or ANY Supabase-related development tasks.

miketromba Skill

isolated-vm documentation and guidance for secure JavaScript isolation using v8 Isolates in Node.js. Use when working with isolated-vm - a native Node.js module providing access to v8's Isolate interface for running JavaScript in completely isolated environments with memory limits. Triggers on questions about isolated-vm, ivm.Isolate, v8 isolates, sandboxed JS execution in Node.js, cross-isolate references, ExternalCopy, Reference, Context, evalClosure, compileModule, or ANY isolated-vm-related development tasks.

miketromba Skill

Look up and use Sprites (sprites.dev) documentation for persistent, hardware-isolated execution environments by Fly.io. Use when the user mentions sprites, sprites.dev, Sprites CLI, sprite commands, sandboxed code execution with Sprites, or microVM environments.

miketromba Skill

Vercel Sandbox documentation and guidance for running untrusted code in isolated environments. Use when working with Vercel Sandbox - a compute primitive for safely executing AI-generated code, user-submitted scripts, or developer experiments in Firecracker microVMs. Triggers on questions about Vercel Sandbox SDK, sandbox CLI, @vercel/sandbox, Sandbox.create, snapshots, persistent sandboxes, sandbox authentication, sandbox pricing, sandbox system specs, microVMs, code execution isolation, or ANY Vercel Sandbox-related development tasks.

miketromba Skill

QuickJS WebAssembly sandbox documentation and guidance for executing JavaScript/TypeScript securely. Use when working with @sebastianwessel/quickjs - a TypeScript package for running untrusted JS/TS code in an isolated QuickJS WebAssembly runtime. Triggers on questions about QuickJS sandbox, @sebastianwessel/quickjs, loadQuickJs, runSandboxed, evalCode, sandbox options, virtual file system, sandboxed fetch, custom modules in QuickJS, AI code execution in WASM, or ANY QuickJS sandbox-related development tasks.