Docs & Writing

congdon1207 Bundle

---

congdon1207 Bundle

---

congdon1207 Bundle

---

aradotso-security-skills Skill

```markdown

aradotso-security-skills Skill

```markdown

aradotso-security-skills Skill

```markdown

aradotso-security-skills Skill

```markdown

hughdbrown Bundle

Nightly "dreaming" review of Claude Code sessions — read the last 24 hours of transcripts, compare them against auto-memory, and propose memory adds/updates/deletions as a numbered, evidence-quoted list. Use when the user types /dream or /dream apply, or when run unattended on a schedule (writes proposals to ~/.claude/dream-report.md).

ligenjian001-ai Bundle

生成个人日报/周报。自动搜集AG对话、Panel Discussion、Task Delegate数据，按项目分组总结，附AI改进建议和明日事项初稿。触发词：生成日报、daily report、今天做了什么、工作总结。

opendcai Bundle

Reference documentation for the RetrievalGenerator operator. [Purpose] Reads one text column from storage, forwards every non-empty row to `llm_serving.generate_from_input(...)`, and writes the returned list into a new output column. [Default backend] Use `LightRAGServing` by default. [Important] `run()` is async. The operator itself does not initialize the serving object; it only awaits `llm_serving.generate_from_input(llm_inputs, system_prompt)`.

opendcai Bundle

Reference documentation for the Text2QASampleEvaluator operator. Use when: evaluating QA pair quality across multiple dimensions.

opendcai Bundle

Reference documentation for the Text2MultiHopQAGenerator operator. [Purpose] Generates multi-hop QA pairs from one text column and writes two output columns: one for `qa_pairs` and one for metadata. [When to use] Use it when you want reasoning-style QA pairs derived from longer text chunks. If only simple single-hop QA is needed, use `Text2QAGenerator` instead.

renanfranca Bundle

Guide repository code changes through a self contained living ExecPlan, behavior focused quiet TDD, a green public checkpoint, post GREEN design review, documentation reconciliation, and final validation. Use when Codex is asked to plan, implement, execute, or continue a software code change and the repository instructions declare a complete workflow profile. Do not use for skill development, documentation only changes, or repositories without the required profile.

greenmamba29 Skill

| name | description | license | tags |

aradotso-security-skills Skill

```markdown

axidify Skill

Implements a scoped code change with inspect-report-verify discipline. Use when the user asks to implement, build, add, fix, or create something; or says /implement. Not for question-only, plan-only, or unexplained-failure debugging.

claude-ai-tools-ventura-county Skill

Convert a highly technical document or subject into a plain, accurate, layman-friendly explanation using Feynman-style teaching moves — everyday analogy, a first-principles ladder, jargon stripping, and honesty about the limits. Use this whenever the user wants to "explain this simply", "make this understandable to a non-technical audience", "translate this for stakeholders / execs / new hires / customers", "ELI5 this doc", "de-jargon this", give me the "plain-English version", "what does this actually mean", or hands over a dense technical doc, spec, paper, RFC, or codebase writeup and wants it made digestible — even if they don't say the word "Feynman". Produces a layered explanation (one-sentence core, then gist, then full plain walkthrough), a jargon-to-plain glossary bridge, analogies that each name where they break down, and a flagged list of anything the source left genuinely unclear. Do NOT use this to merely shorten a document that is already clear (that is a summary, not a translation), to write mar

claude-ai-tools-ventura-county Skill

Save the most recent substantive response — plus session metadata, recent test findings, and phase status — to a persistent, additive snapshot.md file so the user can re-find and resume the session later (next morning, after a crash, or across chat tabs). Trigger whenever the user says "snapshot", "snapshot this", "save this session", "save our progress", "save before I go to bed / sign off / wrap up", "checkpoint this", or expresses worry about losing work, losing the chat, or VS Code crashing. Also offer it proactively when a long working session reaches a natural stopping point with unsaved findings. Use only to preserve session progress — not when the user wants to save or export a specific artifact (a file, PDF, image, code snippet, or document).

kalabint Skill

Do not claim what you did not do or list what you might have missed; absence is not observable from the inside, so verify with an external check.

coolxeo Skill

Use this as the last mechanical pass before publishing, to screen AI tells and house-style misses that a slop word-list can skip.

erikuus Bundle

Analyze a proposed feature before implementation by combining one GitHub issue, one supplied Markdown documentation file, the current project's code, optional documentation-directed Chrome observation of a test UI, and—when visual validation is useful—an isolated disposable Sites prototype; conduct an evidence-led Estonian clarification conversation in the issue, maintain a weekday working-hours same-task monitor, establish explicit participant consensus, and hand a technical plan back to the invoking Codex task without implementing the real feature. Use only when the user explicitly invokes `$analyze-github-feature` with a GitHub issue URL and documentation path. Never invoke implicitly for ordinary feature requests.

igoingdown Bundle

macOS 上通过 IPP 协议向办公室网络打印机打印 PDF 并做真实出纸验证。当用户要连接网络打印机、打印 PDF/文件、打印失败排查（发出去了但没出纸/CUPS 显示 completed 但打印机没反应）、发现或验证办公室打印机 IP、检查打印机状态/能力时使用。实测于 Canon iR-ADV C5250，通用于支持 IPP Everywhere 的网络打印机。

igoingdown Bundle

按团队模板生成严格的面试评价报告。使用时：①用户直接贴飞书招聘候选人链接（feishu.cn/hire/talent/...）——交互式会话用 Chrome 集成、无人值守/launchd 固定用 AppleScript，先按 URL 精确定位标签页并跑前置探针判定本轮材料形态（简历是 PDF/图片附件/仅标准简历、面试速记是否就绪、有无「代码考核」卡片），再采集简历（三路：PDF 长图 / 图片附件直落 / 标准简历截图）+ 抽取面试速记文字记录到 ~/github/interviews/人名拼音/00N/，速记未就绪则跳过不写残缺评价；②用户提供候选人面试材料目录（简历截图 + 语音转文字）。按固定目录结构读取，只评估本轮材料，产出 Markdown 报告。**开工先按 asr.md 说话人分布判用户是主面还是旁听（shadow 陪面）——飞书 interviewer_list 只登记 shadow 者一人、判不出主面；旁听场候选人评价照常写满，面试官复盘改写成观摩笔记且不给用户打 A/B/C/D 档。** 报告包含两部分：候选人**六维**评价（业务理解/技术支撑/技术广度/技术深度/**编码与算法**/软素质；先记证据 P/N1/N2/U 再按优先级生成 `+`/`=`/`-`，有编码题先跑形态状态机 C0~C4；2/2.5/3/3+/3.5/4 六档评分按**决策表**顺序判定，核心维度 `-` 时 ≤2.5 且不因其他维度 `+` 上浮；3+ 及以上通过，3 为合格线边缘、默认倾向不通过但面试官可显式裁定通过；按目标岗位职级校准深度期望）+ 面试官复盘评价（**只能取 A/B/C/D 四档，禁止 A-/B+/B- 等未定义子档**，五维评估 + 改进建议）。打分前先过「证据充分性前置门」——因面试官时间不足/没安排/被打断而未取样的能力一律留空、不记减分项、不触发降档铁律（"没测到"≠"测到且失败"）。**evaluation.md 是对外交付物（会被整段贴进公司招聘系统），零过程性内容：不写版本标记、改判说明、评审过程、自我纠错、规则援引；改判留痕另写 review-log.md。**含 AI coding 题专项评估（看用 AI 的过程而非代码结果）与 AI 生成内容的原理归属校验；含传统算法/编程题专项评估（探针 coding=no 只代表无平台代码产物，仍须回速记扫编程题信号，屏幕共享/白板/

igoingdown Bundle

一个每周自动生成工作周报的定时 loop 的设计与参考实现。每周一读上周所有 Claude Code session，用 headless claude 归纳成分类周报云文档，链接自动归档进汇总索引，再推一条通知。适合想用「定时 + headless AI + 从自己的工作痕迹里自动写周报/月报/汇总」的人参考。触发词：自动周报、session 汇总、headless 定时生成文档、工作痕迹归纳、周报自动化、cron + claude -p 写文档。

clarentcinematics Bundle

Synthesize scattered weekly updates, project notes, metrics, risks, and team reports into a concise executive-ready weekly report. Use when Codex needs to prepare leadership updates, operating reviews, weekly business reviews, board-style summaries, or cross-functional status narratives.

clarentcinematics Bundle

Analyze support tickets, helpdesk exports, issue subjects, customer questions, or support thread summaries to find repeated themes, duplicate-looking requests, documentation gaps, automation candidates, and support-deflection opportunities. Use when Codex needs to convert support noise into prioritized KB, product, or workflow improvements without inventing customer facts.

format-technologies Bundle

Report on what made customers start looking for a solution like yours, over a period the user names — the moment something broke, the tool that hit a wall, the mandate from above, the peer who showed them, or nothing at all beyond an outbound call that landed. Reads voice-of-customer evidence in Format, ranks the trigger patterns by how many companies each reaches, segments them by what those buyers were trying to fix, and writes an authored Format report where every claim carries the customer's own words. Read-only except the single report it authors, left as a draft. Trigger phrases: "demand triggers report", "why did customers come to us", "what made people start looking", "what drives buying decisions", "why now", "what triggers demand", "why are prospects evaluating us", "what prompted them to look", "buying trigger analysis".

jimmyvgdy Bundle

技术方案、架构设计、实施方案、接口或数据库文档、部署手册、故障报告、代码审查报告、管理报告、README、Markdown 重构或基于现有资料整理正式文档时使用。仅更新 CHANGELOG、提交信息或代码注释通常不单独触发。

jimmyvgdy Bundle

Use for technical plans, architecture, implementation plans, API or database documentation, runbooks, incident reports, review reports, management reports, and README work.

anujkumar8076 Skill

Use when the user wants to create, merge, split, or extract text from PDF files.

anujkumar8076 Skill

Use when the user wants to create, edit, or format Word documents (.docx files).

anujkumar8076 Skill

Use when the user wants to create, merge, split, or extract text from PDF files, or prepare documents for printing.

anujkumar8076 Skill

Use when the user wants to create, edit, or format Word documents — reports, letters, contracts, or any .docx file.

anujkumar8076 Skill

Use when the user wants to create PowerPoint presentations or slide decks — pitches, talks, lectures, or slideshows.

yananlong Bundle

Assemble book-style PDFs from one or more source PDFs using CLI PDF tools. Use when Codex needs to collate PDFs in a specific order, drop repeated cover/JSTOR pages, add chapter/section bookmarks, rotate landscape pages to portrait, or optionally crop shared whitespace proportionally across pages.

yananlong Bundle

Pedantic, adversarial stress-testing of documents with claim-by-claim scrutiny, internal consistency checks, citation auditing, and up-to-date fact-checking. Use when asked to critique, peer-review, red-team, verify references, pressure-test time-sensitive statements, or assess whether validation, verification, independence, immutability, isolation, replay, auditability, or route-readiness claims are actually supported; default deliverable is a structured report in chat.