Docs & Writing
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
-
adambbhe Bundle Skill 16用于反身性与预期泡沫识别,聚焦市场行为、预期管理、风险识别、高阶交易研究。本skill主要用于用户问题回答、撰写报告、撰写金融类文章等场景。本报告输出内容较多,不适合简单对话场景。用户想判断一个热门板块或热门个股是否已经进入预期自我强化的泡沫阶段,什么时候从基本面交易转向预期交易,再转向兑现与反噬。使用TDX技能组合(tdx-financials、tdx-trading-info、tdx-dragon-tiger、tdx-hot-topic、tdx-board-valuation、tdx-report-rating、tdx-main-position、tdx-company-info、tdx-shareholder-research、tdx-industry-chain、tdx-stock-events、tdx-board-cpbd、tdx_kline、tdx_quotes、tdx_api_data(entry="tdxf10_gg_rdtc", fixedTag="sjcd")、tdx_api_data(entry="tdxf10_gg_ybpj", fixedTag="yzyq")、tdx_api_data(entry="tdxf10_gg_ybpj", fixedTag="yjyg")等),可自动获取分析所需的全维度数据。[已切换为 F10 替代方案:Wenda 接口需要独立浏览器登录 Session,当前使用 F10 数据作为替代方案(覆盖 80% 功能)]
-
adambbhe Bundle Tdx Report Rating---
-
randommonicle Skill Trace One RecordBefore combining two figures into a derived total, or asserting that one set of amounts sits outside another, trace a single record end to end through both sources to establish what each actually contains. Triggers on any total owed, due, outstanding, exposed or net; on adding, subtracting or netting figures from different reports, systems or dates; on the phrases "sits outside", "excludes", "in addition to", "the two therefore add"; and on any reconciliation between two sources. Does not fire on arithmetic within a single report, on a figure quoted from one source with no combination, or on citations of files and commits in prose, which belong to verified-citations.
-
randommonicle Skill Verify The EffectPlaybook for the always-on norm "never report success from a proxy signal — assert the actual effect or artifact". Load when a status signal (green CI step, HTTP 200, "accepted", exit 0, progress bar) is about to be read as success, when a step's entire output is a side effect, or when routed here from the one-real-ride done gate. Does not fire on test-suite results (prove-it-can-fail) or on declaring a whole feature done (one-real-ride owns that moment).
-
tuanloc1105 Bundle PlanPlan-first collaboration workflow for Codex. Creates one dated, daily-sequenced version 4 Markdown plan bundle under ./plans/, keeps it active through approval and execute handoff, and stores every declared phase in its own self-contained, stable-ID Markdown file under phases/. Use for reviewed implementation planning and durable cross-session handoff.
-
tuanloc1105 Bundle DiscussUse when the user invokes $discuss or requests discussion work with a persistent version 4 Markdown record bundle. Start a new dated, daily-sequenced bundle by default, even when an older bundle is supplied; reuse an older bundle only when the user explicitly asks to continue it. Keep discuss active across scoped actions and exit only through $plan or $execute.
-
tuanloc1105 Bundle ExecutePersistent execution and evidence-tracking mode for an approved version 4 Markdown record bundle produced by $plan or execution-ready $discuss. Keep the exact bundle active, execute dependency-ready phase files, update evidence and verification transactionally, and remain active until explicit exit.
-
tuanloc1105 Bundle Plan 2Plan-first collaboration workflow for Antigravity. Creates one dated, daily-sequenced version 4 Markdown plan bundle under ./plans/, keeps it active through approval and execute handoff, and stores every declared phase in its own self-contained, stable-ID Markdown file under phases/. Use for reviewed implementation planning and durable cross-session handoff.
-
tuanloc1105 Bundle Kiro PlanPlan-first collaboration workflow for Kiro / Kiro Crew. Creates one dated, daily-sequenced version 4 Markdown plan bundle under ./plans/, keeps it active through approval and execute handoff, and stores every declared phase in its own self-contained, stable-ID Markdown file under phases/. Use for reviewed implementation planning and durable cross-session handoff. Kiro port of the Codex `plan` skill.
-
tuanloc1105 Bundle Discuss 2Use when the user invokes $discuss, /discuss, or requests discussion work with a persistent version 4 Markdown record bundle. Start a new dated, daily-sequenced bundle by default, even when an older bundle is supplied; reuse an older bundle only when the user explicitly asks to continue it. Keep discuss active across scoped actions and exit only through plan or execute.
-
tuanloc1105 Bundle Execute 2Persistent execution and evidence-tracking mode for an approved version 4 Markdown record bundle produced by plan or execution-ready discuss. Keep the exact bundle active, execute dependency-ready phase files, update evidence and verification transactionally, and remain active until explicit exit.
-
tuanloc1105 Bundle Plan 3Plan-first collaboration workflow for Claude Code. Creates one dated, daily-sequenced version 4 Markdown plan bundle under ./plans/, keeps it active through approval and execute handoff, and stores every declared phase in its own self-contained, stable-ID Markdown file under phases/. Use for reviewed implementation planning and durable cross-session handoff.
-
tuanloc1105 Bundle Kiro DiscussUse when the user invokes $discuss or requests discussion work with a persistent version 4 Markdown record bundle. Start a new dated, daily-sequenced bundle by default, even when an older bundle is supplied; reuse an older bundle only when the user explicitly asks to continue it. Keep discuss active across scoped actions and exit only through $plan or $execute. Kiro / Kiro Crew port of the Codex `discuss` skill.
-
tuanloc1105 Bundle Kiro ExecutePersistent execution and evidence-tracking mode for an approved version 4 Markdown record bundle produced by $plan or execution-ready $discuss. Keep the exact bundle active, execute dependency-ready phase files, update evidence and verification transactionally, and remain active until explicit exit. Kiro port of the Codex `execute` skill.
-
tuanloc1105 Bundle Discuss 3Use when the user invokes /discuss or requests discussion work with a persistent version 4 Markdown record bundle. Start a new dated, daily-sequenced bundle by default, even when an older bundle is supplied; reuse an older bundle only when the user explicitly asks to continue it. Keep discuss active across scoped actions and exit only through /plan or /execute.
-
tuanloc1105 Bundle Execute 3Persistent execution and evidence-tracking mode for an approved version 4 Markdown record bundle produced by /plan or execution-ready /discuss. Keep the exact bundle active, execute dependency-ready phase files, update evidence and verification transactionally, and remain active until explicit exit.
-
cklxx Bundle Deep ResearchWhen a topic needs thorough investigation from multiple sources → multi-source search + evidence assembly + structured report.
-
cklxx Bundle Memory SearchWhen you need to recall past conversation context → search and read conversation memories (stored as Markdown).
-
vinvcn Bundle Research对照高可信一手来源调研问题,并把发现保存为仓库中的 Markdown 文件。适用于用户想调研主题、收集文档或 API 事实,或把阅读工作委托给后台代理时。
-
weirdgme Bundle Documentation As CodeDocumentation as Code
-
stbenjam Bundle LmkSpawn a subagent to perform the research task, then report back with the answer.
-
ayoubben18 Skill Ab Update ArchitectureRefresh architecture and domain documentation after impactful changes. Use when code has drifted from the documented architecture.
-
agentic-engineering-agency Bundle Specsafe QAFull QA validation with report generation and GO/NO-GO recommendation. Validates all requirements and scenarios.
-
nwave-ai Skill Nw Bdd Methodology 2BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation
-
ishandutta2007 Bundle DocumentationSkill: Technical Documentation
-
malue-ai Skill Nano PDFEdit PDFs with natural-language instructions using the nano-pdf CLI.
-
dhofheinz Bundle ArchitectComprehensive system architecture design, review, and documentation with ADR creation
-
dhofheinz Bundle Documentation ValidationValidate documentation completeness, format, and quality for plugins and marketplaces
-
hivellm Skill DocsGenerate or update project documentation based on recent changes
-
wirasm Skill Prp Debug 3Diagnoses a bug, error, stack trace, regression, or unexplained behavior and publishes the evidence-backed root cause to GitHub. Use when the user says "debug this", "find the root cause", provides a bug report or stack trace, asks to investigate a GitHub issue, or invokes /prp-debug. Defaults to commenting on the matching open issue or creating one when none exists.
-
wirasm Bundle Prp Implement 3Implements and validates existing PRP plans and corrects reviewed or failing-CI pull requests. Always use when executing an implementation plan, implementing an issue that already has a local or published plan, correcting a PR from a PRP review report or CI failure, when another PRP workflow reaches its implementation or correction step, or when the user invokes /prp-implement.
-
wirasm Bundle Prp Technical Writing 3Writes and edits developer documentation that is easy to act on and hard to misread. Use when writing or reviewing a README, RFC, tutorial, how-to guide, reference document, or technical explanation, when the operator says "write the docs", "improve this README", "edit this RFC", or invokes /prp-technical-writing.
-
clawbio Bundle DnaspFull reimplementation of DnaSP 6 for population genetics analysis of aligned DNA sequences. Covers nucleotide diversity, haplotype statistics, neutrality tests (Tajima's D, Fu & Li's D*/F*, R2), linkage disequilibrium (D, D', R², ZnS, Za, ZZ), minimum recombination (Rm), mismatch distribution, InDel polymorphism, between-population divergence (Dxy, Da, fixed/shared sites), outgroup-based Fu & Li D/F tests (fuliout), the HKA multi-locus neutrality test (hka), the McDonald-Kreitman test (mk), Ka/Ks (dN/dS) via the Nei-Gojobori (1986) method (kaks), Fu's Fs test (fufs), the site frequency spectrum (sfs, folded and outgroup-unfolded), transition/transversion ratio (tstv), and codon usage bias - RSCU (Sharp & Li 1987) and ENC (Wright 1990) (codon). Accepts FASTA or NEXUS input; outputs DnaSP-compatible TSV and a Markdown report.
-
thewatcher01 Bundle PDFUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
-
thewatcher01 Skill Doc CoauthoringGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
-
congdon1207 Skill Tasks Spec UpdateUse when updating specifications, comparing branches, or ensuring documentation reflects current implementation.
Frequently asked questions
What are Docs & Writing agent skills?
Docs & writing agent skills turn AI agents into dependable technical writers: READMEs, API references, PDFs and Word documents, changelogs, and style-guide enforcement. Install one and your agent produces the same structure and tone every time it writes.
Which Docs & Writing skills are most installed?
Popular Docs & Writing skills on SkillMD right now include 反身性与泡沫识别, tdx-report-rating, trace-one-record. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Docs & Writing skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.