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
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/obsidian-markdown Skill
2★ repoCreate and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/odoo-l10n-compliance Skill
2★ repoCountry-specific Odoo localization: tax configuration, e-invoicing (CFDI, FatturaPA, SAF-T), fiscal reporting, and country chart of accounts setup.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/openapi-spec-generation Skill
2★ repoGenerate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/plan-writing Skill
2★ repoStructured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/playwright-java Skill
2★ repoScaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Object Model, JUnit 5, Allure reporting, and parallel execution.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/postmortem-writing Skill
2★ repoComprehensive guide to writing effective, blameless postmortems that drive organizational learning and prevent incident recurrence.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/pr-writer Skill
2★ repoCreate pull requests following Sentry's engineering practices.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/professional-proofreader Skill
2★ repoUse when a user asks to "proofread", "review and correct", "fix grammar", "improve readability while keeping my voice", and to proofread a document file and save an updated version.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/readme Skill
2★ repoYou are an expert technical writer creating comprehensive project documentation. Your goal is to write a README.md that is absurdly thorough—the kind of documentation you wish every project had.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/scientific-writing Skill
2★ repoThis is the core skill for the deep research and writing tool—combining AI-driven deep research with well-formatted written outputs. Every document produced is backed by comprehensive literature search and verified citations through the research-lookup skill.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/seo-aeo-blog-writer Skill
2★ repoWrites long-form blog posts with TL;DR block, definition sentence, comparison table, and 5-question FAQ for SEO ranking and AEO citation. Activate when the user wants to write a blog post, article, or long-form content piece.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/seo-aeo-landing-page-writer Skill
2★ repoWrites complete, structured landing pages optimized for SEO ranking, AEO citation, and visitor conversion. Activate when the user wants to write or generate a landing page for a product, service, or offer.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/seo-content-writer Skill
2★ repoWrites SEO-optimized content based on provided keywords and topic briefs. Creates engaging, comprehensive content following best practices. Use PROACTIVELY for content creation tasks.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/skill-writer Skill
2★ repoCreate and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/social-post-writer-seo Skill
2★ repoSocial Media Strategist and Content Writer. Creates clear, engaging social media posts for Instagram, LinkedIn, and Facebook.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/tutorial-engineer Skill
2★ repoCreates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/website-copy-routing Skill
2★ repoUse when the user wants copy, messaging, structure, or content for a homepage, landing page, service page, sales page, about page, location page, or core website page, even if they do not explicitly mention StoryBrand. Also use when the user says "write this page," "rewrite this homepage," "landing page copy," "service page copy," "website messaging," "hero section," "above the fold," "headline and CTA," "page outline," "page structure," "website content," or "sales page." This skill routes website-page writing toward StoryBrand-first messaging, product marketing context, UX strategy, local SEO when relevant, and SEO-aware page structure.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/wiki-changelog Skill
2★ repoGenerate structured changelogs from git history. Use when user asks \"what changed recently\", \"generate a changelog\", \"summarize commits\" or user wants to understand recent development activity.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/wiki-page-writer Skill
2★ repoYou are a senior documentation engineer that generates comprehensive technical documentation pages with evidence-based depth.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/writer Skill
2★ repoDocument creation, format conversion (ODT/DOCX/PDF), mail merge, and automation with LibreOffice Writer.
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/writing-plans Skill
2★ repoUse when you have a spec or requirements for a multi-step task, before touching code
newmindsgroup/ai-agent-skills-library/sources/sickn33-antigravity-awesome-skills/skills/writing-skills Skill
2★ repoUse when creating, updating, or improving agent skills.
almasumdev/awesome-ios-agent-skills/.github/skills/ui/ios-localization Skill
no license2★ repoExpert guidance on iOS localization — String Catalogs (.xcstrings), ICU plurals and genders, right-to-left layout, and dynamic locale switching. Use when adding or auditing translated content.
gokulb20/crewm8-cfo-skills/skills/reporting-compliance/board-reporting Skill
2★ repoPrepares board meeting materials including executive summary, financial review, KPI dashboards, variance analysis, strategic commentary, and action tracking. Use when the user mentions board deck preparation, board meeting materials, financial review for the board, or asks about what to present to the board.
fnord123/hermes-skills/google-docs Skill
2★ repoCreate, read, and edit Google Docs documents — write a new document, read one back, add or insert text, find-and-replace, format text (bold/italic/underline or headings), or remove text. Works through a pre-configured service account; new documents land in the agent's shared Drive folder, and existing documents are reachable once shared with the agent. PREFER THIS SKILL for anything about a Google Doc / document's contents. It is a different, self-contained setup from `google-workspace` (which is OAuth-based) — reach for this one for Docs. Finds documents by name or content, so the user never needs a document ID or URL. Activate on any of: "google doc", "doc", "document", "write a doc", "create a document", "add to the doc", "insert into the document", "edit the doc", "find and replace in the doc", "make this a heading", "bold this in the doc", "read the doc", "what does the document say", "find my doc", "search my docs", "which docs do I have", "it's in my docs".
Investment hypothesis investigation
fnord123/hermes-skills/investment-hypothesis-investigation Skill
2★ repoInvestigate a high-level investment hypothesis through structured, adversarial research. Use when the user states a thesis or claim they want stress-tested - e.g., the strait of Hormuz staying closed longer than expected, transformer makers undervalued vs hyperscalers, AI capex plateauing in 2027, antitrust breaking up Big Tech. Also activate for: test this thesis, research this hypothesis, is this view priced in, what's the edge here, build a case for or against, or any user statement of a directional investing view they want validated against current evidence and consensus. Produces a single living markdown report with linked endnote citations, saved to ~/.hermes/reports/research/.
olzn/skills/skills/handoff Skill
2★ repoCompact the current conversation into a handoff document another session or agent can resume from. Use when wrapping up with unfinished work, when context is getting long, or when the user says "hand this off", "write a handoff", or "save state for the next session". Produces a single Markdown file at a durable, harness-agnostic path and reports it. Does NOT continue the work itself; it only captures state so a fresh session can.
olzn/skills/suites/ui-craft/surface/surface-copy Skill
2★ repoWrite and review interface copy that guides, explains, reassures, or persuades. Use when drafting or improving error message bodies, empty states, helper text, onboarding text, tooltip prose, loading text, success or warning messages, confirmation body copy, and marketing-style CTA copy. Also triggers for UX writing, microcopy, tone, localisation notes, or "this copy feels unclear". Does NOT own product action labels, command names, menu items, feature names, product names, component names, token names, or UI terminology (use system-naming). Does NOT decide placement or flow structure (use system-patterns), component state coverage (use system-components), or accessibility mechanics (use surface-details).
IrfanSadiqRahat/constellation/agents/decision-doc-writer Skill
no license2★ repoDecision docs with options, pros/cons, recommendation, dissent, owner.
IrfanSadiqRahat/constellation/agents/docs-architect Skill
no license2★ repoDiataxis layout, IA, contribution model, doc-as-code.
IrfanSadiqRahat/constellation/agents/prd-writer Skill
no license2★ repoWrite a complete, decision-ready PRD. Activate after Requirements exist. Produces the source-of-truth document for everyone downstream.
IrfanSadiqRahat/constellation/agents/runbook-writer Skill
no license2★ repoStepwise diagnostics with copy-paste safe commands and rollback paths.
grimaldost/craft-collection/plugins/experiment-discipline/skills/experiment-rigor Skill
2★ repoStructure an experiment and its write-up so the Methods reconstruct without the conversation and the uncertainty is declared, not hidden — a typed record.yaml across a probe / measurement / decision tier ladder, every load-bearing rule a script that exits non-zero rather than a line of prose. Use when you pre-register an A/B, freeze a plan before running it, write up an experiment or a comparison, add error bars or a confidence interval to a rate, reconcile declared cells against the runs that happened, separate confirmatory from exploratory outcomes, name the threats to validity, design the 2x2, or ask whether a skill, tier, model, or strategy actually helps and how you would show it rigorously. Covers the small-n refusal (no CLT below 30 — Wilson, Clopper-Pearson, or a within-experiment Beta-Binomial), the design-arithmetic reconciliation (declared cells == disposition == denominators), the plan freeze and its drift gate, the rate that needs both a numerator and a denominator, probe self-labeling, and record-is-source with the report derived. Not for running the scenario matrix or scoring a bank — that is fathom's fathom-eval; not for measuring one skill's trigger activation — that is evaluate-skill; not for judging whether a spec is ready to build — that is keel's Definition of Ready; and not for a throwaway spot-check you will decide nothing on.
grimaldost/craft-collection/plugins/humblepowers/skills/planned-execution Skill
2★ repoTurn an agreed design or spec into a complete implementation plan and execute it task by task with fresh subagents and two-stage review — the midweight lane between direct implementation and a governed PR series. Use when a feature needs a multi-step plan with review checkpoints but not series machinery: 'write the implementation plan for this spec', 'execute this plan task by task', 'plan then build this', 'run docs/plans/<file>', or when work has outgrown a single TDD loop but doesn't warrant keel or convoy. The plan contract is firm: bite-sized steps with exact paths, complete code, exact commands with expected output, and no placeholders — a zero-context engineer could execute it cold. The loop is firm too: per task, a fresh implementer subagent, then spec-compliance review, then code-quality review, re-reviewing after each fix. Not for deciding what to build (brainstorming comes first), not for governed multi-PR series with gates and dependency DAGs (keel and convoy own that), and not for small single-loop fixes (test-driven-development directly).
grimaldost/craft-collection/plugins/session-workflow/skills/corpus-review Skill
2★ repoAudit a large file corpus — dozens to hundreds of docs, configs, or mixed code-plus-docs-plus-tests — by fanning out blind reviewers over partitions, adversarially verifying every high-severity finding before acting on it, fixing in disjoint file partitions, and re-auditing with fresh eyes until the findings converge. Use when reviewing or auditing a whole repo's documentation, a release's doc set, an entire plugin or package, or any file set too large for one reader to hold at once; on asks like "review all the docs before we push", "audit the whole repo for X", "blind review across these N files", "do a pre-push review of everything", or "check the docs still match the code across the project". It orchestrates the audit on the harness's parallel subagent and workflow primitives and ships no engine of its own. Not for a fresh-eyes panel on a single design, spec, or artifact (that is review-panel), not for reviewing one change's diff for bugs and regressions (that is a diff review / code-review), and not for behaviorally measuring whether a skill triggers and performs (that is evaluate-skill).
grimaldost/craft-collection/plugins/session-workflow/skills/feedback-triage Skill
2★ repoTriage a tool's accumulated dogfooding feedback reports into a leverage-ordered improvement backlog — reconcile what already shipped, cluster findings by underlying cause rather than symptom, assign each cluster a disposition (attack this tool, route out to the tool that owns it, or decline), apply a promotion gate (reinforced across reports, specific, actionable), and emit a triage document with a status-tracked promotion table. Use on "triage the feedback backlog", "cluster the feedback reports", "what should this tool fix next", "promote the recurring feedback", or "/feedback-triage". Explicitly invoked maintenance — never run proactively; it reads a whole corpus. If the tool's binding registers its own triage template (e.g. keel's reflection-triage), follow that template. Not for consolidating journal entries into guidance (that is consolidate-knowledge), not for a corpus of one report with no prior triage (nothing to cluster yet — a 1-report delta over an existing baseline IS a valid later pass), not for triaging GitHub issues or a PR queue, and not for triaging a governed series' own reflections into durable checks — the owning method tool's triage skill (e.g. keel's keel-triage) does that, not this generic feedback pass.
grimaldost/craft-collection/plugins/session-workflow/skills/tool-feedback Skill
2★ repoWrite a per-session dogfooding feedback report for each registered in-development tool the session exercised — what worked, friction, misses with the phase that should have caught them, vacuous gates, and severity-tagged proposed changes with stable finding IDs — saved into that tool's own feedback directory. Use when the user asks for feedback on their tools ("write the feedback reports", "tooling feedback", "dogfood report", "capture the friction with keel / convoy") — a direct imperative naming one tool ("write a dogfooding feedback report for keel") is this skill too, since writing that report IS the skill; route it here rather than drafting the report freehand — and offer once, unprompted, when a session that exercised a registered tool is winding down. Registered tools come from a feedback-targets table the user supplies (e.g. in CLAUDE.md) — never hunt the filesystem for targets. Design-only or authoring-only use of a tool still counts as use. Not for feedback on code or PRs (that is code review), not for capturing general session knowledge into a memory store (that is journaling-sessions), and not for product feedback to a third-party vendor.
logicleap-labs/claude-plugins/plugins/no-slop/skills/no-slop Skill
2★ repoMANDATORY before declaring prose "done" or ending a turn after writing a README, doc, blog post, comment, or any .md/.mdx/.txt/.rst. Use whenever you write or edit prose and are tempted to reach for an AI-tell cliché — "delve into", "it's worth noting that", "a testament to", "navigate the complexities", "rich tapestry", "in today's fast-paced world", "unlock the full potential", "seamlessly integrate", "elevate your", or a pile-up of decorative em-dashes. Forces you to cut the tell and say the thing plainly. Triggers on "make it sound better", "polish this copy", "write the intro", "draft the README", "punch up the wording", "add a conclusion".
logicleap-labs/claude-plugins/plugins/no-stub/skills/no-stub Skill
2★ repoMANDATORY before declaring code "done", "ready", or ending a turn after writing a function/handler/module. Use whenever you write or edit code and are tempted to leave a placeholder — TODO/FIXME, NotImplementedError, an empty `...` body, "your code here", "implementation goes here", a stub return, or a half-built path. Forces you to finish the job: real, working implementation, or an explicit intentional-stub declaration. Triggers on "I'll add this later", "placeholder for now", "scaffolding", "stub out", "TODO", "left as an exercise", "wire this up later".
piyushzala158/agent-skills/code-comments Skill
2★ repoImprove code comments and documentation comments. Use when Codex writes, reviews, removes, or refactors inline comments, JSDoc/TSDoc comments, TODO notes, public API documentation, complex logic explanations, or comments that may be stale, noisy, misleading, or missing.
VioletScar-Hui/Build_Great_Loop/skill-craft/examples/weekly-report-standard Skill
2★ repo在撰写或审阅团队周报时提供格式与内容规范。当用户说"写周报"、"检查周报格式"、 "周报该怎么写"时调用。覆盖结构、量化表达和禁忌项。不适用于日报、月度总结或 绩效自评(各有其模板)。
RightBlogger/bloggingskills/skills/brand-voice Skill
2★ repoWhen the user wants their content to sound like a specific person or brand, or wants to capture and reuse a writing voice from samples. Also use when the user says 'make it sound like me', 'match my voice', 'capture my writing style', 'analyze how I write', 'write in our brand voice', 'here are samples of my writing', or 'it doesn't sound like us'. Builds a reusable voice profile the other skills write in. For one-off de-slopping with no captured voice, see humanize. For the blog's niche and audience setup, see blog-context.
affectionatec/agentic-engineering/skills/documentation-maintenance Skill
2★ repoUse when something said or decided in conversation makes a chain document (PRD, SPEC, ADR, IMPL PLAN, AGENTS.md) stale, contradicted, or incomplete, or when the user proposes a new feature or scope change mid-project. Triggers on "I want to add a feature", "let's also support X", "change the architecture", "switch from X to Y", "we decided to...", "the spec is out of date", "keep the docs in sync", "the code now does X but the doc says Y", or noticing any decision in the conversation that the docs don't yet reflect. The agent flags drift proactively and MUST get the user's permission before editing any fundamental document.
affectionatec/agentic-engineering/skills/existing-project-onboarding Skill
2★ repoUse when an existing or legacy codebase needs to enter the agentic-engineering workflow but has no chain documents (or only scattered legacy docs — README, wiki, design notes). Triggers on "onboard this repo", "migrate this project to agentic-engineering", "reverse-engineer the docs", "adopt this workflow on an existing codebase", "we already have a codebase, set up the docs", "document what we already built", or pointing the suite at a brownfield project. Reverse-engineers the code into an as-built documentation chain; changes docs, never code.
affectionatec/agentic-engineering/skills/using-agentic-engineering Skill
2★ repoEntry point and router for the Agentic Engineering suite. Use when starting work in a project that uses (or should use) the documentation chain, when unsure which chain document or skill comes next, or when asked where the project stands. Triggers on "use agentic engineering", "using-agentic-engineering", "where does this project stand in the chain", "what's the next step", "assess the chain", "how do I start with this suite", or a request naming a chain step whose prerequisites aren't in place yet.
dustinkeeton/wafflestack/.claude/skills/docs-agent Skill
2★ repoMachine-readable documentation standard optimized for LLMs and agents — structured, terse, explicit. Defines the project's machine-doc file set and format rules. Use when creating or updating documentation intended for AI consumption.
dustinkeeton/wafflestack/.claude/skills/docs-human Skill
2★ repoHuman-readable documentation standard — scannable, plain-language docs derived from the agent docs but formatted for human consumption. Defines the project's human-doc file set and format rules. Use when creating or updating documentation intended for human stakeholders.
dustinkeeton/wafflestack/.claude/skills/docs Skill
2★ repoOrchestrates documentation updates by spawning the harness-architect, docs-agent, and docs-human agents in sequence. The first pass audits the codebase and reports changes, docs-agent writes machine-readable docs, docs-human writes human-readable docs.
dustinkeeton/wafflestack/.claude/skills/md-maximalist Skill
2★ repoUse markdown's full formatting range — tables, callouts, task lists, collapsible sections, code fences, bold-lead bullets — to build tasteful richness in docs. Chooses the form from the shape of the content (parallel items become tables, sequences become ordered lists, optional depth becomes a collapsible) and holds every formatting choice to one test — does it speed up a scanning reader. Richness in service of scanning, never decoration. Use when writing or restructuring human-facing markdown. Invokable by users and agents.
dustinkeeton/wafflestack/.claude/skills/prose Skill
2★ repoWrite documentation prose a human can actually read — plain language over jargon, one idea per sentence, the conclusion first, and every paragraph scannable. Cuts throat-clearing, hedges, and abstraction that says nothing, and reads the result back as the target reader before shipping. Use when writing or editing human-facing docs, READMEs, decision logs, or any narrative a person must skim under time pressure. Invokable by users and agents.
dustinkeeton/wafflestack/stacks/docs-system/skills/accurate Skill
2★ repoMachine-legible accuracy — write claims an agent can act on without judgment, and treat documentation as another form of code. Verifies signatures against real exports, paths against the filesystem, counts against a real enumeration, and commands against the manifest that defines them; prefers omission over invention, and never launders an unverified guess as a hedge. A wrong doc is a bug. Use when writing or updating machine-readable docs, registries, API references, or any doc whose claims an agent will act on. Invokable by users and agents.
dustinkeeton/wafflestack/stacks/docs-system/skills/docs-agent Skill
2★ repoMachine-readable documentation standard optimized for LLMs and agents — structured, terse, explicit. Defines the project's machine-doc file set and format rules. Use when creating or updating documentation intended for AI consumption.
dustinkeeton/wafflestack/stacks/docs-system/skills/docs-human Skill
2★ repoHuman-readable documentation standard — scannable, plain-language docs derived from the agent docs but formatted for human consumption. Defines the project's human-doc file set and format rules. Use when creating or updating documentation intended for human stakeholders.
dustinkeeton/wafflestack/stacks/docs-system/skills/md-maximalist Skill
2★ repoUse markdown's full formatting range — tables, callouts, task lists, collapsible sections, code fences, bold-lead bullets — to build tasteful richness in docs. Chooses the form from the shape of the content (parallel items become tables, sequences become ordered lists, optional depth becomes a collapsible) and holds every formatting choice to one test — does it speed up a scanning reader. Richness in service of scanning, never decoration. Use when writing or restructuring human-facing markdown. Invokable by users and agents.
dustinkeeton/wafflestack/stacks/docs-system/skills/prose Skill
2★ repoWrite documentation prose a human can actually read — plain language over jargon, one idea per sentence, the conclusion first, and every paragraph scannable. Cuts throat-clearing, hedges, and abstraction that says nothing, and reads the result back as the target reader before shipping. Use when writing or editing human-facing docs, READMEs, decision logs, or any narrative a person must skim under time pressure. Invokable by users and agents.
dustinkeeton/wafflestack/stacks/orchestration/skills/docs Skill
2★ repoOrchestrates documentation updates by spawning the {{roster.architectAgent}}, docs-agent, and docs-human agents in sequence. The first pass audits the codebase and reports changes, docs-agent writes machine-readable docs, docs-human writes human-readable docs.
tywinlu1988/Credence-Global/dev/.claude/skills/credit-report-builder Skill
2★ repoUse when turning a completed fixed-income credit analysis into a deliverable report — selecting the correct report template (Type 1–18), mapping findings to the L0/L1/L2 output tiers, rendering a multi-stakeholder dashboard, or assembling a layered credit report from an analysis artifact. Triggers on 'generate report', 'produce a credit approval report', 'build a dashboard', 'L0 signal card', or when a work-path sheet's templates must be produced. Requires an upstream analysis artifact; does not perform analysis itself.
toverux/grimoire/skills/research Skill
2★ repoInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
toverux/grimoire/skills/writing-great-skills Skill
2★ repoLoad before writing or editing any file an agent will load and act on — a skill (SKILL.md), an AGENTS.md or CLAUDE.md, or a rules file. The vocabulary and principles that make those files predictable. A session that only reads them leaves this unloaded.
skuio/sku-skills/dist/claude/platform/sync-sops Skill
2★ repoKeep your internal Standard Operating Procedures (SOPs) in step with SKU.io. SKU.io ships often — menus move, workflows change, features are added — which quietly breaks the step-by-step procedures your team relies on. Give this skill your SOP content plus the date you last reviewed it: it reads SKU.io's public changelog and documentation, finds the changes that affect your procedures, and rewrites the exact stale steps — or drafts a brand-new SOP from the current docs, in your own format. Use it whenever internal docs/SOPs may be out of date, or on a schedule to catch drift.