agentleFS
bislink360bislink360/styled-markdown/skills/semantic-markdown-writer/SKILL.md

semantic-markdown-writer

Skill3 starsChanged 5 days agoMITView on GitHub

Create and edit Semantic Markdown (.smd) documents (PRDs, ADRs, RFCs/design docs, runbooks, API references, status reports, meeting notes, postmortems, release notes, OKRs, onboarding guides, test plans, PR descriptions, specs and plans) with templates and a validator that fixes mistakes. Use it whenever the user asks to write, draft, create, convert, restructure or update a .smd file, asks for a spec/PRD/ADR/runbook/status report "in smd" or "semantic markdown", wants a Markdown doc converted to .smd, or wants a document that both people and AI agents will read.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. bislink360/semantic-markdown★ 3100% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Start from a template: when one fits: smd init docs/name.smd --template prd --title "Saved searches" (today's date filled in.

    line 14
  2. Very specific:

    Fill it with real content: Delete sections that don't apply.

    line 35
  3. Very specific:

    Meaning over decoration: Use :::warning, :::danger or :::decision for things that matter.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Writing Semantic Markdown (.smd)

.smd is Markdown plus a small, validated vocabulary: callouts, decisions, risks, API blocks, tasks with owners and due dates, KPIs, diagrams, and audience blocks. People read it in a styled preview, AI agents through a compact "agent view". Write for both.

Tool (Node 22+, no install): node <this-skill-dir>/scripts/smd.cjs <command> (or smd if it's on PATH).

Workflow

  1. Start from a template when one fits: smd init docs/name.smd --template prd --title "Saved searches" (today's date filled in; raw files in assets/templates/).

    RequestTemplate
    Product requirements, feature specprd
    Architecture/technical decisionadr
    Design proposal, RFC, tech specrfc
    On-call / operational procedurerunbook
    Endpoint referenceapi
    Weekly/monthly updatestatus-report
    Meeting summary with actionsmeeting-notes
    Incident reviewpostmortem
    Release announcement, upgrade guiderelease-notes
    Objectives and key resultsokrs
    New team member guideonboarding
    Test scope, strategy and casestest-plan
    Pull request descriptionpr-description
    Spec-driven work for an agent: spec → plan → tasksspec, plan, tasks

    Otherwise start from front matter + headings. For a status report on work tracked in .smd docs, draft it with smd report docs/ --since 2026-09-01 -o docs/status.smd --title "Checkout squad" (or --since <git-ref>): tasks done and added, open and overdue tasks, decisions and high-impact risks, each linked. Then write the summary and cut what doesn't matter.

  2. Fill it with real content. Delete sections that don't apply; never leave placeholders such as —, @owner or YYYY-MM-DD. If you don't know a value, ask, or leave a :::question that says what's missing.
  3. Format, validate and fix: smd fmt docs/name.smd, then smd validate docs/name.smd --fix. fmt changes only layout. --fix repairs what has one clear repair (typos in names and values, colors, yes/no booleans, date formats, unclosed ::: or fences at the end). Fix the rest yourself from each error's line:column, message and rule code. A document is done only at 0 errors.
  4. Check what agents will see: smd agent docs/name.smd --brief. If it's long, move narrative into {agent=skip} sections or :::human blocks.

Spend tokens on meaning

Output tokens cost about 5× input tokens. Write meaning: decisions, risks, tasks, :::agent rules, {agent=skip} on narrative. Leave colors, badges and layout (tabs, columns, cards) to people unless asked. The syntax reference is split by topic: read references/syntax.md (a short index), then only the topic file for the construct you're unsure of, and let smd validate --fix catch the rest.

Rules you must follow

  1. Front matter first: smd: 2 (new documents; keep an existing document's value), title, a precise one- or two-sentence summary, status (draft · review · approved · deprecated · archived), owners, updated (YYYY-MM-DD). Don't repeat the title as a # H1; start at ##. Another language adds lang: (de, es, fr, ja, pt, zh, or a tag like pt-BR).
  2. Blocks are :::name{attrs} Title … :::. Attributes go directly after the name, no space. A bare ::: closes the innermost block. Write outer containers with more colons (::::tabs).
  3. Only known names. Blocks: note info tip success warning danger question details card box tabs/tab columns/column steps timeline figure glossary quote decision risk risk-matrix changelog api agent human include. Inline: :badge :status :priority :due :metric :progress :kbd :mention :ref.
  4. Values exactly as specified: decision status proposed · accepted · rejected · superseded · deprecated; risk impact/likelihood low · medium · high · critical; api method GET, POST… and a required path; priority P0–P4; dates YYYY-MM-DD. Figures, glossary, quotes and changelogs have their own forms (syntax/figures-and-notes.md, syntax/project.md).
  5. Named colors only (red orange amber yellow green teal cyan blue indigo purple pink gray muted accent) unless a brand hex is required.
  6. Tasks: - [ ] Verb-first task :priority[P1] @owner :due[2026-10-15], one owner where possible.
  7. Code: give fences a language; embed real source with file="../src/x.ts" lines="10-24" (empty body) instead of pasting it. Shared text goes in one file, pulled in with :::include (syntax/developer.md).
  8. Diagrams: ```mermaid with a valid first line (flowchart LR, sequenceDiagram, gantt, …).
  9. Facts that repeat (version, product name, date) go in the front matter once and appear as {{version}}. Quote versions (version: "2.10"; syntax/inline.md).
  10. Spec v2 shows text as written: straight quotes stay straight (type — or add typography: true), only https://…, www.… and e-mail addresses become links, any :name[…] is a directive (\:name[…] is text). Don't change an smd: 1 document's value while editing; smd migrate FILE --to 2 moves it (syntax/spec-v2.md).

Writing for both audiences

references/style-guide.md covers this in depth. In short:

  • Meaning over decoration. Use :::warning, :::danger or :::decision for things that matter. Color must never be the only signal.
  • Hard constraints for implementers go in one :::agent block near the end. Agents always receive it, even when they read one section.
  • Narrative, history and research go under ## Background {agent=skip} or in :::human. People still see it; agents skip it.
  • Unresolved decisions go in :::question, with who decides and by when; the interim fallback goes in the :::agent block.
  • Requirements, constraints and acceptance criteria get their own blocks with ids (:::requirement{#R1}, :::constraint{#C1 scope=document}, :::acceptance{#AC1 verifies=R1}), not tables. See references/syntax/requirements.md.
  • When a document is under review, propose changes as suggestions (smd review suggest <file> <id> --text … --by …) instead of editing reviewed text. See references/syntax/review.md.
  • Headings name the content ("Requirements", "API", "Rollout") because agents select sections by heading.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.