Agent skill

Adr Writer

by skrun-dev in skrun-dev/skrun

Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention.

MITAuto-check passedDevelopment

Install Adr Writer

skills CLI
$ npx skills add skrun-dev/skrun --skill adr-writer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install skrun-dev/skrun adr-writer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/skrun-dev/skrun.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/adr-writer .claude/skills/adr-writer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
adr-writer
GitHub stars
210
Token cost
~861 tokens
SKILL.md length
321 words
Files
8 (incl. scripts)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention.

  • Works in 7 steps: Find existing ADRs — call list_adrs with… → Compute the next number —… → Generate a slug from the title —… → …
  • Asked to document an architectural decision
  • SKILL.md covers Workflow, Style and Conventions
  • Runs TypeScript scripts from its folder

What it does

Adr Writer is an agent skill from skrun-dev/skrun. Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention. Reads the target ADR directory to compute the next number and to surface candidates for cross-linking. Use when asked to document an architectural decision, draft an ADR, or capture a technical choice with its rationale.

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `README.md`, `agent.yaml` and `fixtures/existing-adrs/0001-stack-choice.md`).

It sits in Development, covering Architecture decision records. It works with Amazon DynamoDB and PostgreSQL. The repository describes itself as: Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM. The licence is MIT.

When your agent uses it

  • Asked to document an architectural decision
  • Capture a technical choice with its rationale

Example prompts

  • “/adr-writer”

Requirements

  • Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Find existing ADRs — call list_adrs with the user's adrs_dir. The tool returns an array of { number, slug, title, status, filename }. If…
  2. Compute the next number — max(existing.number) + 1, or 1 if the list is empty. Zero-pad to 4 digits (e.g., 42 → 0042).
  3. Generate a slug from the title — lowercase, kebab-case, alphanumeric only, max 50 chars (e.g., "Switch from Postgres to DynamoDB" →…
  4. Detect cross-link candidates — scan the existing ADR titles for keywords overlapping with the new decision (entities mentioned in context…
  5. Compose the ADR Markdown — use this exact structure
  6. Write the file — call write_artifact with
  7. Return structured output

What it can do on your machine

Read from SKILL.md and the folder at commit b1d963b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Adr Writer loads about 861 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~861

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from skrun-dev/skrun at commit b1d963b, republished under its MIT licence (© skrun-dev). 321 words, ~861 tokens.

Download SKILL.mdSave it as .claude/skills/adr-writer/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
adr-writer
description
Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention. Reads the target ADR directory to compute the next number and to surface candidates for cross-linking. Use when asked to document an architectural decision, draft an ADR, or capture a technical choice with its rationale.

ADR Writer

You are a discipline coach for architectural decisions. Engineering teams make important calls in meetings and forget to document them. You take a structured input (title / context / options / decision / consequences) and produce a clean, numbered ADR file.

Workflow

  1. Find existing ADRs — call list_adrs with the user's adrs_dir. The tool returns an array of { number, slug, title, status, filename }. If the directory is empty or doesn't exist, the tool returns [] and the new ADR is number 1.

  2. Compute the next number — max(existing.number) + 1, or 1 if the list is empty. Zero-pad to 4 digits (e.g., 42 → 0042).

  3. Generate a slug from the title — lowercase, kebab-case, alphanumeric only, max 50 chars (e.g., "Switch from Postgres to DynamoDB" → switch-from-postgres-to-dynamodb).

  4. Detect cross-link candidates — scan the existing ADR titles for keywords overlapping with the new decision (entities mentioned in context or decision). For each match, note Related: ADR-NNNN <title> for the body. Be conservative — only include genuine semantic links, not coincidental word overlap.

  5. Compose the ADR Markdown — use this exact structure:

    # ADR-NNNN: <title>
    
    ## Status
    
    <status — default "proposed">
    
    ## Context
    
    <context, paragraph form, retain user's wording when possible>
    
    ## Options Considered
    
    <options, formatted as a Markdown bullet list — re-format if the user gave free-form prose>
    
    ## Decision
    
    <decision + rationale, paragraph form>
    
    ## Consequences
    
    <consequences — if user provided, use verbatim; otherwise infer 3-5 bullets covering: what becomes easier, what becomes harder, new risks introduced>
    
    ## Related
    
    <one bullet per cross-link candidate found in step 4 — omit this section if none>
    
    ---
    
    _Date_: YYYY-MM-DD (today's date in ISO format)
  6. Write the file — call write_artifact with:

    • filename: NNNN-<slug>.md (e.g., 0042-switch-from-postgres-to-dynamodb.md)
    • content: the full Markdown from step 5
  7. Return structured output:

    • adr_number: the numeric ID (e.g., 42)
    • adr_filename: the filename (e.g., 0042-switch-from-postgres-to-dynamodb.md)
    • summary: a one-line entry suitable for an ADR index, format: ADR-NNNN: <title> — <status>
Show full SKILL.md (102 more words)Show less

Style

  • Keep the prose neutral and technical — ADRs are not advocacy docs.
  • Don't add emojis, headlines, or stylistic flair. Plain Markdown only.
  • The Status section should contain a single word/phrase, not a paragraph.
  • Cross-links must be genuine. False positives erode trust in the index — when in doubt, omit.

Conventions

  • File naming: NNNN-<slug>.md, NNNN is zero-padded 4-digit, slug is lowercase-kebab.
  • Status vocabulary: proposed | accepted | deprecated | superseded.
  • Numbering is monotonically increasing — never reuse a number, even if an ADR is deprecated.
  • One decision per ADR. If the user's input describes multiple decisions, ask them to split (or note the ambiguity in the output summary).

© skrun-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts) in agents/adr-writer of skrun-dev/skrun.

  • SKILL.md
  • README.md
  • agent.yaml
  • fixtures/empty-adrs/.gitkeep
  • fixtures/existing-adrs/0001-stack-choice.md
  • fixtures/existing-adrs/0002-monorepo.md
  • scripts/list_adrs.ts
  • scripts/write_artifact.ts

Open the folder on GitHubat commit b1d963b

Compare with similar skills

Adr Writer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Adr Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adr Writer this skillskrun-dev/skrun210—~861Automated safety check: PassMIT
Ogham Researchogham-mcp/ogham-mcp115—~1.4kAutomated safety check: PassMIT
Event Store Designwshobson/agents40k9 repos~828Automated safety check: PassMIT
DB SculptorEliasOulkadi/shokunin114—~3.1kAutomated safety check: NotesMIT
Redshift Guideaws/agent-toolkit-for-aws2.8k—~2.6kAutomated safety check: PassApache-2.0
Stash Dynamodbcipherstash/stack157—~5.7kAutomated safety check: PassMIT

Similar skills

  • Ogham Research

    ogham-mcp/ogham-mcp

    Structured memory capture for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

    115 GitHub stars~1.4k tokensUpdated 8 days ago
    Agent WorkflowsAuto-check passed
  • Event Store Design

    wshobson/agents

    Designs event stores for event-sourced systems: requirements, a comparison of EventStoreDB, PostgreSQL, Kafka, DynamoDB and Marten, and stream and versioning practices.

    40k GitHub starsUsed in 9 repos~828 tokens
    Backend & APIsAuto-check passed
  • DB Sculptor

    EliasOulkadi/shokunin

    Design database schemas with Prisma/Drizzle, PostgreSQL index strategy (B-tree, GIN, GiST, BRIN, Hash), query optimization (EXPLAIN ANALYZE), migration safety (expand/contract, zero-downtime), and…

    114 GitHub stars~3.1k tokensUpdated 3 days ago
    DatabasesAuto-check: notes
  • Redshift Guide

    aws/agent-toolkit-for-aws

    Official

    Amazon Redshift is NOT PostgreSQL — corrects PostgreSQL-derived LLM mistakes; covers Redshift-specific SQL, DDL, COPY/UNLOAD, system views, metadata discovery, and operational patterns.

    2.8k GitHub stars~2.6k tokensUpdated today
    DatabasesAuto-check passed
  • Stash Dynamodb

    cipherstash/stack

    Integrate CipherStash encryption with Amazon DynamoDB using @cipherstash/stack/dynamodb and EQL v3 schemas.

    157 GitHub stars~5.7k tokensUpdated today
    DatabasesAuto-check passed
  • Database Designer

    borghei/Claude-Skills

    Database design with schema analysis, index optimization, and migration generation for PostgreSQL, MySQL, MongoDB, and DynamoDB.

    881 GitHub stars~1.6k tokensUpdated today
    DatabasesAuto-check passed

More from skrun-dev/skrun

All 14 skills in this repo
  • Changelog Generator

    skrun-dev/skrun

    Generate a polished CHANGELOG.md and release-notes.md from a local git repository (or a captured .git-log.txt dump).

    210 GitHub stars~770 tokensUpdated 15 days ago
    Auto-check passed
  • Turn a CSV of operational data (sales, usage, signups, support tickets) into a multi-page styled PDF executive report with narrative + matplotlib charts.

    210 GitHub stars~1.1k tokensUpdated 15 days ago
    Auto-check passed
  • Turn a folder of Markdown notes (Obsidian vault, Notion export, plain repo docs) into a navigable static HTML knowledge base bundled as a single .zip file.

    210 GitHub stars~1.4k tokensUpdated 15 days ago
    Auto-check passed
  • Listen to a meeting recording and extract structured action items, decisions, and open questions.

    210 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check passed
  • Semgrep Rule Creator

    skrun-dev/skrun

    Generate a complete Semgrep rule bundle (rule.yml + tests.md + README.md) from a CVE description and a bad-code example.

    210 GitHub stars~1.3k tokensUpdated 15 days ago
    Auto-check passed
  • Receipts To Expenses

    skrun-dev/skrun

    Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary.

    210 GitHub stars~1.1k tokensUpdated 15 days ago
    Auto-check passed

Categories

Questions about Adr Writer

What does Adr Writer do?

Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention. Adr Writer is an agent skill from skrun-dev/skrun. Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention.

When should I use Adr Writer?

Adr Writer fits situations like: asked to document an architectural decision; capture a technical choice with its rationale.

How do I install Adr Writer in Claude Code?

Run `npx skills add skrun-dev/skrun --skill adr-writer -a claude-code`. Or copy the skill folder (agents/adr-writer in skrun-dev/skrun) into .claude/skills/adr-writer in your project. Claude Code loads it when a task matches its description.

How do I install Adr Writer in Codex?

Run `npx skills add skrun-dev/skrun --skill adr-writer -a codex`. Or copy the skill folder (agents/adr-writer in skrun-dev/skrun) into .agents/skills/adr-writer in your project. Codex loads it when a task matches its description.

Can I use Adr Writer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add skrun-dev/skrun --skill adr-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adr-writer, .gemini/skills/adr-writer, .github/skills/adr-writer and .opencode/skills/adr-writer in your project.

What does Adr Writer need to run?

Going by SKILL.md and its folder, Adr Writer needs TypeScript for the scripts in its folder. Our summary lists: Node.js.

Does Adr Writer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Adr Writer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Adr Writer use?

Adr Writer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adr Writer use?

About 861 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Adr Writer?

Skills that share tags, products or a category with Adr Writer: Ogham Research (ogham-mcp/ogham-mcp, 115 stars), Event Store Design (wshobson/agents, 40k stars), DB Sculptor (EliasOulkadi/shokunin, 114 stars) and Redshift Guide (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adr Writer?

skrun-dev (a GitHub organization) maintains it in skrun-dev/skrun, which has 210 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 22, 2026.

Source: skrun-dev/skrun on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.