Agent skill

Architecture Decision Record Writer

by dralgorhythm in dralgorhythm/claude-agentic-framework

Writes Architecture Decision Records with title, status, context, decision, rationale and consequences for significant technical choices, kept short and numbered.

No licenceAuto-check passedDevelopment

Install Architecture Decision Record Writer

skills CLI
$ npx skills add dralgorhythm/claude-agentic-framework --skill writing-adrs -a claude-code

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

GitHub CLI
$ gh skill install dralgorhythm/claude-agentic-framework writing-adrs --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/dralgorhythm/claude-agentic-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/architecture/writing-adrs .claude/skills/writing-adrs && 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
writing-adrs
GitHub stars
125
Token cost
~529 tokens
SKILL.md length
154 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
None found

At a glance

Writes Architecture Decision Records with title, status, context, decision, rationale and consequences for significant technical choices, kept short and numbered.

  • Works in 5 steps: Keep them short: 1-2 pages max → Write when deciding: Not after the fact → Include alternatives: Show what was… → …
  • Recording why a framework, database or API pattern was chosen
  • SKILL.md covers What is an ADR?, When to Write an ADR, ADR Structure and Example ADR, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

An Architecture Decision Record captures one important decision together with its context and consequences. The skill lists when to write one, such as choosing a framework or library, selecting a database or storage solution, defining API patterns, setting coding conventions, making infrastructure decisions, or any decision that affects multiple components.

The structure has a short title, a status of proposed, accepted, rejected, deprecated or superseded, then context describing the situation and forces, the decision, the rationale, and consequences covering trade-offs in both directions. A worked example records a decision to use PostgreSQL as the primary database.

Five habits are recommended: keep each record to one or two pages, write it at decision time rather than after the fact, include the alternatives considered, update the status when a record is deprecated or superseded, and number records in sequence, as ADR-001 and ADR-002.

When your agent uses it

  • Recording why a framework, database or API pattern was chosen
  • Documenting a decision that affects several components
  • Marking an older decision as deprecated or superseded

Example prompts

  • “Write an ADR for moving our job queue from cron scripts to a managed queue service.”
  • “Record the decision to adopt TypeScript for the web client, with the alternatives we rejected.”
  • “Mark the old caching ADR as superseded by the new decision.”

Workflow steps

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

  1. Keep them short: 1-2 pages max
  2. Write when deciding: Not after the fact
  3. Include alternatives: Show what was considered
  4. Update status: Mark deprecated/superseded ADRs
  5. Number sequentially: ADR-001, ADR-002, etc.

What it can do on your machine

Read from SKILL.md and the folder at commit 6436a20. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Architecture Decision Record Writer loads about 529 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 154 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~529

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); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 154 words (~529 tokens).

“An Architecture Decision Record captures an important architectural decision along with its context and consequences.”

— opening of SKILL.md by dralgorhythm
name
writing-adrs

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/architecture/writing-adrs of dralgorhythm/claude-agentic-framework.

Open the folder on GitHubat commit 6436a20

Compare with similar skills

Architecture Decision Record 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.

Architecture Decision Record Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Architecture Decision Record Writer this skilldralgorhythm/claude-agentic-framework125—~529Automated safety check: PassNone
Create Vibe Featuremistralai/mistral-vibe5.1k—~1.2kAutomated safety check: PassApache-2.0
Architecture Decisions and ADRsfirst-fluke/oh-my-agent1.3k—~2.6kAutomated safety check: PassMIT
System Architecture DesignerJeffallan/claude-skills12k—~1.2kAutomated safety check: PassMIT
Light System DesignLight0305/Light-skills640—~3.6kAutomated safety check: PassMIT
Architecture DesignerAratKruglik/claude-laravel1551 repos~895Automated safety check: PassNone

Similar skills

  • Create Vibe Feature

    mistralai/mistral-vibe

    Official

    Guides feature work in the Mistral Vibe Python CLI so each change lands in the right module and matches the project's architecture decision records.

    5.1k GitHub stars~1.2k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Architecture Decisions and ADRs

    first-fluke/oh-my-agent

    Evaluates system boundaries and tradeoffs and writes architecture recommendations, option comparisons or ADRs, with a Mermaid diagram when structure changes.

    1.3k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • System Architecture Designer

    Jeffallan/claude-skills

    Guides system architecture design end to end: gathering requirements, matching them to a pattern, documenting trade-offs with ADRs, and reviewing.

    12k GitHub stars~1.2k tokensUpdated 6 days ago
    DevelopmentAuto-check passed
  • Light System Design

    Light0305/Light-skills

    Evidence-based workflow for designing or modernizing a software system: current-state inventory, options, API and schema contracts, migration plans, ADRs and verification.

    640 GitHub stars~3.6k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Architecture Designer

    AratKruglik/claude-laravel

    A skill your agent uses when designing new system architecture, reviewing existing designs, or making architectural decisions.

    155 GitHub starsUsed in 1 repo~895 tokens
    DevelopmentAuto-check passed
  • Architecture Review

    extra-org/extra

    Guard the project's architecture invariants. An agent skill from extra-org/extra.

    113 GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from dralgorhythm/claude-agentic-framework

All 20 skills in this repo
  • Swarm Coordination

    dralgorhythm/claude-agentic-framework

    Rules for several agents sharing one repository: an orchestrator tracks work in two tiers, workers write to scratch files, and every handoff leaves a pointer to an artifact.

    125 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Threat Modeling

    dralgorhythm/claude-agentic-framework

    Finds security threats in a design with a STRIDE pass per component, rates severity and records fixes, with extra checks for AI agent and tool risks.

    125 GitHub stars~581 tokensUpdated 2 mo ago
    Auto-check passed
  • Codebase Health Auditor

    dralgorhythm/claude-agentic-framework

    Runs a user-invoked, swarm-style audit of a whole codebase for SOLID and DRY violations, code smells, complexity, dead code and pattern consistency, with a prioritized report.

    125 GitHub stars~980 tokensUpdated 2 mo ago
    Auto-check passed
  • Dependency Upgrade Protocol

    dralgorhythm/claude-agentic-framework

    Sequences safe dependency upgrades: read the changelog, verify the version exists upstream, pin it, and keep major bumps in separate commits behind a full gate run.

    125 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Designing Systems

    dralgorhythm/claude-agentic-framework

    Produces this framework's ADR and system-design artifacts from bundled templates with trade-off analysis.

    125 GitHub stars~458 tokensUpdated 2 mo ago
    Auto-check passed
  • Land The Plane

    dralgorhythm/claude-agentic-framework

    Lands in-flight work: quality gates, atomic commit, rebase, push, verified remote sync, then handoff — a user-invoked finish-line workflow.

    125 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Architecture Decision Record Writer

What does Architecture Decision Record Writer do?

Writes Architecture Decision Records with title, status, context, decision, rationale and consequences for significant technical choices, kept short and numbered. An Architecture Decision Record captures one important decision together with its context and consequences. The skill lists when to write one, such as choosing a framework or library, selecting a database or storage solution, defining API patterns, setting coding conventions, making infrastructure decisions, or any decision that affects multiple components.

When should I use Architecture Decision Record Writer?

Architecture Decision Record Writer fits situations like: recording why a framework, database or API pattern was chosen; documenting a decision that affects several components; marking an older decision as deprecated or superseded.

How do I install Architecture Decision Record Writer in Claude Code?

Run `npx skills add dralgorhythm/claude-agentic-framework --skill writing-adrs -a claude-code`. Or copy the skill folder (.claude/skills/architecture/writing-adrs in dralgorhythm/claude-agentic-framework) into .claude/skills/writing-adrs in your project. Claude Code loads it when a task matches its description.

How do I install Architecture Decision Record Writer in Codex?

Run `npx skills add dralgorhythm/claude-agentic-framework --skill writing-adrs -a codex`. Or copy the skill folder (.claude/skills/architecture/writing-adrs in dralgorhythm/claude-agentic-framework) into .agents/skills/writing-adrs in your project. Codex loads it when a task matches its description.

Can I use Architecture Decision Record 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 dralgorhythm/claude-agentic-framework --skill writing-adrs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-adrs, .gemini/skills/writing-adrs, .github/skills/writing-adrs and .opencode/skills/writing-adrs in your project.

What does Architecture Decision Record Writer need to run?

SKILL.md names no scripts, command-line tools or credentials: Architecture Decision Record Writer is instructions for the agent only.

Does Architecture Decision Record 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 Architecture Decision Record 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. Review the folder before installing.

What licence does Architecture Decision Record Writer use?

No licence was found for Architecture Decision Record Writer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Architecture Decision Record Writer use?

About 529 tokens (SKILL.md is roughly 2.1k 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 Architecture Decision Record Writer?

Skills that share tags, products or a category with Architecture Decision Record Writer: Create Vibe Feature (mistralai/mistral-vibe, 5.1k stars), Architecture Decisions and ADRs (first-fluke/oh-my-agent, 1.3k stars), System Architecture Designer (Jeffallan/claude-skills, 12k stars) and Light System Design (Light0305/Light-skills, 640 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architecture Decision Record Writer?

dralgorhythm (a GitHub user) maintains it in dralgorhythm/claude-agentic-framework, which has 125 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on July 24, 2026.

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