adr-writing

Architecture Decision Record format and rules for the developer agent. Load when the implementation introduces a structural decision worth remembering 6 months later — new pattern, new dependency, deliberate departure from convention, non-obvious schema choice. Skip for naming and file-layout micro-choices. No ADR is the default.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable instruction skill with concrete templates, path patterns, and a verification checklist. The namespace rationale paragraph is the main conciseness cost, and the workflow is topical rather than a numbered sequence.

Dimension	Reasoning	Score
Conciseness	Lean overall and assumes Claude knows what an ADR is; the 'Why the session+ticket namespace' paragraph is somewhat long, though it captures genuinely non-obvious project rationale that earns its tokens.	4 / 5
Actionability	Copy-paste-ready file path template, per-language reference-comment syntax, exact commit subject format, and a literal fill-in ADR template fully cover the common cases.	5 / 5
Workflow Clarity	Topical sections imply a clear write → reference → commit sequence and end with an explicit Verification checklist; not a 5 because steps are not a numbered sequence with explicit feedback loops.	4 / 5
Progressive Disclosure	Self-contained skill with no bundle files and clean section headers (When, File naming, Source-code reference, Commit, Template, Red Flags, Verification); well organized but over 50 lines, so it stops short of the simple-skill 5.	4 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-targeted description that answers what and when with concrete, natural trigger language and explicit exclusions. Minor room to broaden trigger-term synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Architecture Decision Record format and rules') and gives concrete sub-cases (new pattern, new dependency, deliberate departure from convention, non-obvious schema choice); minor gaps in that it does not enumerate multiple distinct performed actions.	4 / 5
Completeness	Clearly states what ('ADR format and rules') and an explicit when ('Load when the implementation introduces a structural decision...') with concrete trigger phrases and a negative-trigger clause.	5 / 5
Trigger Term Quality	Natural developer-facing phrases ('structural decision worth remembering 6 months later', 'new pattern', 'new dependency', 'departure from convention', 'schema choice') plus explicit skip terms; a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (ADR writing for the developer agent) with distinct triggers and explicit exclusions ('Skip for naming and file-layout micro-choices'), minimizing overlap with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: marmelab/atomic-crm
Path: .claude/skills/adr-writing/SKILL.md
Commit: 64e2163

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.