adr

Keep track of architectural decisions in a structured format using Architecture Decision Records (ADRs).

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/adr/SKILL.md

Quality

Content

86%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.

The body is a well-structured, lean, single-purpose skill with concrete templates, clear sequenced workflows, and an appropriate cross-reference checkpoint. The main gap is the absence of an explicit validation/verification step after creating or updating an ADR and its index entry.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with no padding or explanation of what an ADR is; every section (directory structure, workflow, naming, template, TOC format) earns its place, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Provides copy-paste-ready concrete guidance (exact paths, the ADR template, the TOC table format, the naming pattern), but the updating/superseding workflows are guidance rather than fully templated, so it sits at 'mostly executable with minor gaps' rather than score 5.	4 / 5
Workflow Clarity	Each workflow (create/update/supersede) is a clearly sequenced numbered list with a real cross-check checkpoint (the FDR sweep), but there is no explicit post-write validation/re-verification step, fitting 'clear sequence with most checkpoints present; minor validation gaps'.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the single-purpose skill is well-organized into clear sections with the template and formats appropriately inline and easy to navigate, satisfying the simple-skill exception for a self-contained skill.	5 / 5
	Total	18 / 20 Passed

Description

53%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.

The description clearly names a distinct niche and what the skill does, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness and leaves trigger-term coverage adequate rather than comprehensive. Adding concrete use-when phrasing would meaningfully raise the score.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to record, update, or supersede an architectural decision, or asks about ADRs.'

List a couple more concrete actions (e.g. 'create, update, and supersede ADRs, and maintain the index') to lift specificity toward 4-5.

Include a few natural synonyms/variants (e.g. 'design decisions', 'technical decisions') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (architectural decisions/ADRs) and one concrete action ('Keep track of architectural decisions in a structured format'), but does not enumerate several specific actions, so it fits the '1-2 concrete actions, not comprehensive' anchor rather than score 2 (minimal/generic) or score 4 (several specific actions).	3 / 5
Completeness	Clearly states what the skill does ('Keep track of architectural decisions in a structured format using ADRs') but provides no explicit 'Use when...' trigger guidance, so per the cap it cannot exceed 3; not score 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Includes natural terms 'architectural decisions', 'Architecture Decision Records', and the acronym 'ADRs' that users would say, but offers limited synonym coverage (no 'design decisions', 'technical decisions'), matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	Architecture Decision Records is a well-defined niche with distinct triggers and minor overlap risk with a general docs/decision skill, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict score 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: chattocorp/chatto
Path: .agents/skills/adr/SKILL.md
Commit: 967a9a1

Reviewed: 5 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.