CtrlK
BlogDocsLog inGet started
Tessl Logo

adr-review

Run a full review of all Architecture Decision Records for implementation drift, contradictions, stale decisions, missing supersession notes, weak rationale, and missing cross-references. Use when the user asks for an ADR review, ADR audit, stale ADR check, architecture decision consistency check, or wants to verify ADRs against the current codebase, feature/design records, architecture docs, glossary, or public API state.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, actionable audit skill that assumes Claude's competence and supplies concrete paths, a finding taxonomy, a report template, and verification steps. Its only weakness is mild length/redundancy across the Ground Rules and Full ADR Audit sections.

Suggestions

Consolidate the overlapping guidance between 'Ground Rules' and 'Full ADR Audit' — e.g., 'Read docs/adr/INDEX.md' and 'always audit the full ADR set' each appear twice — to remove redundancy.

Trim or group the 'Evidence Sources' path enumeration (it lists ~9 source categories) into a shorter canonical set with an 'adapt paths to the project' caveat, since much of the detail is project-layout contingent.

Consider folding the 'What To Check' bullets that overlap with 'Finding Categories' so each check item maps directly to the label it produces, reducing the reader's need to reconcile two parallel lists.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (it never explains what an ADR is), but it runs ~118 lines with mild redundancy — 'Read docs/adr/INDEX.md' and 'Always audit the full ADR set' recur across Ground Rules and the Full ADR Audit steps, and the Evidence Sources list is exhaustive. Not a 3 because some repetition and the long path enumeration could be tightened without losing clarity.

2 / 3

Actionability

Provides concrete guidance throughout: specific paths (docs/adr/INDEX.md, docs/fdr/, docs/GLOSSARY.md), a labeled finding taxonomy, a copy-ready markdown report template with an example ADR link, and explicit fix-application steps with verification commands. Not a 2 because the guidance is complete and specific rather than pseudocode-like or missing key details.

3 / 3

Workflow Clarity

The Full ADR Audit is a clearly numbered 7-step sequence, the 'What To Check' list functions as a checklist, and the propose-only default plus post-edit verification ('markdown link checks or focused grep checks') provide explicit checkpoints. Not a 2 because validation/checkpoints are present rather than implicit.

3 / 3

Progressive Disclosure

No bundle files exist, so this is scored on the self-contained structure: the body is organized into well-labeled sections (Ground Rules, Full ADR Audit, Evidence Sources, What To Check, Finding Categories, Report Format, Applying Fixes) with no nested references. Not a 2 because navigation is easy and content is appropriately sectioned rather than a monolithic wall.

3 / 3

Total

11

/

12

Passed

Description

100%

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 is concise, uses third-person imperative voice, and explicitly covers both capability and trigger conditions with natural ADR-specific terminology. It is a strong, low-conflict trigger description with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete review dimensions — 'implementation drift, contradictions, stale decisions, missing supersession notes, weak rationale, and missing cross-references' — matching the anchor for listing several specific concrete actions rather than naming only some.

3 / 3

Completeness

Clearly answers both what (full ADR review across six drift categories) and when via an explicit 'Use when the user asks for...' clause, satisfying the highest anchor. The 'Use when...' trigger is present so it is not capped at 2.

3 / 3

Trigger Term Quality

Natural user phrasings are explicit: 'ADR review, ADR audit, stale ADR check, architecture decision consistency check', giving good coverage of terms a user would actually say. Not a 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (Architecture Decision Records) with distinct ADR-specific triggers, making conflict with other skills unlikely. Not a 2 because the domain and triggers are sharply scoped rather than broadly overlapping.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
chattocorp/chatto
Reviewed

Table of Contents

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.