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.

73

Quality

91%

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

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 well-structured, actionable audit skill with concrete paths, a findings taxonomy, a report template, and a verified fix workflow. Minor gains are available in tightening redundancy and adding an explicit pre-report validation checkpoint.

Suggestions

Add an explicit validation checkpoint in the Full ADR Audit workflow (e.g., 'confirm each finding cites concrete code/doc evidence before reporting') to close the validation gap and push workflow_clarity toward 5.

Trim overlap between Ground Rules and the What To Check list — the evidence-based and propose-only points appear in both — to improve conciseness.

Consider moving the long Evidence Sources or What To Check bullet lists into a short reference file if the skill grows, to strengthen progressive disclosure beyond its current self-contained form.

DimensionReasoningScore

Conciseness

Efficient domain-specific guidance with concrete paths and categories rather than generic concepts Claude already knows; minor repetition between Ground Rules and the What To Check list keeps it just shy of fully lean.

4 / 5

Actionability

Concrete file paths (docs/adr/INDEX.md, docs/GLOSSARY.md), defined finding categories, a copy-paste report-format template, and a numbered Applying Fixes procedure give fully executable, specific guidance appropriate for an instruction-only audit skill.

5 / 5

Workflow Clarity

The Full ADR Audit is a clear 7-step sequence and Applying Fixes includes a verify-after-edit feedback loop ("markdown link checks or focused grep checks"); the read-only audit workflow itself lacks an explicit validate-findings gate before reporting, leaving a minor checkpoint gap.

4 / 5

Progressive Disclosure

Well-organized into clearly signaled sections (Ground Rules, Full ADR Audit, Evidence Sources, What To Check, Finding Categories, Report Format, Applying Fixes) with no bundle files and one-level references to the adr skill; at ~110 lines with several long bullet lists it is slightly too dense to earn the simple-skill 5.

4 / 5

Total

17

/

20

Passed

Description

100%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 description: concrete actions, comprehensive natural trigger terms, and explicit what/when guidance with a clear niche. It reads in third person with no first/second-person voice or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete review actions — "implementation drift, contradictions, stale decisions, missing supersession notes, weak rationale, and missing cross-references" — giving comprehensive coverage rather than just naming the domain.

5 / 5

Completeness

Explicitly answers both what ("Run a full review of all Architecture Decision Records for...") and when ("Use when the user asks for an ADR review, ADR audit...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural phrasings users would say ("ADR review", "ADR audit", "stale ADR check", "architecture decision consistency check") plus synonyms review/audit/check/verify and both "Architecture Decision Records" and "ADR".

5 / 5

Distinctiveness Conflict Risk

Occupies a clear ADR-review niche with distinct, domain-specific triggers; minimal overlap risk with general code-review skills.

5 / 5

Total

20

/

20

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.