chatto-architecture-inventory

Maintain Chatto runtime documentation in docs/architecture/ when runtime structures change, or audit it when requested.

Quality

68%

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/chatto/chatto-architecture-inventory/SKILL.md

Quality

Content

75%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 tight, well-structured instruction skill with concrete symbol-level checks and an explicit verification step. It misses a 5 mainly due to the absence of a worked example and an explicit error-recovery loop in the verification workflow.

Suggestions

Add a short worked example showing the expected structure of a recorded finding (e.g., one filled inventory entry) to push actionability toward 5.

Turn the verification bullet into an explicit validate-then-fix feedback loop ('If a claim fails verification, correct it and re-verify before reporting') to raise workflow_clarity.

Clarify the audit-vs-update decision branch up front as a numbered sequence so the conditional flow ('update by default; report-only for reviews/audits') is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and information-dense (a compact Source Checks table plus tight bullets) with no padding or explanation of concepts Claude already knows; a few table cells could be tightened further.	4 / 5
Actionability	Concrete, specific guidance names exact symbols and files to check (e.g., 'Subjects()', 'projection_subjects_test.go', 'API.Handlers()'); it stops short of a worked example showing how to record a finding.	4 / 5
Workflow Clarity	A clear sequence is present (read index, read relevant categories, update/audit, verify, report) with an explicit verification step ('Verify changed claims against code'), but there is no explicit error-recovery feedback loop.	4 / 5
Progressive Disclosure	Well-organized sections with a single clearly-signaled one-level reference to the inventory index; no bundle files exist, and the content is appropriately scoped for a short skill.	4 / 5
	Total	16 / 20 Passed

Description

62%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 is third-person, concise, and explicitly pairs a what with a when clause, landing it above the midpoint. It is held back from a 5 by generic action verbs and a lack of natural trigger-term synonyms.

Suggestions

Add a 'Use when ...' clause with concrete natural-language triggers (e.g., 'when runtime components, projections, or NATS resources change') to lift completeness and trigger_term_quality.

Replace the generic verbs 'Maintain' and 'audit' with more specific actions like 'update and verify architecture inventory files' to improve specificity.

Include common synonyms users might say ('review architecture docs', 'inventory runtime resources') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Chatto runtime documentation in docs/architecture/') and two concrete actions ('Maintain' and 'audit'), but the actions are generic and coverage is not comprehensive.	3 / 5
Completeness	Explicitly states both what (maintain Chatto runtime documentation) and when (when runtime structures change, or audit when requested); the when clause is present but could be more specific.	4 / 5
Trigger Term Quality	'audit it when requested' is a natural trigger phrase, but 'when runtime structures change' is technical jargon and common synonyms or variations are missing.	3 / 5
Distinctiveness Conflict Risk	The Chatto runtime documentation niche is clearly distinct and unlikely to fire for unrelated skills, though generic verbs like 'audit' carry minor overlap risk with general audit skills.	4 / 5
	Total	14 / 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 suspicious	Warning

	Total	15 / 16 Passed

Repository: chattocorp/chatto
Path: .agents/skills/chatto/chatto-architecture-inventory/SKILL.md
Commit: 5cbd584

Reviewed: 3 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.