glossary

Maintain Chatto's glossary of terms in docs/GLOSSARY.md. Look up a term, add a new one, or audit the glossary against the codebase, FDRs, and ADRs for missing or stale entries.

Quality

75%

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/glossary/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.

A well-crafted, instruction-only skill body with concrete modes, specific file references, a copy-paste entry template, and a propose-only audit workflow that bakes in verification. Minor conciseness redundancy and slightly abstract research directives keep it just short of top marks.

Suggestions

Consolidate the "section by who-uses-the-word" rule to a single canonical statement and reference it rather than restating it in Mode 2 and Mode 3.

Tighten Mode 2 step 2 ("Research the term in the codebase, FDRs, ADRs, and .claude/rules/") with the specific search heuristic from the Audit Heuristics section so the add path is as concrete as the audit path.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no padding about what a glossary/RBAC/NATS is — but the "section by who-uses-the-word" rule is restated across Sections, the Where-does-a-term-go subsection, and Mode 2/3, offering minor trim opportunities.	4 / 5
Actionability	Concrete guidance throughout: specific file paths (docs/GLOSSARY.md, docs/fdr/INDEX.md, .claude/rules/), a copy-paste entry-format template, named report categories, and explicit heuristics; a few directives like "research the term" remain slightly abstract.	4 / 5
Workflow Clarity	Each of the three modes has a numbered sequence with checkpoints (approval before writing in Mode 2; propose-only with dead-link/stale-flag verification in Mode 3), though no explicit edit→validate→retry feedback loop is specified.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and no inlined material that belongs in a separate file; as a single cohesive ~110-line doc with no bundle it stays at 4 rather than 5 since it lacks an overview-pointing-to-details structure.	4 / 5
	Total	16 / 20 Passed

Description

75%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 specific, well-scoped description that clearly conveys the three modes (look up, add, audit) and is tightly bound to the Chatto glossary niche. Its main weakness is the absence of an explicit "Use when…" trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to define, look up, or add a Chatto term, or to audit the glossary for stale or missing entries."

Include a few natural synonyms ("definition", "jargon", "term") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Look up a term, add a new one, or audit the glossary against the codebase, FDRs, and ADRs" — covering all three operational modes comprehensively.	5 / 5
Completeness	The "what" is clear (maintain the glossary via three modes) but there is no "Use when…" clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural phrases like "look up a term", "add a new one", and "audit the glossary" map to what a user would say, though synonyms like "definition" or "jargon" are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to "Chatto's glossary of terms in docs/GLOSSARY.md" with FDRs/ADRs context — a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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: 2 missing, 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: chattocorp/chatto
Path: .agents/skills/glossary/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.