CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-lint

Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A tight, highly actionable skill body for a single-command workflow, with exact report templates and genuinely useful gotchas. The main defects are an internal contradiction on the staleness default (14 in the example vs 7 stated as default) and missing failure handling for the primary consistency command.

Suggestions

Resolve the staleness-default contradiction: the example command uses `--stale-after-days 14` while the filter description says "(default: 7)" — either drop the flag from the example or correct the stated default.

Add explicit handling for the main `minutes consistency` command failing or returning empty output, parallel to the existing nonzero-exit guidance for `minutes commitments --json`.

Clarify in step 1 or step 2 what to do when the JSON output is empty or the command errors, so the report-formatting workflow has a complete feedback loop.

DimensionReasoningScore

Conciseness

The body is lean throughout — a single command, exact output templates, and a gotchas section containing only non-obvious operational knowledge ("it uses stable source snapshots, not a durable graph cache ... it does not exist"). Nothing explains concepts Claude already knows, and every section earns its place.

5 / 5

Actionability

The command `minutes consistency --stale-after-days 14` is copy-paste ready and the report templates are exact, covering conflicts, resolved supersessions, stale items, and the clean case. However the example uses `--stale-after-days 14` while the filter list says "(default: 7)", an internal inconsistency that leaves a concrete detail ambiguous — a minor gap that keeps it below fully executable.

4 / 5

Workflow Clarity

The sequence (run check → parse JSON → format report → suggest next steps) is clear, and the note "treat a nonzero exit as unavailable, never empty" provides an error checkpoint for the commitments source. It falls short of 5 because the main `minutes consistency` command has no stated failure or empty-output handling, and the default-value contradiction between step 1 and the filter list leaves a checkpoint ambiguous.

4 / 5

Progressive Disclosure

This is a single-command skill with no bundle files (no references/, scripts/, or assets/ exist) and no need for external references; the body is well-organized into clearly labeled sections with all content appropriately inline, which merits a 5 under the simple-skill provision.

5 / 5

Total

18

/

20

Passed

Description

91%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 with an explicit trigger clause quoting natural user phrasings, a clear statement of what the skill does, and a well-defined niche. The only weaknesses are that the enumerated capabilities are variations of one action and a couple of trigger phrases are fairly generic.

DimensionReasoningScore

Specificity

"Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts" plus "audit their decision history" names several concrete defect types, going beyond the 1-2 actions of a score-3 anchor. It is not a 5 because the capabilities are variations of a single consistency-check action rather than a comprehensive set of distinct actions.

4 / 5

Completeness

It explicitly answers what ("Health-check ... for contradictions, stale commitments, and decision conflicts") and when, via an explicit "Use when the user asks ..." clause with concrete trigger phrases — mirroring the top anchor's structure.

5 / 5

Trigger Term Quality

The description quotes literal user utterances — "any conflicts in my meetings", "check for stale action items", "lint my meetings", "are there contradictions" — covering natural synonyms and phrasings a user would actually say. This matches the comprehensive-synonyms anchor exactly.

5 / 5

Distinctiveness Conflict Risk

The meeting-minutes niche and phrases like "lint my meetings" are distinct, but "consistency check" and "are there contradictions" are generic enough to overlap with other consistency-auditing skills, so it is a 4 rather than a 5.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

silverstein/minutes

Path

tooling/skills/goldens/claude/minutes-lint/SKILL.md

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.