CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-mcp-recall

Route meeting-recall questions to the right Minutes MCP tool.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/minutes-mcp-recall/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean routing skill: a decision table with concrete question-to-tool mappings, an explicit host prefix rule, anti-pattern guardrails, and a single well-signaled reference. Its only blemish is the Skill Path export block, which references helper scripts that do not exist in the bundle.

Suggestions

Trim or justify the "Skill Path" env-var block: the bundle has no scripts, and reading references/tool-map.md does not require MINUTES_SKILL_ROOT, so the section can be removed or conditioned on actual script use.

If the export block is kept, state exactly which bundled scripts need it once they are added, so the instruction is not speculative.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence, but the "Skill Path" section instructs setting MINUTES_SKILLS_ROOT/MINUTES_SKILL_ROOT "[b]efore running helper scripts or opening bundled references" — the bundle contains no scripts, and opening references/tool-map.md does not require these variables. This is minor trimmable content, matching anchor 4 rather than anchor 5's 'every token earns its place'.

4 / 5

Actionability

The decision table maps concrete user phrasings to exact tool calls (e.g. "'What do I still owe?'" → track_commitments), the host prefix rule is explicit, and the bash export block is copy-paste ready. Specific examples cover the common routing cases, matching the top anchor for an instruction-only skill.

5 / 5

Workflow Clarity

This is a simple, single-purpose skill (choose the right recall tool), and the single action is unambiguous via the decision table, with anti-patterns acting as guardrails (e.g. avoid speculative get_meeting calls). Per the rubric's simple-skill exception, workflow clarity scores 5; there are no destructive or batch operations that would require validation checkpoints.

5 / 5

Progressive Disclosure

The body is a compact, well-sectioned overview with exactly one clearly-signaled, conditional, one-level-deep reference — "Read [the complete tool map](references/tool-map.md) only when the decision table does not cover the request" — and that file exists in the bundle. Content is appropriately split with easy navigation.

5 / 5

Total

19

/

20

Passed

Description

53%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 concise, accurate, and on-domain, but it omits any 'Use when...' trigger guidance and lacks the natural phrases users would say when needing meeting recall. Adding an explicit trigger clause and a few natural trigger terms would lift completeness and trigger-term quality to the top anchors.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks what was said in a meeting, wants a transcript, or asks about meeting commitments or history."

Include natural user phrasings as trigger terms, such as "what did we say", "find that meeting", "meeting transcript", and "who owes me", to improve trigger-term coverage.

Optionally enumerate one or two more concrete capabilities (e.g. searching transcripts, tracking commitments) to raise specificity beyond a single routing action.

DimensionReasoningScore

Specificity

"Route meeting-recall questions to the right Minutes MCP tool" names the domain and a single concrete action (routing), but lists only one action rather than several specific capabilities. It fits anchor 3 (domain plus 1-2 concrete actions, not comprehensive) and not anchor 4, which requires several listed specific actions.

3 / 5

Completeness

The 'what' is clear (route meeting-recall questions to the right tool), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete and unambiguous.

3 / 5

Trigger Term Quality

"meeting-recall" and "Minutes MCP tool" are on-domain keywords, but the description misses the natural phrases a user would actually say ("what did we say", "find that meeting", "transcript", "who owes me"). This matches anchor 3 (some relevant keywords, missing common variations) rather than anchor 2, since the keywords are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

Naming the specific Minutes MCP server and the meeting-recall niche makes it mostly distinct with only minor overlap risk against generic meeting-notes or transcript skills. It falls just short of anchor 5's 'distinct triggers' since the description itself provides few distinguishing trigger phrases.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

silverstein/minutes

Path

.opencode/skills/minutes-mcp-recall/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.