CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-search

Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas. Use this whenever the user asks "what did we discuss about X", "find that meeting where we talked about Y", "what did Alex say", "did we decide on", "what was that idea about", or any question that could be answered by searching their meeting history. Also use for "do I have any notes about" or "check my meetings for".

Quality

89%

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

The canonical home for this skill is minutes-search in silverstein/minutes

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 highly actionable, well-organized CLI skill guide with executable commands, a flags reference, and an explicit result-verification step. It falls just short of top marks on conciseness (coaching dialogue padding), workflow clarity (no recovery path for failed `minutes get`), and progressive disclosure (all content inline at ~85 lines).

Suggestions

Trim the scripted dialogue quotes in "Search coaching" to one-line directives and merge overlapping advice from "Tips for good searches" to reduce token spend.

Add an error-recovery branch for the `minutes get` step (e.g., what to do on non-zero exit or a stale path, such as re-running `minutes list` or the search to confirm the path).

Move the "Search coaching" heuristics and "Gotchas" into a single reference file (e.g., `references/search-strategies.md`) to keep SKILL.md closer to a lean overview.

DimensionReasoningScore

Conciseness

The body is largely lean and command-first, but the "Search coaching" section carries several scripted dialogue responses (e.g., "That'll return hundreds of results. What specifically are you looking for?") and "Tips for good searches" partially reiterates coaching content, so it is not anchor-5 tight.

4 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: `minutes search "pricing strategy"`, `-t memo`, `--since 2026-03-01 --limit 5`, `minutes get "<exact path>" --json`, plus concrete auxiliary commands like `date -v-7d +%Y-%m-%d` and `qmd update && qmd embed`, with a flags table and output-field list.

5 / 5

Workflow Clarity

The sequence — narrow the query (coaching), run `minutes search`, then reauthorize with `minutes get "<exact path>" --json` while requiring "exit status 0" — includes an explicit validation checkpoint, but there is no error-recovery guidance for what to do when `minutes get` fails or the path is stale.

4 / 5

Progressive Disclosure

Sections (Usage, Flags, Output, How search works, Search coaching, Tips, Gotchas) are well-labeled and easy to navigate, but at ~85 lines with everything inline — including a coaching section that could live in a separate reference file — it doesn't meet the under-50-lines condition for a 5, and there is minor content that would fit better split out.

4 / 5

Total

17

/

20

Passed

Description

90%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 what-and-when structure and exceptionally natural trigger phrases. The only weakness is that it describes a single search action rather than enumerating multiple concrete capabilities.

DimensionReasoningScore

Specificity

"Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas" names the domain and one concrete action with its objects, but offers only a single action verb rather than the several specific actions of anchor 4/5 (e.g., no mention of retrieving or reading full transcripts).

3 / 5

Completeness

Explicitly answers both what ("Search past meeting transcripts and voice memos for specific topics, people, decisions, or ideas") and when ("Use this whenever the user asks...") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Comprehensive natural phrases users would actually say — "what did we discuss about X", "what did Alex say", "did we decide on", "do I have any notes about", "check my meetings for" — covering questions, people-lookups, decisions, and ideas with varied phrasings.

5 / 5

Distinctiveness Conflict Risk

A clear niche — searching the user's own meeting history/memos — with distinctive trigger phrasings that are unlikely to fire for unrelated skills; no generic language that would overlap with other capabilities.

5 / 5

Total

18

/

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

.agents/skills/minutes/minutes-search/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.