CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-recap

Generate a daily digest of today's policy-authorized meetings and voice memos — key decisions, action items, and themes across available recordings. Use when the user asks "recap my day", "what happened in my meetings today", "daily summary", "what did I discuss today", "any action items from today", or wants a consolidated view of the day's conversations.

Quality

90%

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

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.

The body is a tight, highly actionable workflow with concrete commands, validation checkpoints, and thoughtful edge cases. Its main weaknesses are the missing error-recovery loop for failed commands and a referenced template file that is not actually bundled. A few justificatory sentences could also be cut for token efficiency.

Suggestions

Add a failure-recovery step: specify what to do when `minutes list` or `minutes get` exits non-zero (e.g., retry once, then report the error and the exact command that failed) so the workflow has a feedback loop rather than only success-path checkpoints.

Ship `templates/daily-recap.md` in the skill bundle or inline its section skeleton — the body's only external reference currently points to a file that does not exist in the reviewed bundle.

Trim rationale sentences that explain why the guidance matters (e.g., "This turns the recap from a passive report into an active reconciliation tool", "ideas captured on the go are easy to forget") to tighten token efficiency.

DimensionReasoningScore

Conciseness

Largely efficient — commands, gotchas, and checklists carry weight without padding — but a few rationale sentences could be trimmed ("This turns the recap from a passive report into an active reconciliation tool", "ideas captured on the go are easy to forget — surface them"). Not 5 because those justifications of behavior Claude could infer add tokens; not 3 because the verbosity is minor and localized.

4 / 5

Actionability

Gives copy-paste-ready commands ("minutes list --limit 50", "minutes get \"<exact path>\" --json"), an exact template path, a fully specified AskUserQuestion format with option sets, and concrete edge-case handling (memos in ~/meetings/memos/, cross-day meetings, raw transcripts). Common cases are covered specifically; matches the anchor-5 example.

5 / 5

Workflow Clarity

Clear 4-step sequence with validation checkpoints ("Require exit status 0", "Never reopen list paths through the host filesystem") and explicit empty-result handling ("No recordings today ≠ an error"). Not 5 because there is no error-recovery path when a command exits non-zero — the workflow requires success but never says what to do on failure.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level reference ("use the template in templates/daily-recap.md"), but that referenced file does not exist in the reviewed bundle (no references/, scripts/, assets/, or templates/ directories), so the pointer dangles. Good structure with a minor organization gap matches anchor 4; not 5 because the single external reference cannot be resolved.

4 / 5

Total

17

/

20

Passed

Description

95%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 that clearly states both capability and explicit trigger conditions in third person. Trigger phrases are natural and varied, and the niche is distinct. The only minor gap is that capability coverage rests on one primary action with its outputs rather than a broader list of actions.

DimensionReasoningScore

Specificity

Names the domain ("policy-authorized meetings and voice memos") and enumerates concrete outputs ("key decisions, action items, and themes across available recordings") plus a "daily digest" deliverable. It stops short of a 5 because the action list centers on a single verb ("generate") rather than multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both what ("Generate a daily digest ... key decisions, action items, and themes") and when ("Use when the user asks ...") with concrete trigger phrases. Matches the anchor-5 example structure exactly; not 4 because the 'when' clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Covers comprehensive natural phrasings users would actually say: "recap my day", "what happened in my meetings today", "daily summary", "what did I discuss today", "any action items from today", plus "consolidated view of the day's conversations". Anchor 5 for breadth of natural synonyms; anchor 4 would require missing common variations, which is not the case.

5 / 5

Distinctiveness Conflict Risk

Clear niche — a consolidated daily recap across meetings and voice memos — with trigger phrases specific to that niche, so minimal conflict risk with adjacent skills like single-meeting summarization. Not 4: no meaningful overlap surface is left ambiguous.

5 / 5

Total

19

/

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-recap/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.