CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-weekly

Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week. Use when the user says "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review", or at the end of a work week.

72

Quality

89%

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

88%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.

An exceptionally actionable, well-sequenced workflow skill: every phase has executable commands, exit-status validation, and failure handling, and edge cases are handled explicitly. The only costs are token budget — the ordering lists are repeated verbatim per preference — and a monolithic single-file layout that could offload detail to references.

Suggestions

Compress the Phase 6 preference branches by stating the ordering rule once (e.g., 'the chosen focus area leads; the remaining sections follow in default order') instead of enumerating all three full orderings.

Move the Gotchas list and the set-presentation-focus command examples into a reference file (e.g., references/preferences.md) and link them from the body to reduce inline token load.

Trim the sample dialogue in the Phase 7 closing ritual to a compact format illustration rather than full quoted lines.

DimensionReasoningScore

Conciseness

The body is command-first and free of basic-concept explanation, but the Phase 6 presentation-focus section repeats the same four-section ordering three times (once per preference value) and sample dialogue in Phase 7 and the Gotchas adds trimmable padding — anchor 4, not 5. Not a 3: the verbosity is localized, not pervasive.

4 / 5

Actionability

Commands are copy-paste ready ("minutes list --limit 50", "minutes search \"<topic>\" --since <30-days-ago> --limit 20", "minutes actions"), with concrete output templates, classification schemes, and explicit edge-case handling for zero recordings, light weeks, and tool failures — anchor 5.

5 / 5

Workflow Clarity

Seven phases are clearly sequenced with explicit validation checkpoints ("require exit status 0", "use only the returned content") and error-recovery paths (report the source unavailable rather than grep fallback; never hallucinate a summary on zero recordings) — anchor 5. Not a 4: checkpoints are present and explicit at every external-data step.

5 / 5

Progressive Disclosure

The body is well-sectioned with clear headers and only one-level-deep references (the plugin hook script), but at ~215 lines with no bundle files present, material like the Gotchas list and the presentation-focus persistence commands could be split into a reference file — anchor 4. Not a 5: no well-signaled external references exist to absorb the detail content.

4 / 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 that cleanly answers what and when with an unusually rich set of natural trigger phrases. The only weaknesses are slight under-coverage of the skill's actual outputs and one overly broad trigger term that could fire outside the weekly-synthesis niche.

Suggestions

Consider tightening the trigger "any outstanding items" to a weekly framing (e.g., "what's outstanding from this week") to reduce conflict with plain todo-list requests.

Add one or two more of the skill's real outputs (e.g., voice-memo synthesis or unresolved-prep detection) to raise capability coverage to fully comprehensive.

DimensionReasoningScore

Specificity

"Weekly meeting synthesis — themes, decision arcs, stale commitments, and what deserves your attention next week" names the domain and several concrete outputs, matching anchor 4. It is not a 5 because capabilities the body actually delivers (voice memos, unresolved preps, relationship intelligence) are absent, and 'what deserves your attention' is partially abstract.

4 / 5

Completeness

It explicitly answers both what (synthesis into themes, decision arcs, stale commitments, attention items) and when ("Use when the user says..." with concrete trigger phrases), matching anchor 5 exactly. Not a 4: the when-clause is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Seven quoted natural phrases — "weekly review", "what happened this week", "weekly summary", "recap my week", "any outstanding items", "week in review" — plus a timing trigger ("at the end of a work week") give comprehensive synonym coverage. Not a 4: no common variation of the request is obviously missing.

5 / 5

Distinctiveness Conflict Risk

The weekly-synthesis niche is clear and triggers are mostly week-specific, but "any outstanding items" is a phrase a user might naturally say when they just want a todo list, creating minor overlap risk with task-management skills — anchor 4. Not a 3: the bulk of triggers are unmistakably weekly-recap phrasings.

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
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.