meeting-assistant

Extracts key meeting information in chronological order and outputs decisions and action items; use when you need meeting minutes, action tracking, or project sync notes from transcripts or raw notes.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Other/meeting-assistant/SKILL.md

Quality

Content

56%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 skill's core workflow and worked example are genuinely actionable and well-sequenced, but the body is heavily padded with duplicated sections and generic boilerplate that wastes tokens. Tightening the structure and wiring real links to the existing reference/asset files would markedly improve it.

Suggestions

Remove the duplicated section block: keep only the numbered "## 1."–"## 5." sections and delete the earlier generic "## When to Use"/"## Key Features"/"## Dependencies"/"## Example Usage"/"## Implementation Details" duplicates.

Trim the generic boilerplate sections ("When Not to Use", "Required Inputs", "Recommended Workflow", "Output Contract", "Validation and Safety Rules", "Failure Handling", "Quick Validation") down to only the meeting-specific guidance; most currently restate generic skill platitudes.

Replace generic "Reference material available in references/" pointers with explicit links to the real files, e.g. "Output checklist: see [references/guide.md](references/guide.md); blank template: [assets/meeting_minutes_template.md](assets/meeting_minutes_template.md)", and move the inlined example minutes into the asset file to avoid duplication.

Dimension	Reasoning	Score
Conciseness	The body duplicates its core sections twice ("## When to Use/Key Features/Dependencies/Example Usage/Implementation Details" then again as "## 1."–"## 5.") and layers on generic boilerplate ("When Not to Use", "Required Inputs", "Recommended Workflow", "Output Contract", "Failure Handling", "Quick Validation") that is mostly not meeting-specific, matching the noticeably-verbose anchor 2.	2 / 5
Actionability	Section 5 gives concrete extraction rules (sort by timestamp, decisions vs pending vs disagreements, action items with owner/deadline and TBD/Unassigned fallbacks, sensitive-data masking) plus a full worked input/output example, which is mostly executable guidance with only minor gaps.	4 / 5
Workflow Clarity	The 4-step processing workflow (normalize → parse timeline → extract → structure output) is clearly sequenced with an explicit final validation pass and safety rules; checkpoints are present with only minor gaps, and the skill is non-destructive so no hard cap applies.	4 / 5
Progressive Disclosure	Bundle files exist (references/guide.md, references/evaluation-checklist.md, assets/meeting_minutes_template.md) and are mentioned, but the body references them generically ("Reference material available in references/") rather than with clear one-level navigation, and inlines the full example minutes and template structure that belong in those files.	3 / 5
	Total	13 / 20 Passed

Description

83%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 strong: it clearly states what the skill does and when to use it with concrete, natural trigger phrases. Minor improvements in trigger-term breadth and specificity would push it to the top anchor.

Dimension	Reasoning	Score
Specificity	"Extracts key meeting information in chronological order and outputs decisions and action items" lists several concrete actions (chronological extraction, decisions, action items), with only minor coverage gaps versus the comprehensive anchor 5.	4 / 5
Completeness	It explicitly answers both what ("Extracts key meeting information in chronological order and outputs decisions and action items") and when ("use when you need meeting minutes, action tracking, or project sync notes from transcripts or raw notes") with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	"meeting minutes, action tracking, project sync notes, transcripts, raw notes" gives good natural-term coverage a user would say, but is missing some common synonyms/variants to reach comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The meeting-minutes/notes niche is clearly distinguishable with distinct triggers, but has minor overlap risk with general summarization or note-taking skills, sitting just below the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/meeting-assistant/SKILL.md
Commit: 63c61d3

Reviewed: 13 hours ago

Table of Contents

Discovery Implementation Validation

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.