CtrlK
BlogDocsLog inGet started
Tessl Logo

meeting-synthesis

Workflow for turning meeting transcripts or notes into decisions, action items, unresolved questions, risks, and follow-up artifacts. Use for prompts like "summarize this meeting", "extract action items", "what did we decide", or "draft the follow-up". Best when you have notes or a transcript, attendee context, and the reason the meeting happened. Optional Open Brain search and capture can pull surrounding context and store the final synthesis or decisions.

65

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 ./skills/meeting-synthesis/SKILL.md
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 tight, well-structured instruction skill that respects the context budget and gives concrete synthesis guidance with clear sequencing. Its main gap is the absence of explicit validation feedback loops and concrete output templates that would push it to top marks.

Suggestions

Add an explicit validation step (e.g., 'Re-check each extracted decision/action against the transcript; if unsupported, mark as unresolved') to create a validate-fix-retry loop.

Include a compact output template or example brief so the default output format is copy-paste ready rather than implied.

DimensionReasoningScore

Conciseness

Lean and efficient throughout; assumes Claude's competence, avoids explaining what a meeting is or padding with library recommendations, and every line earns its place.

5 / 5

Actionability

Provides concrete, specific guidance such as separating 'decided', 'assigned', and 'discussed' and naming owners, but stays somewhat process-level rather than offering copy-paste-ready output templates.

4 / 5

Workflow Clarity

A clear six-step numbered sequence with implicit quality checkpoints via the Evidence and Judgment Rules, but lacks an explicit validate-against-source feedback loop.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections with content appropriately placed and no nested references, though as a self-contained body it has no one-level-deep reference structure to demonstrate maximal signaling.

4 / 5

Total

17

/

20

Passed

Description

75%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, well-scoped description that clearly states what it does and when to use it with natural trigger phrases. It sits just below top marks due to slightly less comprehensive action enumeration and minor overlap with adjacent research skills.

Suggestions

Add a few more natural trigger synonyms (e.g., 'meeting recap', 'meeting notes summary') to broaden keyword coverage.

Tighten the 'when' clause into a single explicit 'Use when...' sentence to make the trigger guidance crisper and reduce overlap with research-synthesis.

DimensionReasoningScore

Specificity

Names the meeting-synthesis domain and several concrete actions ('decisions, action items, unresolved questions, risks, and follow-up artifacts'), but the action list is slightly less comprehensively enumerated than anchor 5.

4 / 5

Completeness

Explicitly answers both what ('turning meeting transcripts or notes into decisions, action items...') and when ('Use for prompts like...', 'Best when you have notes or a transcript...'), with the 'when' slightly less crisp than anchor 5's clean trigger phrasing.

4 / 5

Trigger Term Quality

Includes natural user phrases ('summarize this meeting', 'extract action items', 'what did we decide', 'draft the follow-up') that users would actually say, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Has a clear meeting-synthesis niche with distinct triggers, but carries minor overlap risk with research-synthesis for interview/diligence-call inputs based on the description alone.

4 / 5

Total

16

/

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.

Validation15 / 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
NateBJones-Projects/OB1
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.