CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

action-evidence-synthesis

Turn messages, meeting notes, and documents into sourced decisions, actions, dependencies, and risks

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 lean, well-structured instruction-only skill: clear trigger conditions, a concrete six-step procedure, explicit pitfalls, and a verification checklist, with no wasted tokens. Its only notable gap is the lack of a brief example output showing how a sourced action or decision line should look.

Suggestions

Add a short example output line showing the expected citation format, e.g. "Ship API v2 by Friday [Alice, standup 10-03, tentative owner: Bob]".

Optionally show one mini example of how to flag an unresolved conflict in the output so the reconciliation step is unambiguous.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and efficient: every section (When to Use, Procedure, Pitfalls, Verification) adds guidance Claude would not infer on its own, with zero padding or explanation of known concepts. This matches anchor 5 (lean and efficient; every token earns its place).

5 / 5

Actionability

The procedure gives concrete, directive guidance — "preserve stable source identifiers, authors, and timestamps", "preferring the newest authoritative record", "label every inference as tentative", "concise source references beside consequential claims" — which is actionable for an instruction-only skill. The minor gap is the absence of a concrete example output showing the citation/reference format, so it fits anchor 4 (mostly executable guidance with minor gaps) rather than anchor 5.

4 / 5

Workflow Clarity

The six numbered steps form a clear sequence (scope → gather → extract → reconcile → separate facts/inferences → produce), backed by an explicit Verification checklist and error-handling guidance ("keep unresolved conflicts visible instead of guessing"). This is a non-destructive synthesis task so no validation cap applies, and the explicit checklist plus conflict handling matches anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, has no need for external references (no references/, scripts/, or assets/ exist), and is organized into well-labeled sections. Per the rubric guideline for simple skills under 50 lines with no need for external references, this scores 5.

5 / 5

Total

19

/

20

Passed

Description

66%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 specific, third-person description with good natural trigger terms and a clear capability statement, but it omits any explicit "when to use" trigger clause, which caps its completeness. Adding a Use-when clause with synonyms like transcripts, action items, and meeting minutes would raise both completeness and trigger coverage.

Suggestions

Append an explicit trigger clause, e.g. "Use when information is scattered across messages, meeting notes, transcripts, or chat threads and the user needs action items, a status summary, or a decision brief."

Include common synonyms users would say — "transcripts", "action items", "meeting minutes", "chat history" — alongside the existing trigger terms.

Name the concrete output formats (action list, status summary, feasibility assessment, executive brief) in the description to sharpen the what.

DimensionReasoningScore

Specificity

"Turn messages, meeting notes, and documents into sourced decisions, actions, dependencies, and risks" names the domain and lists several concrete outputs (decisions, actions, dependencies, risks) with a sourcing qualifier. It goes beyond the 1-2 actions of anchor 3 but lacks the comprehensive action coverage of anchor 5, so anchor 4 is the best fit.

4 / 5

Completeness

The description clearly answers "what" (turns fragmented communications into sourced decisions, actions, dependencies, risks) but contains no "Use when..." clause or equivalent explicit trigger guidance. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; the input types only weakly imply the "when".

3 / 5

Trigger Term Quality

Natural terms "messages", "meeting notes", and "documents" are phrases users would genuinely say. However common variations are missing — "transcripts", "action items", "minutes", "chat history" — which the skill body itself uses, so it matches anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The niche — synthesizing fragmented communications into sourced decisions and action lists — is fairly distinct, though "messages" and "documents" give minor overlap risk with general summarization and document-handling skills. This matches anchor 4 (mostly distinct, minor overlap risk) better than anchor 5's minimal-conflict framing.

4 / 5

Total

15

/

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

odysseus-dev/odysseus

Path

resources/skills/communication/action-evidence-synthesis/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.