CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

multimodal-evidence

Extract and verify evidence from images, documents, and video without redundant inspection

Quality

76%

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 ./resources/skills/media/multimodal-evidence/SKILL.md
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: the procedure is clearly sequenced with a feedback loop and explicit final validation checkpoint, tool guidance is specific, and nothing pads the token budget. The only minor gap is the absence of a copy-paste example command for the named parsers.

DimensionReasoningScore

Conciseness

Every line carries actionable guidance — tool names ("python-docx", "pdftotext"), pitfalls, and verification checks — with zero explanation of concepts Claude already knows, fitting "Lean and efficient; assumes Claude's competence; every token earns its place".

5 / 5

Actionability

Concrete tool-level guidance ("python-docx or ZIP/XML inspection for DOCX, pdftotext or a PDF library for PDF") and anti-patterns ("Do not search binary office files with plain grep or cat") are actionable, but no executable example commands exist, so it is "Mostly executable guidance; concrete code or commands with minor gaps" rather than copy-paste ready.

4 / 5

Workflow Clarity

The six sequenced steps include a conflict-resolution feedback loop ("Resolve conflicts with one targeted reinspection") and an explicit validation checkpoint ("perform a final coverage check against every requested item"), reinforced by a dedicated Verification checklist — matching "Clear sequence with explicit validation steps; feedback loops for error recovery; checklists".

5 / 5

Progressive Disclosure

The skill is under 50 lines, no bundle files exist to reference, and sections (When to Use, Procedure, Pitfalls, Verification) are well organized, so per the simple-skill guideline it earns 5 with just well-organized sections and no external references needed.

5 / 5

Total

19

/

20

Passed

Description

50%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 states a clear 'what' across three media domains but omits any explicit 'when to use' trigger clause and the natural synonyms or file extensions users would say, leaving all dimensions at the midpoint. It reads as a capability summary rather than an invocation trigger.

Suggestions

Add an explicit trigger clause, e.g.: "Use when the user provides images, PDFs, scanned documents, screenshots, or video and asks to read, transcribe, or verify their content."

Enumerate concrete capabilities — OCR text extraction, reading tables and form fields, locating claims at timestamps — to lift specificity beyond two generic verbs.

Include natural synonyms and file extensions users say (PDF, DOCX, XLSX, MP4, screenshots, footage, OCR) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Extract and verify evidence from images, documents, and video" names the domain and two actions (extract, verify), matching the anchor "Names domain and 1-2 concrete actions, but not comprehensive". It is not 4 because it does not list several specific actions such as OCR, table extraction, or timestamp lookup.

3 / 5

Completeness

The 'what' is stated ("Extract and verify evidence from images, documents, and video") but there is no "Use when..." clause or equivalent trigger guidance; "without redundant inspection" describes a manner of working, not when to invoke the skill. Per judging guidelines, a missing 'Use when' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Keywords "images, documents, video, evidence" are natural, but common variations users actually say (PDF, screenshots, footage, OCR, file extensions) are missing, fitting "Some relevant keywords but missing common variations or synonyms". Not 4, since keyword coverage is not good-with-only-a-few-missing.

3 / 5

Distinctiveness Conflict Risk

Spanning three broad media domains ("images, documents, and video") creates overlap risk with image-analysis, PDF, and document skills, matching "Somewhat specific but could still overlap with similar skills". Not 4 because the evidence/verification framing differentiates it only mildly from those adjacent skills.

3 / 5

Total

12

/

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/media/multimodal-evidence/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.