CtrlK
BlogDocsLog inGet started
Tessl Logo

diffs

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

60

Quality

70%

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 ./extensions/diffs/skills/diffs/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.

The body is a lean, actionable reference for the diffs tool with a clear mode-based workflow and no wasted tokens; its only gaps are the absence of a complete copy-paste example and explicit section headers.

Suggestions

Add one short concrete example showing a full diffs tool invocation (e.g. before/after with mode=file) and the subsequent message-tool delivery call to reach fully copy-paste-ready actionability.

Use lightweight section headers (e.g. '## Modes', '## Delivering the artifact') to make the already-organized structure explicit and improve navigability.

Optionally note how to verify the artifact was delivered (e.g. confirm the message tool returned a path) to add a light validation checkpoint for the delivery workflow.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: each line delivers a concrete mode, parameter, or integration step with no padding or explanation of basic diff concepts, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Guidance is concrete and executable with specific tool names, modes (view/file/both), and parameters (fileFormat=png|pdf, fileQuality standard|hq|print), but lacks a fully copy-paste-ready example call, leaving minor gaps versus a 5.

4 / 5

Workflow Clarity

A clear sequence exists (choose mode -> call diffs -> use details.viewerUrl with canvas or details.filePath with the message tool), and producing diffs is non-destructive so the validation cap does not apply; only minor implicit-checkpoint gaps keep it below 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, and content is topically organized by mode, but it lacks explicit section headers that would make the structure fully navigable, fitting the 4 anchor.

4 / 5

Total

17

/

20

Passed

Description

58%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 specific and names a distinct tool with concrete outputs, but lacks an explicit 'Use when...' trigger clause and broader keyword synonyms, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user wants a shareable diff, patch preview, or rendered change artifact instead of a manual edit summary.'

Broaden trigger terms with natural synonyms like 'patch', 'compare changes', or 'change preview' to improve keyword coverage.

Optionally mention concrete deliverable formats (e.g. '.png/.pdf artifact') to push specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the tool and lists concrete deliverables ("viewer URL, file artifact, or both"), giving several specific outcomes, but stops short of the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

The "what" is clear (produce real shareable diffs), but the "when" is only weakly implied via "instead of manual edit summaries" with no explicit 'Use when...' trigger clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

The natural term "diffs" is present and "manual edit summaries" is a recognizable phrase, but common variations like patch, compare, or changes are missing, matching the 'some relevant keywords but missing synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

Naming a specific "diffs tool" with a distinct niche (shareable diffs vs manual summaries) is mostly distinct with only minor overlap risk against general change-summary skills, fitting the 4 anchor rather than the clearly-niche 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
qsimeon/openclaw-engaging
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.