CtrlK
BlogDocsLog inGet started
Tessl Logo

visual-recap

Turn a PR, branch, commit, or git diff into a structured visual recap so a reviewer scans the shape of the change before reading raw lines. Use when asked to "recap this PR/branch", "show me what changed", or to summarize a large multi-file diff at a higher altitude than line-by-line review.

70

Quality

85%

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

75%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 well-structured, lean instruction-only skill with concrete output formats and a clear sequencing skeleton grounded by an accuracy rule. It lacks a worked example and an explicit feedback loop, which keep it at a solid-but-not-perfect 4 across dimensions.

Suggestions

Add one compact worked example recap (a small multi-file diff through the canonical skeleton) so the format guidance is copy-paste concrete rather than abstract.

Tighten the "Lean, But Substantial" section and drop or shorten the provenance/"Adapted from BuilderIO" line to remove restated framing.

Consider moving the detailed "Diff to Artifact Mapping" rules into a one-level-deep reference file (e.g. ARTIFACT-MAPPING.md) to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is dense and directive with no basic-concept padding, but a few passages restate the same idea (the "from a diff, not toward one" framing, the provenance line, and the "Lean, But Substantial" section restating the no-boilerplate rule) that could be trimmed.

4 / 5

Actionability

It gives concrete formats — a `was` column for schema tables, method/path/params API tables, `sk-•••`/`<redacted>` redaction, and numeric budgets (3-8 diffs, ~150 lines) — but provides no fully worked end-to-end example recap, leaving a minor gap.

4 / 5

Workflow Clarity

A clear top-to-bottom canonical skeleton is sequenced, and the Grounding Rule acts as an explicit accuracy checkpoint ("Never infer, round, or invent"; mark inferred items), but there is no validate→fix→retry feedback loop, leaving minor validation gaps.

4 / 5

Progressive Disclosure

The single file is well-organized into clearly headed sections with no nested or buried references and no bundle files to verify; at ~128 lines it exceeds the under-50-line simple-skill exception, and the long "Diff to Artifact Mapping" section is borderline material that could live in a reference file.

4 / 5

Total

16

/

20

Passed

Description

95%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 states a concrete capability, gives explicit "Use when" triggers with natural user phrasing, and occupies a distinct niche. The only minor gap is that it centers on one action (build a recap) rather than enumerating several, which leaves specificity just short of a perfect score.

DimensionReasoningScore

Specificity

"Turn a PR, branch, commit, or git diff into a structured visual recap" names the domain and a concrete core action across multiple input variants, but it is essentially one action rather than the several distinct actions the score-5 anchor calls for.

4 / 5

Completeness

It explicitly answers what ("Turn a ... diff into a structured visual recap") and when ("Use when asked to ... or to summarize a large multi-file diff") with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Quotes natural user phrasing — "recap this PR/branch", "show me what changed" — plus synonyms PR/branch/commit/diff, giving comprehensive coverage of the terms a user would actually say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

"Visual recap" of a PR/branch/commit/diff is a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tslateman/duet
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.