CtrlK
BlogDocsLog inGet started
Tessl Logo

diff-review

Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.

56

Quality

65%

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 ./plugins/_official/atoms/diff-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 compact, well-structured overview that specifies concrete output artifacts and a completion condition, but it presents the process implicitly rather than as a sequenced workflow and lacks an explicit validation checkpoint before the destructive rollback step. Progressive disclosure is excellent for a self-contained single-file skill.

Suggestions

Replace the scattered implicit flow with a numbered step sequence so the render → surface → capture → persist/rollback order is explicit.

Add an explicit validation checkpoint before the reject rollback (e.g. verify decision.json is well-formed and that affected files are within plan/steps.json files[] before running git restore).

Trim the editorial opener ("is worthless without a human-reviewable diff") to tighten conciseness toward a lean 5.

DimensionReasoningScore

Conciseness

The body is lean (~40 lines) and assumes Claude's competence — it never explains what a diff, GenUI, or unified diff is; minor editorial padding ("a code-migration / tune-collab handoff is worthless without a human-reviewable diff") keeps it at anchor 4 rather than 5.

4 / 5

Actionability

Concrete, actionable artifacts are specified: the output file tree, the decision.json schema with enumerated fields, the three top-level choices, and the rollback command "git restore"; the gap is that "raises a choice GenUI surface" is abstract about mechanism, matching anchor 4 (mostly executable guidance with minor gaps).

4 / 5

Workflow Clarity

The flow (inputs → diff/summary → surface → decision.json → accept writes handoffKind / reject rolls back) is implied across sections rather than listed as a sequence, and the destructive rollback via "git restore" lacks an explicit validate-before-act checkpoint, so per the destructive-operation cap workflow clarity is held at 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/scripts/assets absent) and is organized into clearly signaled sections (Inputs, Output, Convergence, Anti-patterns, Status), meeting the simple-skill exception for a top score; the only referenced paths are external implementation files noted for status, not navigational bundle references.

5 / 5

Total

16

/

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 concretely states what the skill does across three actions but omits any "Use when..." trigger guidance and leans heavily on internal jargon, which weakens trigger-term quality and caps completeness. It is distinct within its niche yet not maximally discoverable by natural user phrasing.

Suggestions

Add an explicit trigger clause, e.g. "Use when presenting accumulated patch edits for human accept/reject review in a code-migration or tune-collab handoff."

Soften jargon with natural synonyms users actually say ("review the diff", "accept or reject changes", "show me what changed") alongside the technical terms.

Include the file extensions or artifact names a user would reference (e.g. ".patch", "decision.json") to broaden trigger coverage.

DimensionReasoningScore

Specificity

Quotes three concrete actions — "Render the patch-edit run's accumulated changes as a reviewable diff", "surface it through a GenUI choice surface", "persist the user's accept / reject decision" — matching anchor 4 (several specific actions with minor gaps); not 5 because the actions lean on jargon ("GenUI choice surface", "artifact manifest") rather than plainly enumerated capabilities.

4 / 5

Completeness

The "what" is clear (render diff, surface choice, persist decision) but there is no "Use when..." clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3 — matching anchor 3 (clear what, when missing or only weakly implied).

3 / 5

Trigger Term Quality

Relevant keywords exist ("reviewable diff", "accept / reject decision") but they are embedded in heavy technical jargon ("GenUI choice surface", "artifact manifest", "patch-edit run"), missing the natural variations a user would say ("review my changes", "show me what changed"); not 2 because some natural terms are present, not 4 because coverage of natural phrasings is thin.

3 / 5

Distinctiveness Conflict Risk

"diff-review" occupies a clear niche (reviewing a patch-edit run's accumulated changes in a code-migration handoff) with low overlap risk; not 5 because the description lacks explicit distinguishing trigger phrases that would fully separate it from adjacent review/approval skills.

4 / 5

Total

14

/

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
nexu-io/open-design
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.