CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hunk-review

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.

Quality

92%

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

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.

An exemplary pointer skill: minimal, fully executable, and version-synced by delegating instructions to the installed CLI, with explicit fallbacks for older versions and missing installs. The single deduction is the version-pinned compat note ("before 0.24") sitting outside a deprecated/old-patterns section, which ages poorly.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — "This file is a pointer. The instructions live in the installed `hunk` CLI so they always match its version" — with zero padding. However, "Hunk versions before 0.24" is time-sensitive version-pinned information not placed in a deprecated/old-patterns section, which the guidelines penalize; otherwise this would be a 5, and there is no verbosity that would justify a 3.

4 / 5

Actionability

Fully executable, copy-paste-ready commands covering the common cases: `hunk skill show hunk-review`, the fallback `hunk skill path hunk-review`, and the install URL for when the CLI is missing. This matches the anchor for copy-paste ready commands whose examples cover the common cases; a 4 would require minor gaps in the commands or coverage.

5 / 5

Workflow Clarity

The sequence is unambiguous with explicit error-recovery branches: "If it fails, print the bundled skill's path instead, then read that file and follow it" and "If `hunk` is not on PATH, ask the user to install Hunk first". Per the simple-skill guidance, a single unambiguous action with these feedback loops scores 5, and no destructive or batch operations are involved.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and defers all detail one level deep to the CLI at runtime — the ideal pointer pattern. Well-organized with a clear primary path and fallbacks; this fits the clear-overview, one-level-deep reference anchor rather than the minor-gaps 4 anchor.

5 / 5

Total

19

/

20

Passed

Description

88%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 strong description: third-person, action-dense, with an explicit and concrete "Use when..." clause anchored to the Hunk tool. The only notable gap is keyword coverage — common review phrasings like "code review" or "PR review" are absent, leaving slight trigger overlap risk with generic review skills.

DimensionReasoningScore

Specificity

Lists six concrete actions covering the full session lifecycle — "Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges" — all in third-person verb form. This matches the anchor for multiple specific concrete actions with comprehensive coverage; a 4 would require minor gaps in coverage, which are not evident.

5 / 5

Completeness

Explicitly answers both questions: the what is the concrete action list, and the when is the explicit clause "Use when the user has a Hunk session running or wants to review diffs interactively" with two concrete trigger conditions. A 4 would require the when-clause to be less explicit or specific than it is here.

5 / 5

Trigger Term Quality

Includes natural phrases users would say such as "Hunk session running", "review diffs", and "inline review comments", but misses common variations like "code review", "PR", or "pull request review". This fits "good keyword coverage; a few natural terms missing" rather than the comprehensive synonym coverage of a 5, and exceeds the partial coverage of a 3.

4 / 5

Distinctiveness Conflict Risk

The tool-specific framing ("live Hunk diff review sessions via CLI", "Hunk session running") carves a clear niche, but the generic trigger "wants to review diffs interactively" carries minor overlap risk with general code-review skills. Mostly distinct with minor overlap risk fits better than the minimal-conflict 5 anchor, and well above the overlap-prone 3 anchor.

4 / 5

Total

18

/

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

modem-dev/hunk

Path

.agents/skills/hunk-review/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.