CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Quality

60%

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 ./.claude/skills/requesting-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 maximally lean redirect stub, which is excellent for token efficiency but provides almost no actionable content: the entire skill substance lives in an external, non-bundled file. The dangling `scripts/agent-harnesses.py` reference further signals that the bundle is incomplete as a standalone skill.

Suggestions

Bundle the actual guidance (or a meaningful summary of it) inside the skill directory instead of pointing to an external home-directory path that may not exist on other machines.

Remove or correct the stale `scripts/agent-harnesses.py` reference, since no scripts directory ships with this bundle.

Add at least a minimal inline outline of the review-request process (what to include, where to post it) so the skill degrades gracefully if the external path is unavailable.

DimensionReasoningScore

Conciseness

The body is two lines with zero padding and no explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

"Load and follow the shared skill at `~/.agents/skills/requesting-code-review/SKILL.md`" is a concrete pointer, but it contains no steps, commands, or guidance for the skill's actual task — everything is delegated elsewhere.

2 / 5

Workflow Clarity

The single load-and-follow instruction is unambiguous, but the actual workflow is entirely deferred to an external home-directory path outside the bundle, and no validation checkpoints of any kind are present.

3 / 5

Progressive Disclosure

The sole reference is one level deep and clearly signaled, but it points outside the bundle to `~/.agents/skills/`, no references/scripts/assets files exist, and the comment's `scripts/agent-harnesses.py` refers to a file that is not present.

3 / 5

Total

13

/

20

Passed

Description

45%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 has a clear and explicit trigger clause but never states what the skill actually does, relying on a single vague purpose clause. It also omits the most natural trigger terms ("review", "PR", "code review"), which limits both discoverability and distinctiveness.

Suggestions

State the "what" explicitly, e.g. "Requests a code review of completed work by preparing a review request with the diff, context, and verification steps."

Add natural trigger terms users would actually say, such as "code review", "review my changes", "PR", or "pull request".

Replace the overly broad "completing tasks" trigger with something narrower like "finishing a coding task" to reduce conflict risk with unrelated skills.

DimensionReasoningScore

Specificity

The only action phrase is the generic "verify work meets requirements"; "completing tasks", "implementing major features", and "before merging" are triggers rather than capabilities, so the description names a domain with minimal actions.

2 / 5

Completeness

The "when" is explicit and multi-triggered ("Use when completing tasks, implementing major features, or before merging"), but the "what" exists only as the vague purpose clause "to verify work meets requirements" — what the skill actually does is never stated.

3 / 5

Trigger Term Quality

Phrases like "before merging" and "implementing major features" are natural user language, but the central terms a user would actually say for this skill ("review", "code review", "PR", "check my work") are entirely absent.

3 / 5

Distinctiveness Conflict Risk

"Completing tasks" is an entirely generic trigger that would fire alongside nearly any skill, though "before merging" and "implementing major features" narrow it to development workflows with residual overlap risk against related review/testing skills.

3 / 5

Total

11

/

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.claude/skills/requesting-code-review/SKILL.md

Revision

4d65cab

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill