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

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

Quality

Content

70%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-sequenced, actionable workflow with a strong feedback and triage loop, undermined by redundancy across three sections that repeat the same review triggers. Its single external dependency is broken — code-reviewer.md is absent from the bundle — which weakens both actionability and navigation at the critical dispatch step.

Suggestions

Ship code-reviewer.md in the bundle (e.g. under references/) or inline the reviewer prompt template so the dispatch step is self-contained and the dangling reference is resolved.

Merge 'Integration with Workflows' and 'Red Flags' into 'When to Request Review' and 'Act on feedback' to eliminate the repeated trigger lists and duplicated triage rules.

DimensionReasoningScore

Conciseness

When-to-review triggers are stated three times ('When to Request Review', 'Integration with Workflows', and the worked example), and 'Red Flags' repeats the triage rules from 'Act on feedback' (e.g. Critical/Important handling, push-back guidance). The body is mostly efficient but these redundant sections mean it could be tightened noticeably — anchor 3 rather than 4.

3 / 5

Actionability

Concrete bash commands (git rev-parse for BASE/HEAD SHAs), named placeholders with definitions, a specific tool/type ('task' tool, 'general-purpose' type), and severity-based triage make the guidance mostly executable. The gap keeping it from 5: the pivotal reviewer prompt template lives in 'code-reviewer.md', which is not present in the bundle, so the dispatch step cannot be executed as written.

4 / 5

Workflow Clarity

The three-step sequence (get SHAs → dispatch reviewer → act on feedback) is explicit and numbered, with severity checkpoints (fix Critical immediately, Important before proceeding), fix-before-continue rules, and a disagreement/recovery protocol — matching the clear-sequence-with-explicit-checkpoints-and-feedback-loops anchor.

5 / 5

Progressive Disclosure

Section headers are clear and the single external reference is plainly signaled ('fill template at code-reviewer.md', 'See template at: requesting-code-review/code-reviewer.md'), but that file does not exist anywhere in the bundle — navigation dead-ends at exactly the point where the needed detail lives. A dangling reference is more than the 'minor organization gaps' of anchor 4, so it sits at anchor 3.

3 / 5

Total

15

/

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 is a well-formed trigger clause with explicit 'Use when' guidance tied to real workflow milestones, but it omits the skill's core capability and its most distinctive keyword ('code review'). It reads as pure trigger context with a generic purpose appended, leaving specificity and completeness mediocre.

Suggestions

Lead with the concrete capability, e.g. 'Dispatches a code-reviewer subagent with BASE/HEAD SHAs to review completed work against its requirements' — this fixes both the missing 'what' and the generic action language.

Add the natural trigger phrases users would actually say: 'code review', 'review my changes', 'check my work before merge'.

Mention the review artifact (the diff between commits) to distinguish this skill from testing/QA skills that also 'verify work'.

DimensionReasoningScore

Specificity

The description names workflow milestones ('completing tasks, implementing major features, or before merging') but its only action phrase, 'verify work meets requirements', is generic — it never states the concrete capability (dispatching a code-review subagent against a diff). This matches anchor 2 (domain named, actions minimal/generic) rather than 3, which requires 1-2 concrete actions.

2 / 5

Completeness

The 'when' is explicit ('Use when completing tasks... or before merging') but the 'what' is only a vague purpose clause ('verify work meets requirements') with no statement of what the skill actually does. It exceeds anchor 2 ('only when present without what') yet falls short of anchor 4's concrete both-what-and-when.

3 / 5

Trigger Term Quality

'before merging' and 'implementing major features' are natural workflow triggers, but the phrases users would most naturally say — 'code review', 'review my changes', 'review the diff' — are absent. Some relevant keywords with missing common variations fits anchor 3.

3 / 5

Distinctiveness Conflict Risk

'verify work' and 'completing tasks' are broad enough to overlap with testing, QA, and general verification skills, though the merge context narrows the field — 'somewhat specific but could still overlap with similar skills' fits anchor 3.

3 / 5

Total

11

/

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

phatblat/dotfiles

Path

.agents/skills/requesting-code-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.