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

62%

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

63%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 skill body is actionable and clearly sequenced, with executable commands and a useful worked example. Its weaknesses are redundancy (when-to-review rules stated three times, boilerplate closing sections) and a referenced template file that is absent from the bundle and inconsistently pathed. Tightening the repeats and shipping or fixing the template reference would lift it further.

Suggestions

Merge the duplicated trigger guidance: 'Integration with Workflows' repeats 'When to Request Review' almost verbatim — consolidate into one section or a short table.

Remove the generic 'When to Use'/'Limitations' boilerplate at the end, which adds no skill-specific information.

Fix the template reference: either include code-reviewer.md in the bundle (e.g. under references/) and cite one consistent path, or inline the dispatch template directly in SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly efficient (terse lists, shell commands, placeholder definitions), but when-to-review guidance is repeated across 'When to Request Review', 'Integration with Workflows', and the Example, and the trailing 'When to Use'/'Limitations' sections are boilerplate padding ('This skill is applicable to execute the workflow or actions described in the overview'). More than minor trimming is needed, so this sits at anchor 3 rather than 4.

3 / 5

Actionability

Concrete, executable guidance throughout: copy-paste-ready git commands, an enumerated placeholder list, severity-based triage rules, and a fully filled-in example. It falls short of anchor 5 because the dispatch step depends on an external template file rather than a literal Task-tool invocation, leaving a minor gap.

4 / 5

Workflow Clarity

A clear three-step numbered sequence (get SHAs → dispatch reviewer → act on feedback) with explicit triage checkpoints for Critical/Important/Minor issues. Below anchor 5 because there is no re-review/validation loop confirming fixes before proceeding, only the instruction to fix issues.

4 / 5

Progressive Disclosure

Section headers are clear, but the referenced template file 'code-reviewer.md' does not exist in the bundle (no references/ or scripts/ directories) and is cited via two inconsistent paths ('code-reviewer.md' and 'requesting-code-review/code-reviewer.md'). A dangling, ambiguously-signaled reference with content that belongs in the missing file fits anchor 3 rather than 4.

3 / 5

Total

14

/

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 provides clear trigger timing but never states what the skill does, omitting even the word 'review'. It reads as a pure 'when' clause with a generic purpose tail. Adding the concrete action (requesting/dispatching code review) and natural terms like 'code review' or 'PR' would substantially improve it.

Suggestions

State the concrete action in the description, e.g. 'Requests code review by dispatching a code-reviewer subagent...' so the 'what' half is explicit rather than just 'to verify work meets requirements'.

Include the natural trigger terms users actually say — 'code review', 'review my code', 'pull request' / 'PR' — since the skill's core domain term is currently absent.

Trim the overly broad 'completing tasks' trigger or narrow it (e.g. 'after completing a coding task') to reduce overlap with testing/validation skills.

DimensionReasoningScore

Specificity

The description contains no concrete actions — phrases like 'completing tasks' and 'verify work meets requirements' are generic, and the actual capability (dispatching a code-reviewer subagent) is never stated. It names a loose verification/merge domain but actions are minimal, matching anchor 2 rather than anchor 1 only because the domain is at least implied.

2 / 5

Completeness

The 'when' is explicit and strong ('Use when completing tasks, implementing major features, or before merging'), but the 'what' is only a vague purpose clause ('to verify work meets requirements') with no statement of what the skill actually does. This is the mirror of anchor 3 — one half explicit, the other weak — and clearly below anchor 4, which requires both what and when.

3 / 5

Trigger Term Quality

'completing tasks', 'implementing major features', and 'before merging' are phrases users would naturally say, but coverage misses the most obvious triggers for this skill — 'code review', 'review my code', 'PR', or 'feedback'. Some relevant keywords with common variations missing fits anchor 3; it is below anchor 4 because the core term 'review' is entirely absent.

3 / 5

Distinctiveness Conflict Risk

'before merging to verify work meets requirements' carves out a dev-workflow QA niche, but 'Use when completing tasks' is broad enough to overlap with testing, validation, and CI skills. Somewhat specific yet still overlapping with similar skills fits anchor 3; it does not reach anchor 4 because the missing 'code review' terminology makes it hard to distinguish from generic verification 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BigSimmo/Communication

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.