CtrlK
BlogDocsLog inGet started
Tessl Logo

requesting-code-review

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

52

Quality

58%

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/AI-Agents-Safe-Coding-Skills-claude/skills/requesting-code-review/SKILL.md

The canonical home for this skill is requesting-code-review in administrakt0r/AI-Agents-Safe-Coding-Skills

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 body is a clear, actionable playbook with concrete commands and a sensible review-request workflow, but it carries redundant sections, a tautological closing line, and an external template reference that cannot be verified against any bundle.

Suggestions

Remove the tautological 'When to Use' section and merge 'Integration with Workflows' into 'When to Request Review' to eliminate overlap.

Make the dispatch step copy-paste ready by showing the exact Task-tool invocation for the superpowers:code-reviewer subagent instead of only describing it.

Add an explicit validation checkpoint after acting on feedback (e.g., 're-run review only if Critical/Important changes were made') and ship the referenced code-reviewer.md template as a bundle file so the reference is verifiable.

DimensionReasoningScore

Conciseness

Sections are mostly efficient, but the closing 'When to Use' line ('applicable to execute the workflow...described in the overview') is tautological fluff and 'When to Request Review' overlaps with 'Integration with Workflows', matching 'Mostly efficient but includes some unnecessary explanation or could be tightened.'

3 / 5

Actionability

It gives executable git commands (`git rev-parse HEAD~1`, `git rev-parse HEAD`), named template placeholders, and a filled example, but the subagent dispatch itself is described abstractly rather than as a copy-paste command, matching 'Mostly executable guidance; concrete code or commands with minor gaps.'

4 / 5

Workflow Clarity

A clear 3-step sequence (get SHAs, dispatch, act on feedback) is paired with a Critical/Important/Minor triage checkpoint and push-back guidance, matching 'Clear sequence with most checkpoints present; minor validation gaps.' Not 5 because checkpoints are implicit rather than explicit validate-then-proceed steps.

4 / 5

Progressive Disclosure

Content is well-sectioned with a one-level reference to `code-reviewer.md`, but no bundle files exist to verify that reference and the example/red-flags material is inlined, matching 'Some structure...references present but not clearly signaled; content that should be separate is inline.'

3 / 5

Total

14

/

20

Passed

Description

53%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 correctly pairs an explicit 'Use when...' trigger with a stated goal, but the 'what' is vague and missing the natural keyword 'review', leaving it broad enough to risk overlap with adjacent skills.

Suggestions

Name a concrete action in the what, e.g. 'Dispatch a code-reviewer subagent to review your diff and catch issues'.

Add the natural trigger term 'review' / 'code review' so users searching for review help land on this skill.

Tie the trigger to a more distinctive cue (e.g. 'before merging a PR' or 'after implementing a feature') to reduce overlap with general testing/QA skills.

DimensionReasoningScore

Specificity

The only 'what' is the generic action 'verify work meets requirements'; no concrete actions (e.g., review diffs, dispatch a reviewer subagent) are named, matching 'Names the domain but actions are minimal or generic.' Not 3 because the named action is abstract rather than concrete.

2 / 5

Completeness

Both 'what' (verify work meets requirements) and 'when' (tasks, major features, before merging) are present with an explicit 'Use when...' clause; the when is concrete but the what is vague, matching 'Has both what and when; when could be more explicit or specific.' Not 5 because the what lacks concrete trigger phrases; not 3 because the explicit Use when clause keeps it uncapped.

4 / 5

Trigger Term Quality

It includes natural phrases like 'completing tasks' and 'before merging' but omits the most natural terms users say ('review', 'code review', 'check my work'), matching 'Some relevant keywords but missing common variations or synonyms.'

3 / 5

Distinctiveness Conflict Risk

'Verify work meets requirements' is broad and could overlap with testing/QA skills, and no marker like 'code review' or 'subagent' narrows the niche, matching 'Somewhat specific but could still overlap with similar skills.' Not 4 because nothing distinguishes it from related verification skills.

3 / 5

Total

12

/

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.