CtrlK
BlogDocsLog inGet started
Tessl Logo

common-code-review

Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback.

51

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/common/common-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 compact and directive with a usable output template and checklist, but it is marred by corrupted fragments, undefined terms ('framework P0 rules', 'AC'), a broken code fence, triple redundancy across its cautionary sections, and three of five bundle files that are never referenced. Consolidating the redundant sections, repairing the format block, and wiring up (or removing) the orphaned references would materially raise quality.

Suggestions

Repair the corrupted artifacts: fix the '" this handle null?"' quote, expand 'AC', define or delete 'Enforce active framework P0 rules', and move the meta-instruction out of the output-format code fence so the template is copy-paste ready.

Consolidate Red Flags, Rationalization Prevention, and Anti-Patterns into one section; they restate the same three rules and cost tokens without adding guidance.

Reference or remove the orphaned bundle files: lenses.md, report.md, and request-template.md are never linked from SKILL.md, and the inlined checklist duplicates references/checklist.md.

Add a short numbered review sequence (read diff -> run checklist -> classify by severity -> emit output format) so the workflow is ordered rather than topic-grouped.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows, but the Red Flags, Rationalization Prevention, and Anti-Patterns sections repeat the same three ideas (style vs. behavior, evidence, no nitpicking) three times over. This matches anchor 3 ('mostly efficient but... could be tightened') rather than 4, which would have only minor trims needed.

3 / 5

Actionability

The output template ('[SEVERITY] [File] Issue Description / Why: / Fix:') and checklist items are concrete, but key execution details are broken or undefined: the malformed quote '" this handle null?"', 'Enforce active framework P0 rules' with no framework defined anywhere, the unexpanded 'AC', and a format block whose fence contains a stray meta-instruction and blank lines. Anchor 3 ('some concrete guidance but incomplete... missing key details') fits better than 4.

3 / 5

Workflow Clarity

No sequenced review process is given (read diff, run checklist, classify severity, emit the format); the sections are topic-grouped rather than ordered. The Red Flags 'Stop if...' conditions act as implicit self-check checkpoints, which holds this at anchor 3 ('sequence present but checkpoints missing or implicit') rather than dropping to 2.

3 / 5

Progressive Disclosure

references/checklist.md and references/output-format.md are real, one level deep, and linked from the body, but lenses.md, report.md, and request-template.md are never referenced from the body, and the inlined Review Checklist/Principles sections duplicate checklist.md content. Anchor 3 ('some structure... references present but not clearly signaled; content that should be separate is inline') fits; not 4 given the orphaned bundle files and duplication.

3 / 5

Total

12

/

20

Passed

Description

65%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 solid explicit 'Use when...' clause with natural trigger phrases and reasonable distinctiveness, but the capability statement is a single generic action padded with adjectives. Expanding what the review actually produces (severity-tagged findings, security/logic/efficiency checks, evidence-backed output) would lift specificity and completeness.

Suggestions

Replace adjective padding ('high-quality, persona-driven') with concrete capabilities, e.g. 'Conduct code reviews producing severity-tagged findings (BLOCKER/MAJOR/NIT) covering security, logic, efficiency, and test coverage.'

Add natural trigger variations users say: 'code review', 'pull request', 'diff feedback', 'review my changes'.

State the output artifact (e.g. a structured findings report with Why/Fix per issue) so the what is explicit rather than implied.

DimensionReasoningScore

Specificity

"Conduct high-quality, persona-driven code reviews" names the domain but offers only one generic action; "high-quality, persona-driven" are adjectives rather than concrete capabilities (no findings format, severity levels, security checks, or output artifacts). This matches anchor 2 ('Names the domain but actions are minimal or generic') rather than 3, which would require 1-2 distinct concrete actions.

2 / 5

Completeness

Both what ("Conduct... code reviews") and an explicit when ("Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback") are present with concrete trigger phrases. Not 5 because the what is thin: a single generic action with no scope of what the review covers, which anchor 5 requires to be clearly and fully explicit.

4 / 5

Trigger Term Quality

"reviewing PRs", "critiquing code quality", "analyzing changes", and "team feedback" are natural phrases users would say. Not 5 because common variations are missing: "code review" as a noun phrase, "pull request" spelled out, "diff", or "feedback on changes".

4 / 5

Distinctiveness Conflict Risk

The persona-driven framing is mostly distinct, but "reviewing PRs" and "analyzing changes" overlap with closely related generic PR-review skills, matching anchor 4 ('minor overlap risk with closely related skills') rather than 5's 'clear niche with distinct triggers'.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
HoangNguyen0403/agent-skills-standard
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.