CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

backend-code-review

Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A tight, well-structured instruction-only skill: an evidence-first workflow, deterministic routing to shared guides, and a concrete severity/output contract with no wasted tokens. Its minor gaps are the absence of an example finding and references that point outside the skill's own bundle.

DimensionReasoningScore

Conciseness

The body is lean with zero padding: every line instructs (e.g., "Trace callers, persistence boundaries, authorization, generated schemas, or external I/O only when they decide correctness") and assumes Claude's competence. No section could be trimmed without losing instruction, matching the "every token earns its place" anchor.

5 / 5

Actionability

Concrete, executable guidance throughout: the diff-matched routing table, the P0–P3 severity taxonomy with explicit criteria, and the output spec "Include a tight file and line reference, the failing contract or reproduction path, impact, and a concrete fix direction". It stops short of 5 because no example finding is shown, so the exact output shape is described but not exemplified.

4 / 5

Workflow Clarity

"Evidence First" provides a clear numbered sequence (establish scope → read changed lines and contracts → trace only what decides correctness → report only evidence-tied findings), gated by "Report only findings tied to an observable failure". Not 5 because there is no explicit verify-before-report feedback loop (e.g., re-confirming the reproduction path for each finding).

4 / 5

Progressive Disclosure

References are well signaled and one level deep, each labeled and routed by diff content ("[Database schema][db-schema]", "[SQLAlchemy][sqlalchemy]"). However, the four targets live outside the skill bundle at "../../../docs/" and could not be verified to exist, a minor organization and portability gap that keeps it below the clear in-bundle navigation of the 5 anchor.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: it combines an explicit positive trigger, three named review modes, and explicit negative boundaries in a concise third-person form. The only weakness is that the concrete capabilities stop at review modes without stating the review's output, which costs it specificity points.

DimensionReasoningScore

Specificity

"Supports pending-change, file-focused, and pasted-diff reviews" lists several concrete review modes within a clearly defined scope. It falls short of 5 because it never states what the review produces (e.g., severity-ranked findings), leaving minor coverage gaps.

4 / 5

Completeness

"Use only when the user explicitly requests a review or audit of backend code under `api/`" provides explicit trigger guidance, "Supports pending-change, file-focused, and pasted-diff reviews" states the what, and "Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside `api/`" adds concrete negative triggers. Both what and when are answered explicitly.

5 / 5

Trigger Term Quality

Natural terms users would say are present: "review or audit", "backend code", "pasted-diff", "pending-change", "diff". A few common variations ("code review", "PR review", "critique") are missing, so it sits between "some relevant keywords" (3) and comprehensive synonym coverage (5).

4 / 5

Distinctiveness Conflict Risk

The scope is tightly niched to "backend code under `api/`" with explicit exclusions (frontend code, implementation-only requests, backend code outside `api/`), giving distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

18

/

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

langgenius/dify

Path

.agents/skills/backend-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.