CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sdlc-code-review

Language-agnostic workflow for code reviews and security audits using a Two-Axis (Standards vs Spec) approach against Clean Code/SOLID principles, generating formal refactoring plans.

Quality

71%

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/sdlc-code-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

66%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 delivers an exceptionally clear, well-checkpointed workflow with concrete commands and complete templates, and it externalizes domain depth into four real, one-level-deep reference files. Its main weaknesses are significant redundancy (triple-stated pushback rules, persona theatrics, duplicated Overview) and the inlining of the large plan template that belongs in a reference file.

Suggestions

State the pushback rule and /sdlc-write-code handoff once in a single Boundary section and reference it from Phases 2-4 instead of repeating it three times.

Remove the persona-activation theatrics ("CRITICAL SYSTEM OVERRIDE", commanded identity shift, session-lock rules) and the duplicative Overview section; they add tokens without adding instruction.

Move the Mandatory Refactoring Plan Template (~80 lines) into a reference file such as PLAN-TEMPLATE.md, keeping SKILL.md as an overview with a clearly signaled link, consistent with the other four references.

DimensionReasoningScore

Conciseness

Noticeably verbose: persona theatrics ("CRITICAL SYSTEM OVERRIDE", "YOU ARE HEREBY COMMANDED TO STOP ACTING AS A GENERAL ASSISTANT"), an Overview that restates the persona section, and the pushback/handoff rule repeated three times (Core Directives, Boundary & Pushback Rules, Phase 4). Several padded sections that assume Claude needs role-play framing it does not.

2 / 5

Actionability

Highly concrete: the exact diff command "git diff <fixed-point>...HEAD" (three-dot, against the merge-base), explicit sub-agent prompt instructions, verbatim report and plan templates with task tables, and exact pushback wording. Minor gap: it depends on environment-specific tool names ("invoke_subagent", "view_file", "write_to_file") that may not exist in the executing harness, keeping it below fully copy-paste ready.

4 / 5

Workflow Clarity

Clear sequence with explicit validation and feedback loops: Phase 1's five steps include "Confirm the diff is non-empty before proceeding" and Step 5 "Verify the Verification"; missing inputs trigger asking the user; Phase 2 is skipped when no critical/required issues exist; Phase 3 is an explicit remediation loop updating plans from audit reports; templates embed VERIFY/APPROVAL checkpoints and severity-label checklists.

5 / 5

Progressive Disclosure

A dedicated "Mandatory References" section describes all four reference files, each of which exists in references/ and is one level deep (no nested references verified). However, roughly 120 lines of templates are inlined in the body — the 80-line Mandatory Refactoring Plan Template is a strong candidate for its own reference file, which is a moderate organization gap rather than a minor one.

4 / 5

Total

15

/

20

Passed

Description

62%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 specific and third-person with a clear articulation of what the skill does, but it completely lacks a 'Use when...' trigger clause and misses common natural trigger phrases like "PR review" or "pull request". Its core triggers overlap broadly with generic code-review skills, leaving moderate conflict risk.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to review code, a diff, a pull request, or a branch, or requests a security audit or refactoring plan."

Include natural trigger variations users actually say: "PR review", "pull request", "code quality", "audit my code", not just "code reviews and security audits".

Sharpen distinctiveness by stating what this skill alone does (e.g., produces a formal refactoring plan document in plan/ rather than applying fixes), so it does not fire for general review requests.

DimensionReasoningScore

Specificity

Lists several concrete actions ("code reviews", "security audits", "generating formal refactoring plans") with a named methodology, but coverage has minor gaps (spec-compliance checking, report format, and sub-agent orchestration are not mentioned). Fits the 'several specific actions, minor gaps' anchor rather than 3 (more than 1-2 actions) or 5 (not comprehensive).

4 / 5

Completeness

The 'what' is clear (workflow for code reviews/security audits generating refactoring plans) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the 'what' is specific rather than vague; not 4 because 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Natural phrases users would say are present ("code reviews", "security audits", "refactoring"), but common variations like "PR review", "pull request", and "code quality" are missing. Good keyword coverage with a few natural terms absent, so not 5.

4 / 5

Distinctiveness Conflict Risk

"Two-Axis (Standards vs Spec) approach" and "generating formal refactoring plans" carve a niche, but the primary triggers "code reviews" and "security audits" are broad and overlap with many generic review skills, with nothing signaling when to choose this one. Somewhat specific but with real overlap risk, so not 4.

3 / 5

Total

14

/

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

glenrioariesto/social-content-studio

Path

.agents/skills/sdlc-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.