CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

common-code-review

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

Quality

71%

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 ./.agents/skills/common/common-code-review/SKILL.md

The canonical home for this skill is common-code-review in HoangNguyen0403/agent-skills-standard

SKILL.md
Quality
Evals
Security

Code Review Expert

Priority: P1 (HIGH)

Role: Principal Engineer / senior review. Focus: logic, security, architecture. constructive.

Review Principles

  • Substance > style. Find behavioral, security, and design defects; do not nitpick.
  • Findings first; no strengths or praise section. Every finding cites evidence and explains risk.
  • Deterministic gate: a current orchestrator-observed required-check FAIL returns CHANGES REQUESTED before semantic lens review. Missing, unknown, NOT RUN, or stale status is an evidence gap, never PASS.
  • Blind first: phase one receives only the brief, cumulative diff, and orchestrator-observed check receipt. Freeze findings and SHA-256 before author claims; this declared sequence is not filesystem isolation.
  • Reproduce only when every provenance, host-enforced isolation, verified prevention of shared-worktree writes, no-credentials/no-publication, default-deny-network, and orchestrator-published-command predicate is verified. Otherwise stay static-only and name the gap; never execute author-controlled commands in a privileged reviewer runtime.
  • Compare authorized reproduction command, output, and source identity with the receipt. Observed/claimed mismatch is a Blocker.
  • Reconcile: resume the same reviewer with frozen findings and digest plus author claims. If resume is unavailable, BLOCKED; replacement requires restarting the full blind phase.
  • Review completeness includes test and edge-case coverage even when CI is green or the request is quick.
  • Test-Review Evidence Gate: before a missing-test Major, identify the changed contract, plausible consumer-visible escaped fault, and evidence nearby/upstream suites do not cover it. One logical contract per test; do not demand tests per symbol.
  • Independence and host provenance are verified separately; self-approval is forbidden. Missing optional metadata is a recorded gap; missing required scope evidence blocks approval.
  • For complete phases and formats, load Adversarial Review Protocol. Load orchestration when ticket/AC, PR metadata, or specialist lenses are needed.

Review Checklist (Mandatory)

  • Security: No injection, secrets, auth leaks.
  • Efficiency: No N+1 queries, memory leaks, high Big O.
  • Logic: Requirements met. Edge cases handled.
  • Clean Code: DRY/SOLID. Intent-revealing names.

See references/checklist.md.

Output Format (Strict)

Use only [Blocker], [Major], or [Nit]. Each substantive finding has Evidence:, Why:, Fix:, and Prevent-by: lint | type | test | eval | runtime | guidance | none; missing code/diff means state the evidence needed. No praise section. See finding template.

Red Flags

  • Stop if you are praising before reviewing: Start with findings.
  • Stop if a claim lacks evidence: Mark it as assumption or inspect more.
  • Stop if you are reviewing style only: Return to behavior, security, tests.

Rationalization Prevention

  • "It probably handles that edge case": Probably is not evidence.
  • "CI is green so review is done": Tests do not replace review.
  • "Only style matters here": Ignore style, not behavioral risk.

Anti-Patterns

  • No Nitpicking: Ignore style; focus on impact.
  • No Vague Demands: Explain why and how.
  • No Skimming: Review tests and edge cases.

References

Repository

HoangNguyen0403/agent-skills-standard

Path

.agents/skills/common/common-code-review/SKILL.md

Last updated
First committed

Canonical home

HoangNguyen0403/agent-skills-standard
In sync

since Apr 14, 2026

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.