AgentStack
SKILL verified Apache-2.0 Self-run

Doncheli Review

skill-doncheli-don-cheli-sdd-doncheli-review · by doncheli

Perform strict 7-dimension peer review analyzing correctness, tests, performance, architecture, security, style, and diff cleanliness. Activate when user mentions "review", "revisar", "peer review", "code review", "check my code".

No reviews yet
0 installs
8 views
0.0% view→install

Install

$ agentstack add skill-doncheli-don-cheli-sdd-doncheli-review

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Doncheli Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Don Cheli: 7-Dimension Peer Review

Dimensions

  1. Functional Correctness — All Gherkin P1/P2 scenarios implemented
  2. Tests & Coverage — Unit, integration, BDD tests pass; coverage >= 85%
  3. Performance — No N+1 queries, no unbounded queries, no O(n^2) where avoidable
  4. Architecture & Design — SOLID principles, separation of concerns, DI
  5. Security — Input validation, parameterized queries, no hardcoded secrets, auth on all protected endpoints
  6. Style & Conventions — Consistent naming, no unused imports/vars, no console.log
  7. Clean Diff — Only changes related to the feature

Adversarial Rule

You MUST find at least 1 concrete issue in every review. Zero findings triggers a mandatory second pass focused on: N+1 queries, race conditions, untested edge cases, sensitive data in logs, naming inconsistencies.

Output Format

For each finding: ID, severity (Critical/High/Medium/Low), file:line, description, suggested fix.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.