Agent skill · Security

ln-12-delivery-reviewer

Reviews a completed scoped change and its affected runtime and contract paths. Use to find change-caused defects and verify readiness; not for codebase audit, implementation, or repair.

levnikolaevichgithub.com/levnikolaevichGitHub ↗
claude-codecodexMIT
Install
npx skills add levnikolaevich/claude-code-skills --skill ln-12-delivery-reviewer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 28 KB
Bundled scripts: none
Path: plugins/review-suite/skills/ln-12-delivery-reviewer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 528
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Reviews a completed scoped change and its affected runtime and contract paths. Use to find change-caused defects and verify readiness; not for codebase audit, implementation, or repair.

How it works

  • Treat the ordered checkbox workflow as the Definition of Done and work through every item in order.
  • Mark each item complete only when action and required evidence are complete; otherwise leave incomplete and provide specified notes.
  • Before returning, apply verdict rules to every incomplete item and prepend a Checklist line indicating completion status and next actions.
  • Use a structured tool-routing scheme to gather evidence: read repository state, inspect diffs, verify definitions and consumers, run automated verification if available, observe behavior, perform correction research if needed, and conduct an independent review with limited subagents.
  • For each evidence question, rely on reproduced behavior, changed code paths, acceptance criteria, and official contracts as the strongest proof; document evidence and impact for each finding.
  • Include an Independent Review Panel approach where lenses (specialist viewpoints) are selected to inform the verdict; limit rounds and subagents per the two-round budget.

When to use it

• When evaluating a completed scoped change to determine if it meets acceptance and release safety criteria. • When verifying the causal paths from change to business outcome and ensuring no unrelated code is implicated.

What it can touch

  • Tools: claude-code, codex
  • States: reads repository state, diffs, citations to definitions and consumers, and evidence artifacts

Caveats

  • This skill explicitly avoids auditing unrelated code, implementing repairs, or widening scope beyond the requested delivery change.
  • It requires confirming that evidence supports acceptance criteria and that the path from change to outcome is properly evidenced; otherwise items remain incomplete.
From the SKILL.md

# Delivery Reviewer **Goal:** Review only the requested delivery change and the causal paths needed to prove its business outcome. Judge scoped acceptance and release safety with concise evidence; do not audit unrelated code, repair findings, update trackers, or widen scope. **Execution contract:** Treat the ordered checkbox workflow below as this skill's Definition of Done. Work through every item in order, and mark it complete only when its action and required evidence are complete. `N/A`, skipped, unavailable, or delegated items remain incomplete. Before returning, apply this skill's verdict, decision, and approval rules to every incomplete item and prepend **Checklist: X/Y complete**<br>**Incomplete: None | section/item — reason; outcome impact; exact next action**; list every incomplete item. ## Tool Routing | Need | Preferred capability | Use when | Fallback | |---|---|---|---| | Scope and repository state | Native file reads plus Git | Establishing outcome, non-goals, base, head, and worktree | Supplied requirements with explicit limitations | | Changed behavior | Diff, status, and focused reads | Resolving the implementation delta and entrypoints | Compare supplied artifact

What's inside
Steps it walks through
  1. Tool Routing
  2. Evidence Rules
  3. Independent Review Panel
  4. Checklist
  5. 1. Establish Business and Change Scope
  6. 2. Trace Requirements into Implementation
  7. 3. Review Safety, Contracts, and Simplicity
  8. 4. Verify Tests, Documentation, and Operations
  9. 5. Challenge and Synthesize
  10. Output Contract
More from claude-code-skills
All skills →
About this skill
What does the ln-12-delivery-reviewer skill do?

Reviews a completed scoped change and its affected runtime and contract paths. Use to find change-caused defects and verify readiness; not for codebase audit, implementation, or repair.

How do I install it?

Run `npx skills add levnikolaevich/claude-code-skills --skill ln-12-delivery-reviewer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From levnikolaevich/claude-code-skills, a repository with 528 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going