review-pack

Solid

Use after verify-gate returns `ready` and before finish-branch or any outward-facing action. Performs a self-review pass (Reflexion-style) — the skill critiques its own completed work against the spec and the plan, surfaces issues in order of severity, and presents the diff to the user for explicit sign-off. No outward-facing action runs until the user approves.

Code & Development 19 stars 1 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
43
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# review-pack ## Overview A structured self-review and user sign-off. The skill: 1. Re-reads the spec and the plan. 2. Reads the full diff from the isolation base to HEAD on the vibe branch. 3. Critiques its own work against the spec (not against abstract best practice — against *this* spec). 4. Presents a severity-ranked list of findings + the full diff + a sign-off prompt. 5. Waits for user approval before handing off. This is the last reasoning gate before the pipeline touches anything outside the isolated workspace. ## When to invoke - After `verify-gate` returns verdict `ready`. - `security-review` is a complementary optional gate (threat-model, not spec-conformance). Either or both may run after `verify-gate` and before `finish-branch`; there is no ordering dependency between them. - Before `finish-branch`, before any merge, PR, push, tag, or deploy. - When the user explicitly asks for a review of completed work. Do not invoke: - If `verify-gate` returned `not ready`. Review-pack is not a bypass. - If no commits exist on the vibe branch beyond the base — there is nothing to review. ## Prerequisites - Spec exists at the path recorded by the vibe run, `status: approved` in frontmatter. - Plan exists at the path recorded by the vibe run. - Verify-gate report exists with `verdict: ready`. - Vibe branch has at least one commit beyond the isolation base. If any prerequisite fails, stop and surface what is missing. ## Self-review procedure (Reflexion) Run through t...

Details

Author
rizukirr
Repository
rizukirr/vibekit
Created
4 months ago
Last Updated
yesterday
Language
JavaScript
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

security-review

Use after verify-gate returns `ready`, as an optional security pass over a vibe run's diff before finish-branch. Runs a tiered threat-model review — universal code-security checks on every diff, plus AI-artifact checks when the diff builds a skill, agent, prompt, or MCP server — quotes verbatim file:line evidence, scores findings, and hard-gates the handoff on CRITICAL/HIGH with a written-waiver escape. Peer to review-pack; both optional, either may run before finish-branch.

19 Updated yesterday
rizukirr
Code & Development Listed

vibe-review

Evidence-based code review skill — mandatory gate after every phase completes. Triggers on "review:" prefix, "review the code", "code review", "audit the codebase", "check code quality", "review phase N", "is the code ready", "quality check". Mandatory gate: Phase N cannot proceed to Phase N+1 without review passing with no P0 issues. Final phase review blocks deploy until all P0 and P1 issues are resolved. Acts as Senior Engineer, Architect, and Code Quality Auditor. Gracefully handles missing ARCHITECTURE.md — reviews against PLAN.md patterns instead. Automated checks adapt to project stack (not npm-only). Every finding backed by file path and line number. No vague feedback.

7 Updated today
aakashdhar
Code & Development Listed

review-it

Standalone implementation-review skill in the Agentic Engineering pipeline. Reviews a worktree, branch, or PR against a substantive, evidence-backed checklist and reports verified findings, a scoped clean result, or explicit limitations — never fixing what it finds. Callable standalone against any worktree, branch, or PR with no prior implement-it session or plan-it-authored issue required; also callable by implement-it before Gate 1 and during an authorized delivery correction. Trigger to review implemented code, review a branch or PR, or verify a correction before it's relied on. Reports only — it never fixes application code, applies formatting fixes, commits, pushes, approves a gate, merges, or mutates GitHub or other live/production state; every correction returns to implement-it. Does not own guide review, issue/plan-synthesis review, investigation discipline, or commit-plan review — those stay with document-it, plan-it, lab-it, and implement-it.

0 Updated today
elieandraos