Perform an independent adversarial review of an integrated game or software project using reproducible runtime, visual, interaction, accessibility, determinism, and performance evidence.
Perform an independent adversarial review of an integrated game or software project using reproducible runtime, visual, interaction, accessibility, determinism, and performance evidence.
Use after a Project Forge slice enters review, before accepting a baseline, or when a project looks complete but its quality claims have not been independently verified.
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude CodeNot declared
CursorNot declared
CodexNot declared
GitHub CopilotNot declared
WindsurfNot declared
Gemini CLINot declared
ClineNot declared
OpenCodeNot declared
Repository health
LicenseLICENSE
Default branchmain
Open issues0
Status
Archived
Skill metadata
Parsed from SKILL.md frontmatter.
Version0.1.0
LicenseMIT
CompatibilityWorks with any agent. Browser, screenshot, audio, and profiling capabilities are optional, but unavailable evidence remains unverified.
More metadata
author
moinsen-dev
version
0.1.0
Package contents
Files included with this skill beyond the listing page.
skill mdSKILL.md3,474 B
docsSUMMARY.md384 B
History
First seen on skills.sh
First recorded snapshot · 1 installs
SKILL.md
Project Forge Review
Review the integrated result, not an implementer's summary. Be demanding, specific, reproducible, legally distinct, and honest about unavailable evidence.
Read [references/critic-protocol.md](references/critic-protocol.md) before reviewing.
Independence Check
Record:
reviewed slice and revision,
whether this context authored any reviewed code,
available runtime and capture capabilities,
required gates,
missing evidence.
If this context authored the implementation, do not issue final approval. Perform a useful self-review, label independence limited, and require another reviewer for acceptance.
Review Workflow
Read the project contracts and current assignment.
Inspect the worktree and identify the exact reviewed revision.
Build and run the integrated product.
Exercise the real player, user, or request path.
Reproduce every required named review state.
Inspect console, server, lifecycle, and failure behavior.
Review deterministic captures at representative viewports.
Inspect motion, audio, and timing when relevant.
Profile active worst-case scenarios when required.
Perform a blind A/B comparison when legal references are available.
Rank defects by severity and player or user impact.
Return PASS, REWORK, BLOCKED, or UNVERIFIED.
Do not edit the reviewed subsystem silently. The lead may explicitly assign a separate correction slice after the report.
Findings
Every finding must include:
severity: critical, high, medium, or low,
observable symptom,
exact reproduction,
evidence path or metric,
likely owning subsystem,
root-cause hypothesis clearly labeled as a hypothesis,
observable closing condition.
Aggregate repeated symptoms when one root cause explains them.
Verdict Rules
Return REWORK while any critical or high finding remains.
Return UNVERIFIED when a required claim lacks evidence or the environment cannot capture it.
Return BLOCKED only for a real external constraint after meaningful available review work is exhausted.
Return PASS only when:
all required states were exercised,
evidence belongs to the reviewed revision,
all applicable gates pass,
no critical or high defect remains,
originality and legal-distinctness checks pass,
residual risks are explicit.
Rework Loop
After corrections:
Rebuild the integrated product.
Reproduce the original defect.
Capture fresh evidence.
Rerun affected neighboring states.
Update rather than erase the finding history.
Issue a new verdict.
Do not lower the threshold because several iterations were required.
Output
Write or return a report using the schema and template in [references/critic-protocol.md](references/critic-protocol.md). Keep evidence status distinct from subjective scoring.