forge-review
Skill13 starsChanged 44 days agoMITView on GitHub
Judge an exact integrated candidate against accepted intent, applicable engineering/design/quality/security/performance risks, and pragmatic craft. Use for "Forge review", PR review, local Forge loop review, or code/branch/diff review selected through Forge. Read-only; direct Review ends at its report. Explicit standalone code-only review uses forge-code-review instead.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- antonailog/forge-skillstheir own version, first seen Oct 25, 2026
- fabioalencar/forgedesigntheir own version, first seen Oct 20, 2026
- peterzat/OrgSmiththeir own version, first seen Oct 13, 2026
- yike-gunshi/forge-skillstheir own version, first seen Oct 13, 2026
- KhaledAufDB/lakeforgetheir own version, first seen Oct 13, 2026
- BrandedTamarasu-glitch/ForgeFlowtheir own version, first seen Oct 11, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- antonailog/forge-skills★ 13same name
- yike-gunshi/forge-skills★ 13same name
- peterzat/OrgSmith★ 6same name
- tonmoy007/forge-plugins★ 2same name
- BrandedTamarasu-glitch/ForgeFlow★ 1same name
- fabioalencar/forgedesign★ 1same name
- khaledayeva/star-forge★ 1same name
- redteamlife/forge★ 1same name
- tinyorbit-ai/skills★ 1same name
- tusharpandey13/forge★ 1same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- forge-buildSkill
- forge-code-reviewSkill
- forge-planSkill
- forge-shipSkill
- forge-simplifySkill
- forgeSkill
- forge-specSkill
- forge-verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Run this phase only when explicitly invoked through Forge, selected by the caller, or reached by an authorized Forge lifecycle.
- Distinctive: line 53
Use the shared return contract.
- Distinctive: line 64
Use the existing review artifact template when a separate artifact is earned.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Forge Review
<skill name="forge-review">
<activation>
Run this phase only when explicitly invoked through Forge, selected by the caller,
or reached by an authorized Forge lifecycle. Ordinary unselected requests do not
activate portable Forge.
Reuse accepted Launch/authority on resume. Stop at this phase's boundary; an
installed machine name is not evidence of native slash-command support.
An explicitly requested standalone code-only review or `forge-code-review` selects
the [Code Review leaf](../forge-code-review/SKILL.md) directly and stops there.
</activation>
<setup>
Read [authority](../forge-shared/references/authority.md) and
[target harness resolution](../forge-shared/references/target-harness.md), [Launch and gates](../forge-shared/references/workflows.md),
and the target repository's applicable root/nested harness. Adopt
[Reviewer](../../agents/reviewer/instructions.md) as primary professional guidance.
Reviewer owns dimension coverage and the integrated verdict. Focused Judges remain read-only helpers; their findings cannot create scope.
</setup>
<workflow>
<step n="1" name="Bind the assignment">
Identify the accepted outcome/source revision, selected workflow/depth/control,
requested boundary, actual candidate/state, allowed writes, required proof, and
material unresolved choices. A direct bounded read-only Review request authorizes
inspection and its prepared report: briefly state scope, team and boundary, then
proceed under the shared direct-Review Launch exception. Preserve existing
consequential intent/authority gates; do not ask permission again for the requested
review. Other lifecycle entries show or reuse their accepted Launch.
</step>
<step n="2" name="Perform the phase">
Select one entry by the requested review target and read only its reference:- Pull request, including a PR backed by a Forge loop: PR review.
- Local Forge loop or its integrated candidate: local loop review.
- Code, branch, commit, or diff without a PR/loop: standalone review.
The selected entry supplies intake and reporting; all use the same
owning procedure, loading only applicable
support and professionals. Select and load the actual judge rubrics,
including practical Security/Performance where applicable. When Code Review applies,
the Reviewer directly reads and follows the selected Code Review leaf
or passes that exact selected path to a required delegated Judge. Both read the
actual applicable target app standards and check paths. Record the selected source
and inspected standards/evidence in the existing report; preserve delegated
originals and inspect their evidence before disposition.
</step>
<step n="3" name="Inspect and return">
Use the shared return contract. The
accountable owner opens the actual result and relevant new log entries before
advancement, checking the selected template/rubric, candidate, actual evidence,
and gaps. Correct incomplete handoffs; do not promote self-reports into proof.
</step>
</workflow>
<output>
For a PR, return the concise PR-facing report first, scaled
to the actual change. Retain detailed integrated evidence and original judge
returns separately in existing records; link them only when accessible to the
reader. Do not paste the internal packet into the PR-facing report.
Use the existing review artifact template when a separate
artifact is earned; otherwise record its applicable information in the existing
Issue/log. Preserve actual results, findings and remedy authority, evidence limits,
and the direct-phase stopping boundary.
</output>
<checklist>
- Requested phase, authority, Launch, and applicable target harness resolved.
- Owning procedure/template and applicable professional instructions loaded.
- Shared pragmatic severity and scope rules applied to findings and remedies.
- Actual result, required independent return, and relevant new log evidence inspected.
- Unsupported checks remain incomplete; next phase/publication is not implied.
</checklist>
</skill>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.