pre-pr
Skill602 starsChanged 14 days agoMITView on GitHub
Run Biopass's local review flow before opening or updating a PR — verification checks, a fresh-context code review against REVIEW.md, and a security review for high-risk paths. Use when the user runs /pre-pr or asks to check a change before a PR.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- safe-global/safe-wallet-monorepotheir own version, first seen Nov 9, 2026
- salvo8519/fairmarktheir own version, first seen Nov 8, 2026
- OrionArchitekton/orion-skillstheir own version, first seen Nov 2, 2026
- JohnnyMcGee/claude-skillstheir own version, first seen Nov 1, 2026
- plastic-labs/honchotheir own version, first seen Oct 23, 2026
- MichinaoShimizu/kirokutheir own version, first seen Oct 11, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- mongodb/mongo-go-driver★ 8.5ksame name
- plastic-labs/honcho★ 8ksame name
- safe-global/safe-wallet-monorepo★ 598same name
- asynkron/asynkron-skills★ 32same name
- MichinaoShimizu/kiroku★ 2same name
- OrionArchitekton/orion-skills★ 2same name
- Docat0209/SoloForge★ 1same name
- salvo8519/fairmark★ 1same name
- JohnnyMcGee/claude-skills★ 0same name
- nfeuer/project-foundation-kit★ 0same name
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 repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
4
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
- Distinctive: line 8
All review runs on this machine.
- Very specific: line 26
Run this step if the diff touches auth/pam, auth/core, app/src-tauri/scripts, app/src-tauri/capabilities, tauri.conf.json, or model …
- Distinctive: line 31
Stop after 3 rounds. If findings keep appearing, tell the user to rethink the approach instead of looping.
- Distinctive: line 32
If the same kind of issue came up that REVIEW.md doesn't already list, propose a one-line entry for its "Recurring issues" section.
- Distinctive: line 40
Leave the manual-testing table and the checklist for the author unless they gave you those facts.
“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
Pre-PR review (local)
All review runs on this machine; there is no AI reviewer on GitHub. CI only runs the mechanical checks.
1. Scope
Diff against the base: git diff main...HEAD plus uncommitted changes. If the user passed a base branch, use it instead. Note which areas are touched: app/src, app/src-tauri, auth/, app/src-tauri/scripts, docs.
2. Verify
Run the commands from the "Verify before saying done" table in CLAUDE.md for every touched area, and show the output. If a check fails, fix it before continuing. If something can't run here (no camera, no fingerprint reader, PAM needs a VM), say so explicitly instead of skipping silently.
3. Code review
Spawn one subagent with fresh context (don't pass it your conclusions). Give it the diff range and tell it to follow REVIEW.md exactly and use CLAUDE.md for context. Its output must use REVIEW.md's format (path:line, Important / Nit / Pre-existing, summary line).
Then check each Important finding yourself by opening the cited line. Drop the ones that don't hold up and say why.
4. Security review
Run this step if the diff touches auth/pam, auth/core, app/src-tauri/scripts, app/src-tauri/capabilities, tauri.conf.json, or model download code. Run /security-review and apply the focus list in security-focus.md.
5. Converge
- Fix confirmed Important findings. Then re-run only steps 2 and 3, on the new changes only.
- Stop after 3 rounds. If findings keep appearing, tell the user to rethink the approach instead of looping.
- If the same kind of issue came up that REVIEW.md doesn't already list, propose a one-line entry for its "Recurring issues" section.
6. Draft the PR description
Fill .github/PULL_REQUEST_TEMPLATE.md and save it to the scratchpad (or a path the user gives):
- Verification: the real output from step 2, trimmed to the relevant lines. List what couldn't run under "Not tested".
- Review report: the summary line from step 3, whether step 4 ran, and each finding fixed or dismissed with a reason.
- Risk and How to revert: tick the tier from the paths touched, not the author.
- Leave the manual-testing table and the checklist for the author unless they gave you those facts.
Facts only. Keep every heading; write "N/A" rather than deleting one. Tell the user to read it before opening the PR.
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.