pr-truth-triage
Skill1 starsChanged 33 days agoMITView on GitHub
Classify stale branches by their actual integration diff, conflicts and current requirements; preserve work and separate remaining content from readiness.
In this repository42 other files it gives its agents.
- ansible-hardeningSkill
- cavetechSkill
- ci-cdSkill
- claude-to-cursorSkill
- code-consistencySkill
- code-qualitySkill
- config-auditorSkill
- container-sandboxSkill
- cpa-tax-specialistSkill
- database-designSkill
- definition-of-doneSkill
- differential-reviewSkill
- exact-head-reviewSkill
- fast-ciSkill
- grill-meSkill
- inbound-syncSkill
- infosec-architectSkill
- insecure-defaultsSkill
- lonely-sysadminSkill
- mcp-createSkill
- mcp-hardeningSkill
- model-evaluationSkill
- modern-pythonSkill
- ms-office-suiteSkill
- mutation-checkSkill
- plan-to-execution-handoffSkill
- prd-to-planSkill
- property-based-testingSkill
- repo-hardening-workflowSkill
- resume-writerSkill
- skill-updaterSkill
- software-developerSkill
- software-development-lifecycleSkill
- solutions-architectSkill
- stay-readySkill
- supply-chain-risk-auditorSkill
- systematic-debuggingSkill
- tddSkill
- token-miserSkill
- triage-issueSkill
- verification-before-completionSkill
- write-a-prdSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- could be automatic: a setting could enforce it
- Very specific: line 10
Create a fresh disposable worktree at the current base with a unique temporary branch.
- Distinctive: line 18
If useful work remains, create an owned review branch and run applicable tests/reviews.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Branch truth triage
Inspect live refs, PR state, related commits and the current requirement. Branch names, git cherry, ancestor checks and merged-PR titles are useful evidence, not sufficient proof that the current content is already present or still wanted. A three-dot diff shows changes from the merge base; it does not count commits.
- Fetch the verified remote and record full base/candidate SHAs. Check failures explicitly. An unavailable ref is unknown, not an empty branch.
- Create a fresh disposable worktree at the current base with a unique temporary branch. Use
git worktree add -b, never-Bon an existing branch. Preserve other writers' worktrees and refs. - Attempt a no-commit integration of the candidate in that worktree. If conflicts occur, record conflicting paths and requirements; abort only your own attempt. Do not automatically cherry-pick a whole history or resolve toward an outdated implementation.
- Inspect the staged integration diff against the pinned base.
git diff --cached --quietexits 0 for empty, 1 for differences, and higher values for errors. Handle all three separately. - Classify:
- EMPTY: this integration contributes no content change; no new implementation PR is needed on that evidence.
- NONEMPTY: content remains to assess. Review requirements, regressions, deletions and tests before proposing it.
- CONFLICT: requires contextual investigation; do not call it redundant or shippable.
- UNKNOWN: missing refs, tool errors or incomplete evidence.
- If useful work remains, create an owned review branch and run applicable tests/reviews. A nonempty diff is not permission to ship. Never force-push another contributor's branch to publish a trial integration.
Report repository, refs, classification, evidence, current applicability and owner/next action. Preserve ambiguous branches. Clean up only your own clean test worktree through git worktree remove; retain dirty evidence for review.
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.

