resolve
Skill0 starsChanged 3 months agoMITView on GitHub
Apply the minimum repair for owned reproducible issues and return them to independent verification without closing them yourself. Use when Test has recorded a reproducible owned defect with a bounded repair gate.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- mlflow/mlflowtheir own version, first seen Nov 8, 2026
- grainulation/grainulatortheir own version, first seen Nov 3, 2026
- pauljasperdev/skillstheir own version, first seen Nov 1, 2026
- pluk-inc/md-preview.apptheir own version, first seen Oct 17, 2026
- pluk-inc/markdown-previewtheir own version, first seen Oct 17, 2026
- gufranco/claude-engineering-rulestheir own version, first seen Oct 12, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- mlflow/mlflow★ 29ksame name
- pluk-inc/markdown-preview★ 2.8ksame name
- pluk-inc/md-preview.app★ 2.8ksame name
- optave/ops-codegraph-tool★ 94same name
- grainulation/grainulator★ 86same name
- gufranco/claude-engineering-rules★ 3same name
- AndriiShramko/360-video-editing-playbook★ 0same name
- chanhyeok-made/ccx★ 0same name
- pauljasperdev/skills★ 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 repository30 other files it gives its agents.
- auditSkill
- bootstrap-agent-contextSkill
- buildSkill
- closeSkill
- decision-logSkill
- feature-trackerSkill
- handoffSkill
- health-checkSkill
- idea-to-briefSkill
- live-state-preflightSkill
- portfolio-reviewSkill
- pre-commit-reviewSkill
- retrospectiveSkill
- session-summarySkill
- spec-packSkill
- stack-summarySkill
- strategizeSkill
- testSkill
- the-loop-autonomySkill
- the-loop-autoSkill
- the-loop-cloudSkill
- the-loop-controlSkill
- the-loop-doctorSkill
- the-loop-endlessSkill
- the-loop-parallelSkill
- the-loop-setupSkill
- the-loop-skill-creatorSkill
- the-loopSkill
- the-loop-skill-plannerSkill
- the-loop-watchSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
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 19
Use only after Test records one or more reproducible issues and an explicit owner accepts the bounded resolution work.
- Distinctive: line 38
Run only the smallest repair check needed before independent Test.
- Distinctive: line 41
If the issue reopens after one attempted closure, stop the autonomous loop and surface the stuck condition.
- Very specific: line 47
run ID, stage resolve, track and declared asset.
“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
Resolve
Purpose
Provide the complete bundled fallback for lifecycle.resolve. Repair evidence-backed defects through the durable issue lifecycle while preserving failure history.
Use when
Use only after Test records one or more reproducible issues and an explicit owner accepts the bounded resolution work.
Required inputs
- Validated run ID, declared asset, track and stage
resolve. - Owned issue IDs, original failure evidence and minimal reproductions.
- Affected requirement IDs, approved write boundary and regression procedure.
- The issue-specific done gate for returning the repair to independent Test.
- Current artifact or repository state, including unrelated changes.
- Active authority, matching lease, frozen budgets and stop controls.
Reject unowned issues, invalid issue transitions and fixes without a reproducible failure.
Procedure
- Validate issue status and ownership, then move the issue to
resolvingthrough the durable event boundary. - Rerun the original reproduction and inspect for a narrower cause.
- Make the minimum change that addresses that cause while preserving unrelated work.
- Record what changed and link it to the same issue and requirement IDs.
- Run only the smallest repair check needed before independent Test.
- Move the issue to
verification_pending; do not close it. - Return the original reproduction and regression procedure to Test.
- If the issue reopens after one attempted closure, stop the autonomous loop and surface the stuck condition.
Output contract
Return:
- run ID, stage
resolve, track and declared asset; - owned issue IDs and status transitions;
- root cause, changed artifacts and preserved unrelated state;
- repair evidence and exact regression procedure;
- issues moved to
verification_pending; - usage, gate state and recommended
testor halt.
Evidence gate
Resolve passes its own stage only when the original failure remains linked, the repair is documented, the issue is verification_pending and Test has a reproducible regression procedure. Repair evidence is not closure evidence.
Track requirements
For the code track, preserve isolation, command output and executable regression steps. For the non-code track, preserve source and factuality evidence, changed sections, calculation or render checks and reviewer instructions. Both code track and non-code track retain the original defect record.
Safety and authority
Mutate only the owned issue and declared artifact boundary under the current lease. Do not weaken tests, evidence gates, issue severity or authority to make a failure disappear. External correction, publication or notification needs explicit outward authority.
Self-refutation
Rerun the original reproduction, ask whether the cause is narrower than the proposed fix and look for a regression hidden by the change. Do not alter the reproduction merely to make it pass.
Halt conditions
Halt when the issue lacks evidence or ownership, the reproduction is no longer valid and cannot be explained, scope expands, unrelated changes overlap, authority or lease is invalid, a stop is detected, an unknown outcome exists, the issue reopens, or Test remains red after three passes.
Core execution does not require network access or the source checkout. The links below are optional public documentation.
References
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.

