ci-debug
Skill4 starsChanged 4 months agoMITView on GitHub
Use when CI history needs analysis, a local branch needs exact-SHA GitHub Actions qualification, CI is red, or one matrix failure needs isolated repair.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- stoa-platform/stoatheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- stoa-platform/stoa★ 9same 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 repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bib-auditSkill
- bootstrap-dispatcher-runtimeSkill
- cloud-filesSkill
- connect-googleSkill
- daily-planSkill
- distill-to-ruttersSkill
- email-clientSkill
- email-triageSkill
- find-handoff-candidatesSkill
- formal-prose-reviewSkill
- get-weatherSkill
- git-workflowSkill
- hook-makerSkill
- initialize-tddSkill
- install-launchersSkill
- latex-workshopSkill
- list-managerSkill
- llm-wakeupSkill
- loose-modeSkill
- make-tex-docstringSkill
- math-dependency-graphSkill
- milestone-loggingSkill
- node-certifySkill
- node-driftSkill
- notation-reviewSkill
- online-calendarSkill
- pdf-to-markdownSkill
- prepare-handoffSkill
- proof-auditSkill
- recurring-tasksSkill
- refactor-nodeSkill
- regenerate-blueprintsSkill
- relocate-nodesSkill
- semantic-integrationSkill
- send-feedbackSkill
- setup-interface-managerSkill
- skill-makerSkill
- technical-flow-reviewSkill
- tight-modeSkill
- tool-applicabilitySkill
- update-standardsSkill
- using-compassSkill
- wrap-upSkill
The file
Files
<!-- BEGIN BLUEPRINT INTERFACES -->Generated from
blueprint.yaml. Do not edit this block by hand.
Executable Interfaces:
Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.
ci-debug._rtx.interface.fetch-github-actions-history— Fetch one bounded GitHub Actions workflow history with complete attempt enumeration and frozen Git provenance into a private snapshot.- Caller:
ci-debug - Version: 1
- Security level: 2
- Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--branch": "BRANCH", "--event": "EVENT", "--repo-root": "REPO", "--run-limit": "N", "--since": "ISO_8601", "--snapshot-dir": "NEW_DIR", "--timeout": "SECONDS", "--workers": "N", "--workflow": "WORKFLOW"}, "positionals": [], "stdin": null} Required options: ["--branch", "--repo-root", "--snapshot-dir", "--workflow"]; positional arity: 0..0; stdin: forbidden
- Caller:
ci-debug._rtx.interface.report-ci-runtime-hotspots— Report descriptive API timing observed job execution envelopes job-minutes and heuristic repeated-step hotspots from one snapshot.- Caller:
ci-debug - Version: 1
- Security level: 2
- Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--report-dir": "NEW_DIR", "--snapshot-dir": "SNAPSHOT"}, "positionals": [], "stdin": null} Required options: ["--report-dir", "--snapshot-dir"]; positional arity: 0..0; stdin: forbidden
- Caller:
ci-debug._rtx.interface.report-test-failures-between-green-runs— Report one canonical test incidence per complete green-to-green episode with recurrence bounds frozen provenance and explicit coverage gaps.- Caller:
ci-debug - Version: 1
- Security level: 2
- Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--report-dir": "NEW_DIR", "--snapshot-dir": "SNAPSHOT"}, "positionals": [], "stdin": null} Required options: ["--report-dir", "--snapshot-dir"]; positional arity: 0..0; stdin: forbidden
- Caller:
ci-debug._rtx.interface.run-ci— Start or poll one durable complete remote CI matrix for an exact pushed candidate.- Caller:
ci-debug - Version: 2
- Security level: 2
- Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--context": "DIR", "--expected-sha": "SHA", "--ref": "REF", "--repo-root": "REPO", "--timeout": "SECONDS"}, "positionals": [], "stdin": null} Required options: ["--context", "--expected-sha", "--ref", "--repo-root"]; positional arity: 0..0; stdin: forbidden
- Caller:
ci-debug._rtx.interface.run-targeted-tests— Run one selected failure set or complete matrix element for an exact candidate.- Caller:
ci-debug - Version: 1
- Security level: 2
- Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--context": "DIR", "--expected-sha": "SHA", "--jobs": "N", "--os": "OS", "--profile": "PROFILE", "--ref": "REF", "--repo-root": "REPO", "--selector": "NODE", "--task": "TASK", "--timeout": "SECONDS"}, "positionals": [], "stdin": null} Required options: ["--context", "--expected-sha", "--os", "--ref", "--repo-root", "--selector", "--task"]; positional arity: 0..0; stdin: forbidden - Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--context": "DIR", "--expected-sha": "SHA", "--jobs": "N", "--os": "OS", "--profile": "PROFILE", "--ref": "REF", "--repo-root": "REPO", "--selectors-json": "JSON", "--task": "TASK", "--timeout": "SECONDS"}, "positionals": [], "stdin": null} Required options: ["--context", "--expected-sha", "--os", "--ref", "--repo-root", "--selectors-json", "--task"]; positional arity: 0..0; stdin: forbidden - Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--context": "DIR", "--expected-sha": "SHA", "--from-report": "PATH", "--jobs": "N", "--os": "OS", "--profile": "PROFILE", "--ref": "REF", "--repo-root": "REPO", "--task": "TASK", "--timeout": "SECONDS"}, "positionals": [], "stdin": null} Required options: ["--context", "--expected-sha", "--from-report", "--os", "--ref", "--repo-root", "--task"]; positional arity: 0..0; stdin: forbidden - Alternative:
defaultArguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--context": "DIR", "--expected-sha": "SHA", "--jobs": "N", "--os": "OS", "--profile": "PROFILE", "--ref": "REF", "--repo-root": "REPO", "--task": "TASK", "--timeout": "SECONDS", "--whole-element": true}, "positionals": [], "stdin": null} Required options: ["--context", "--expected-sha", "--os", "--ref", "--repo-root", "--task", "--whole-element"]; positional arity: 0..0; stdin: forbidden
- Caller:
Instruction Interfaces:
These are LLM-readable instruction surfaces. Read and follow them directly; do not invoke the MCP server for them.
ci-debug.source.instructions-analyze-ci.interface.analyze-ci@1— Collect one bounded immutable workflow-history snapshot and report deduplicated green-to-green failures plus descriptive runtime hotspots without dispatching CI.ci-debug.source.instructions-qualify-ci.interface.qualify-ci@2— Coordinate structured local-branch qualification and evidence-bounded CI repair through optional target publication.ci-debug.source.instructions-repair-element.interface.repair-element@1— Repair and verify one assigned CI matrix element without integrating it or claiming overall CI success.git-workflow.interface.default@1— Check branch and ownership boundaries first, then perform only explicitly authorized and exactly scoped Git mutations.
<!-- END BLUEPRINT INTERFACES -->CI Debug
Route by requested outcome before taking any action:
- Historical failures, recurrence, timing, elapsed job-minutes, or hotspots:
use
ci-debug.interface.analyze-ci. - Branch or exact-SHA qualification, full-matrix repair, or optional target
publication: use
ci-debug.interface.qualify-ci. - One explicitly assigned matrix element: use
ci-debug.interface.repair-element.
Mixed historical-analysis and mutating qualification requests require the user to choose or explicitly authorize both operations. Never silently select one.
"Cost" means historical observed job-minutes unless the user says otherwise. Monetary pricing is unsupported and must be reported as a gap. A controlled benchmark is outside this skill and requires clarification. The words cost or benchmark never authorize a workflow dispatch.
Analysis may create only the requested private evidence tree. It never dispatches, cancels, reruns, repairs, commits, or changes Git or GitHub state. Qualification and repair retain their own explicit mutation boundaries.
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.

