runtime-triage
Skill2 starsChanged 56 days agoMITView on GitHub
Diagnose preview, install, and runtime issues in Workspace Hub and sibling repos
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- agent-tooling-doctorSkill
- quality-gateSkill
- repo-onboardingSkill
- security-checkSkill
- ssh-keychain-accessSkill
- typescript-reviewSkill
- workspace-maintenanceSkill
- workspace-quality-gateSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 8
Use this skill when a repo in the workspace fails to install, start, preview, or report health correctly.
- Very specific: line 14
Check .workspace/project.json for explicit overrides before changing inference logic.
- Distinctive: line 15
Verify runtime commands directly in the repo only after reading the tracked metadata and logs.
- Distinctive: line 26
Do not hard-code one package manager across all repos.
- Distinctive: line 27
Do not switch a repo into a proxy or mapped-host preview mode unless it solves a real problem.
≈ “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
Runtime Triage
Use this skill when a repo in the workspace fails to install, start, preview, or report health correctly.
Triage flow
- Inspect the repo in Workspace Hub first for runtime, install, health, and manifest state.
- Open the latest failure report if one exists.
- Check
.workspace/project.jsonfor explicit overrides before changing inference logic. - Verify runtime commands directly in the repo only after reading the tracked metadata and logs.
- Promote repeat fixes into docs, manifests, scripts, or skills.
Useful locations
repos/workspace-hub/docs/runtime-troubleshooting.mdrepos/workspace-hub/data/cache/context/agents/jobs/
Guardrails
- Do not hard-code one package manager across all repos.
- Do not switch a repo into a proxy or mapped-host preview mode unless it solves a real problem.
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.

