resolving-app
Skill5 starsChanged 53 days agoMITView on GitHub
Use to resolve which of the project's managed apps a request belongs to.
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-feedbackSkill
- asking-peer-agentsSkill
- boss-assistantSkill
- boss-saySkill
- bringing-coworkerSkill
- choosing-graphSkill
- contacting-orchestratorsSkill
- create-great-harnessSkill
- dispatching-workSkill
- handoff-orchestratorSkill
- i-am-orchestratorSkill
- initSkill
- notifying-main-agentSkill
- peeking-workSkill
- reporting-to-userSkill
- shipping-taskSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
No configuration: use the repo root as an implicit app when it contains one codebase.
- Distinctive: line 12
One active app: use it unless the request is explicitly outside that app.
≈ “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
Resolve the app
Resolve the git root, then use the shared read handler. Exit 0 returns the configuration; exit 3 uses the implicit-app branch below; exit 1 requires correcting the reported configuration error.
- No configuration: use the repo root as an implicit app when it contains one codebase. Derive its name from the manifest or directory name. With several plausible apps, ask which directory the request targets.
- One active app: use it unless the request is explicitly outside that app.
- Several apps: match the request against every entry's
nameandmatch. Return each app touched; clarify an ambiguous match. - Legacy entry: apply
redirectTofor new work and surface itsnote. An audit of existing legacy code stays in that checkout; a user-confirmed compatibility fix can also stay there. - External or unmanaged work: return that classification to the caller.
Return
Return the app names, absolute directories, config source, and applicable crossAppSkills pointers.
App ownership alone establishes no dependency order.
The caller uses boss-say for work needing a plan; this skill only resolves targets.
Complete when: the caller has unambiguous targets or a specific unresolved routing question.
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.

