capability-manager
Skill0 starsChanged 41 days agoApache-2.0View on GitHub
Research, compare, create or adopt project-specific agents, skills and MCP integrations when existing capabilities leave a concrete gap. Verify provenance, scope, actual registration and smoke tests; preserve user tools and installation authority.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- xhqing/TeamToolkittheir own version, first seen Nov 8, 2026
- xhqing/CapabilityManagerAgenttheir own version, first seen Oct 23, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- xhqing/CapabilityManagerAgent★ 1same name
- xhqing/TeamToolkit★ 1same 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- business-operationsSkill
- decision-routingSkill
- global-orchestratorSkill
- integration-builderSkill
- plugin-safety-reviewSkill
- project-designSkill
- project-discoverySkill
- project-documentationSkill
- project-evidence-reviewSkill
- project-knowledgeSkill
- project-qaSkill
- project-releaseSkill
- project-securitySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Start with the requested project, acceptance criteria and actual session catalog/tool schemas.
- Distinctive: line 13
Read the acquisition and creation contract.
- Distinctive: line 14
Use a scoped capability_researcher or native read-only fallback to compare maintained primary-source candidates, exact source/artifact …
- Distinctive: line 22
Keep generated role instructions bounded.
≈ “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
Project capability manager
Start with the requested project, acceptance criteria and actual session catalog/tool schemas. Reuse suitable connected capabilities and existing roles. Identify the concrete gap before researching tools or generating another skill. Do not install a framework just because it is popular or listed in a registry.
Read the acquisition and creation contract. Use a scoped capability_researcher or native read-only fallback to compare maintained primary-source candidates, exact source/artifact versions, licenses, compatibility, privileges, data destinations, costs, dependencies and evaluation evidence. Include reuse/direct implementation as alternatives. Separate verified facts from vendor claims.
The coordinator selects from evidence and confirmed constraints. For creation, assign an owned-file worker/scoped_implementer and load the host's skill-creator/mcp-builder guidance when available. Otherwise follow the self-contained creation contract here. Keep generated role instructions bounded; they cannot invent tools, permissions or independent reviewers. Independently review and test the result before activation.
Adopt only the selected reviewed source/artifact into the authorized scope. Reuse existing authorization for the same action/target; a recommendation or model score does not authorize arbitrary installs, account linking, global changes or data uploads. Prepare a concrete plan/diff first when authority is missing. Never overwrite another user's same-name role/skill or change permission policy to make an integration work.
Track candidate -> selected -> reviewed -> created/downloaded -> installed -> configured -> registered/discovered -> connected/authenticated when applicable -> smoke-tested -> active, or rejected/blocked/rolled back. Each transition needs actual evidence. Installed files alone cannot pass a live-connection check. Record exact scope, source revision/digest, test results, update policy and rollback in the project's docs/. Stop the failing capability, preserve evidence, and continue independent work after a demonstrated integration failure.
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.