integration-builder
Skill0 starsChanged 41 days agoApache-2.0View on GitHub
Assess applications without MCP or CLI interfaces and build a scoped Rust CLI or MCP adapter using supported APIs, SDKs, local formats or permitted UI automation, with real integration tests and clear access boundaries.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Hainrixz/agente-pagokittheir 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
- Hainrixz/agente-pagokit★ 68same 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
- capability-managerSkill
- decision-routingSkill
- global-orchestratorSkill
- 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
Use when the user wants ChatGPT or another supported host to control an application that has no suitable MCP server or CLI.
- Distinctive: line 22
Use official protocol SDK documentation and pinned reviewed dependencies.
- Distinctive: line 26
Do not claim a plugin alone can start a service or control arbitrary desktop windows.
- Distinctive: line 45
If no reliable interface or permitted automation exists, return evidence and feasible alternatives instead of a fake CLI, success stub or …
≈ “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
Integration builder
Use when the user wants ChatGPT or another supported host to control an application that has no suitable MCP server or CLI. Read references/adapter-design.md. Discover existing tools first; reuse an adequate connector instead of duplicating it. Apply capability-manager and a relevant MCP-builder skill when available, after reading their actual instructions.
Establish the exact application/version/platform, desired operations, account/data scope, supported access method, host and success criteria. Ask about material gaps. Research official API/SDK, automation, export/import and authentication documentation. Inspect authorized local code when available. Distinguish a supported control interface from a guessed endpoint, undocumented storage format or unsupported automation path.
Choose the smallest viable adapter: a Rust CLI for a supported operation contract, a Rust MCP service exposing bounded typed tools, or a supported UI automation workflow. Use official protocol SDK documentation and pinned reviewed dependencies. Check the target host's actual transport and installation capabilities before deciding packaging. A local stdio MCP server requires a host supporting local processes; a remote-only host needs a separately hosted, authenticated service and appropriate data authorization. Do not claim a plugin alone can start a service or control arbitrary desktop windows.
Assign an implementer explicit owned paths. Define typed operation schemas, read/write classification, errors, authentication, limits, retry/idempotency behavior and audit evidence. Keep credentials in approved host/OS storage. Avoid arbitrary shell tools, unrestricted URLs/paths, hidden retries of writes and remote token passthrough. For UI adapters, inspect real state and stable supported selectors, verify the actual target after navigation, stop on ambiguity, and report changes that break automation.
Implement the confirmed scope, inspect source independently, review dependencies and security, and run unit/integration checks plus actual target-application E2E in an authorized test account/workspace. Mocks support development but cannot establish live compatibility. Missing app/access/service leaves the live check unverified and blocks claiming a working control integration. Keep a reversible smoke test and rollback/unregistration instructions. Verify discovered MCP tools in the actual host.
The user can authorize adapter development once; do not request repeated approval for routine edits and local tests. Resolve missing authority before login/account changes, production writes, data upload, public hosting or externally visible actions. If no reliable interface or permitted automation exists, return evidence and feasible alternatives instead of a fake CLI, success stub or invented MCP connection.
This skill guides project-specific adapter creation. It does not bundle a universal app controller, public listener or preconfigured remote service.
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.