agentleFS
NicholasFlemmerNicholasFlemmer/styx-app/.claude/skills/provider-adapter/SKILL.md

provider-adapter

Skill31 starsChanged 2 months agoApache-2.0View on GitHub

Add or modify a target provider (vercel, aws, gcp, supabase, github, ssh, or a new one) - connect modes (CLI login, token, OAuth, keys), test and health, token issue/revoke and scoping, scope classification, shims, fixtures and tests.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add the id to providerSchema (packages/core/src/model/common.ts) and the second Provider union in apps/desktop/src/main/providers/types.ts.

    line 13
  2. Very specific:

    Run the security-reviewer subagent.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Provider adapter: $ARGUMENTS

The full, current walkthrough is docs/contributing/adding-a-target.md (worked example: Supabase). Read it first and follow its "Adding yours" checklist; this is the short version.

  1. Add the id to providerSchema (packages/core/src/model/common.ts) and the second Provider union in apps/desktop/src/main/providers/types.ts; targets.provider has a SQL CHECK, so add a table-rebuild migration (/db-migration).
  2. Implement ProviderAdapter in apps/desktop/src/main/providers/$0.ts: connect (CLI login first, then token / OAuth / keys under Advanced), test, health, issue, revoke, scopeOfCommand(argv) (fails closed: unknown commands are the widest scope). Register it in providers/index.ts.
  3. Secrets go through CredentialVault only, behind credentialRef; config holds non-secret ids. Report scoped honestly: an unscoped prod credential needs MFA even for reads.
  4. Shims are generic (packages/cli/src/wrap.ts + exec_authorize); add the CLI name to the shim tool list, the stripped env vars and the secret shapes the guide lists.
  5. Copy and UI: provider names, connect bodies and the renderer's provider lists (see the guide's checklist).
  6. Tests: MemoryVault, stubbed fetch, FakeCliRunner, a scope table including "fails closed", the registry test. Fake credentials are marked FIXTURE; never call real providers.
  7. Run the security-reviewer subagent.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.