Skip to content

donaldfilimon/abi / .claude/skills/connector-localcheck

connector-localcheck

Verified

Build the abi CLI and exercise the connector surfaces that run fully locally — the Twilio ConversationRelay simulation and the auth-status report. Use to smoke-test connectors without credentials or network. Does NOT touch the live transport or any remote provider.

connector-localcheck — drive abi's local connector surfaces

Driver: .agents/skills/connector-localcheck/connectors.sh (paths relative to repo root). Read-only-effect CLI check — evidence is the RESULT: line. No creds, no network.

Run (agent path)

.agents/skills/connector-localcheck/connectors.sh                      # default utterance
.agents/skills/connector-localcheck/connectors.sh "cancel my account"  # custom caller text

Builds the CLI, runs abi twilio simulate "<utterance>" (asserts Twilio ConversationRelay simulation, response:, escalation:) and abi auth status (asserts Authentication Status:). Prints RESULT: PASS (exit 0) or a FAIL count.

Current Rust driver: checks the local Twilio simulation response/escalation shape plus credential status without selecting a live transport.

Gotchas

  • ⚠️ Local only by design. This exercises the deterministic local connector paths. The remote/.live transport (real OpenAI/Anthropic/Discord/Twilio calls) needs stored credentials and is deliberately NOT driven here — use abi auth signin <svc> + abi complete --live for that, manually.
  • For a source-level audit of credential validation and the live/local boundary, use the connector-validator subagent.

Troubleshooting

SymptomFix
build FAIL./tools/check.sh.
missing Twilio ConversationRelay simulationgrammar drift — check crates/abi-cli/src/twilio.rs and crates/abi-connectors/src/twilio_relay.rs.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall