Skill Creator
shami-ah
19 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
oe-release-readiness
Pre-merge/release readiness checklist for OpenEvent-AI. Use when preparing a PR for production: run the fastest validation lanes first (compile/import, smoke suite, deterministic site-visit trace), then escalate to full suites or integration checks as needed.
oe-docs-updates
Keeps OpenEvent-AI “living docs” in sync while coding. Use whenever you fix a bug, discover a new bug, add/modify behavior, or capture a future idea. Updates docs/guides/TEAM_GUIDE.md (bug list + regressions), DEV_CHANGELOG.md (what changed), new_features.md (ideas parked for later), and TO_DO_NEXT_SESS.md (next-session tasks).
oe-security-prompt-injection
Maintain and extend prompt-injection defenses. Use when adding new user-input surfaces, changing prompt templates, or when a new injection pattern is observed; run the security regression suite and add a minimal new test case.
oe-e2e-site-visit
End-to-end verification for the site-visit (Step 7) flow. Use when you need to reproduce or validate that the system reaches the site-visit prompt/options and can proceed to confirmation, either via deterministic backend-only traces (manual_ux_scenario_I/H) or via browser UI checks (Playwright/MCP).
oe-backend-prod-hardening
Production hardening review for the OpenEvent backend. Use when scanning for LLM smells, noisy prints, swallowed exceptions, dev-only defaults, fallback diagnostic leakage, and inconsistent error/logging patterns; produce a prioritized, PR-sized cleanup plan.
oe-trace-and-fallback-triage
Debug and eliminate fallback/generic-stub replies quickly. Use when you see empty assistant replies, “Thanks for your message…” stubs, or “no specific information available” messages. Produces a minimal reproduction (test or deterministic trace) and pinpoints the fallback source + trigger.
openevent-email-workflow
Canonical OpenEvent email workflow architecture (intake, date confirmation, room availability, offer review, negotiation, confirmation) and file map.
oe-workflow-routing
Fast routing triage for workflow messages; points to docs/workflow-routing-map.md.
skill-authoring-and-retrospectives
How to write/update .claude/skills and capture durable OpenEvent learnings via retrospectives.
oe-test-matrix-navigator
Maps a code change or bug symptom to the smallest high-signal test subset. Use when deciding what tests to run (DET_/FLOW_/REG_), when a regression guard mentions a test ID, or when you need a minimal repro that matches tests/TEST_MATRIX_detection_and_flow.md.
oe-mcp-bootstrap
Setup and verification for MCP tooling used in OpenEvent-AI (filesystem, Context7 docs, LSP/Pyright, Playwright). Use when onboarding a new developer/agent or when Codex/Claude cannot access LSP, browser automation, or docs.
oe-workflow-triage
Workflow bug triage for OpenEvent. Use when you have a regression/bug report (wrong step, wrong detour, HIL stuck, site visit issues) and need a minimal reproduction trace plus a fix plan tied to workflow invariants and tests.
oe-project-orientation
Repo navigation and “where do I start?” guide for OpenEvent-AI. Use when an agent/dev is lost, needs an overview of the project or a subsystem, or needs pointers to the most important docs, entrypoints, scripts, and tests without rescanning the entire codebase.
oe-lsp-pyright-refactor
Refactor planning and execution discipline using LSP/Pyright. Use when making non-trivial refactors (splitting files, renaming symbols, moving modules) and you want compiler-accurate references/definitions, plus a Pyright-driven contract baseline to avoid regressions.
oe-hil-and-billing-triage
Debug common manager/HIL + billing/deposit regressions: tasks not appearing in the panel, approve/reject button failures, billing capture loops, and “deposit paid but workflow stuck”. Produces a targeted repro + test run and points to the likely faulty layer (frontend vs backend).
oe-backend-startup-triage
Debug “backend won’t start / first request 500 / ports stuck” quickly. Use when uvicorn reload behaves strangely, ports 8000/3000 are blocked, or you see first-request errors like “unexpected keyword argument” due to stale bytecode caches.
oe-llm-provider-toggle
Switch OpenEvent-AI between OpenAI, Gemini, hybrid, or stub LLM modes via environment variables or the /api/config/llm-provider admin endpoints. Use when Codex/Claude needs to verify or change AGENT_MODE, INTENT/ENTITY/VERBALIZER providers, or OE_LLM_PROFILE settings.
oe-integration-mode-smoke
Smoke-test “integration mode” safely (Supabase + optional live OpenAI integration tests). Use when debugging prod-only differences, validating Supabase connectivity, or running backend/tests_integration without turning every local run into a deployment.
openevent-email-change-checklist
Review and testing checklist for OpenEvent email workflow changes (intake, offers, availability, confirmation).