gracefullight/pkgs / .agents/skills/oma-market
oma-market
UnverifiedResearch customer pain points, trends, and competitors through the OMA market engine. Use for market discovery or voice-of-customer analysis.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.1 KB |
| resources/checklist.md | markdown | 876 B |
| resources/error-playbook.md | markdown | 1.4 KB |
| resources/execution-protocol.md | markdown | 2.5 KB |
| resources/frameworks/pestel.md | markdown | 2.8 KB |
| resources/frameworks/porters-5f.md | markdown | 2.8 KB |
| resources/frameworks/swot.md | markdown | 2.4 KB |
| resources/intent-rules.md | markdown | 2.5 KB |
| resources/output-laws.md | markdown | 2.2 KB |
resources/error-playbook.md
View on GitHub# oma-market error playbook
| Symptom | Cause | Action |
|---|---|---|
| `detect-trap` exit 2 | keyword-trap / demographic-shopping / too-broad topic | Show REFUSE + reframe; stop. `--force` only after explicit user reconfirmation |
| `oma market resolve` → `ok: false`, "engine unavailable" | first run offline, or `market.managed: false` with no local copy | `oma market update` once online, or set `market.path` / `LAST30DAYS_HOME` |
| `resolve` → "Python 3.12+" hint | no compatible interpreter | relay hint (`brew install python@3.12` / `apt install python3.12` / `uv python install 3.12`) or set `market.python` / `LAST30DAYS_PYTHON`; stop, never WebSearch-only |
| `engine.status: stale` | GitHub unreachable / rate-limited during refresh | proceed on cached engine; mention version in report |
| Engine prints setup-wizard prompts | first run, no `~/.config/last30days/.env` | follow upstream Step 0 in chat; never answer consent questions on the user's behalf |
| Engine non-zero exit | source/network/auth failure | report stderr verbatim; check `oma market run "<topic>" --diagnose` |
| Sources listed as skipped in footer | keys / cookies absent | keep the list visible; suggest the upstream setup wizard for those sources |
| Output has `Sources:` block, `—`, `##` in body | LAW violation during synthesis | fix per upstream LAWs and `output-laws.md` self-check before writing |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |