op1 marketing seo experiment stage1
- Repo stars 0
- Author repo skills-registry
- Domain
- Security
- Author-declared agents
- No explicit declaration found; this is not inferred or tested compatibility
- Static check
- 88 / 100 · heuristic scan, not runtime safety proof
- Runtime evidence
- Not run; no isolated runtime test evidence is currently recorded
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No explicit requirements detected
- Detected file/system behavior
-
- Read-only
- Shell exec
- Network behavior
- Local-only
- Install commands
- None (reference only)
Heads up: Tool permissions are not declared; actual access depends on the runtime.
# Stage1 SEO Experiment Runner (Shadow)
## Objective
Run the Stage1 SEO pipeline in shadow mode and produce auditable artifacts under `research/stage1_marketing_seo/`.
## Single-cycle run
From workspace root:
```bash
./scripts/run_marketing_seo_stage1.sh --mode shadow --force
```
Check:
- `research/stage1_marketing_seo/run.latest.json`
- `research/stage1_marketing_seo/experiments.queue.latest.json`
- `research/stage1_marketing_seo/scoreboard.latest.json`
- `research/stage1_marketing_seo/decision_log.latest.md`
## 1/2/3 validation run
Use the bundled helper:
```bash
python3 {baseDir}/scripts/run_rounds_123.py
```
This executes:
1. Round1 baseline
2. Round2 controlled handoff perturbation
3. Round3 baseline restore + rerun
Then it writes snapshot artifacts and validation checks to:
- `research/stage1_marketing_seo/rounds/<timestamp>/rounds_1_2_3.report.md`
- `research/stage1_marketing_seo/rounds/<timestamp>/rounds_1_2_3.report.json`
Expected checks:
- `R1 == R3` for queue/content reproducibility
- `R2 != R1` for input-sensitivity
## Guardrails
- Keep mode as `shadow` for Stage1 capability validation.
- Treat this as experiment generation/scoring/queueing only (not auto publish).
- If run status is `blocked_input_incomplete`, stop and report missing requirements from `run.latest.json.input_sync.completeness`.
## References
- `references/stage1-output-contract.md`
- `references/analysis-checklist.md`
---
> Source: [Daihaolin201/OperatorOne](https://github.com/Daihaolin201/OperatorOne) — distributed by [TomeVault](https://tomevault.io).
<!-- tomevault:4.0:skill_md:2026-05-22 -->
Sections and files
Listed in source order.
sections -> Objective → Single-cycle run → 1/2/3 validation run → Guardrails → References
terms -> This executes: 1. · --- > Source: [Daihaolin201/OperatorOne](https://github.com/Daihaolin201/OperatorOne) — distributed by [TomeVault](https://tomevault.io).
files/cmd -> research/stage1_marketing_seo/ · research/stage1_marketing_seo/run.latest.json · research/stage1_marketing_seo/experiments.queue.latest.json · research/stage1_marketing_seo/scoreboard.latest.json · research/stage1_marketing_seo/decision_log.latest.md · research/stage1_marketing_seo/rounds/<timestamp>/rounds_1_2_3.report.md · research/stage1_marketing_seo/rounds/<timestamp>/rounds_1_2_3.report.json · R1 == R3
body sha256 -> 0394b249ac2a
Objective
Run the Stage1 SEO pipeline in shadow mode and produce auditable artifacts under
research/stage1_marketing_seo/.Single-cycle run
From workspace root: Check:
research/stage1_marketing_seo/run.latest.jsonresearch/stage1_marketing_seo/experiments.queue.latest.jsonresearch/stage1_marketing_seo/scoreboard.latest.json1/2/3 validation run
Use the bundled helper: This executes: Round1 baseline Round2 controlled handoff perturbation Round3 baseline restore + rerun
Guardrails
Keep mode as
shadowfor Stage1 capability validation. Treat this as experiment generation/scoring/queueing only (not auto publish). If run status isblocked_input_incomplete, stop and report missing requirements fromrun.latest.json.input_sync.completeness.References
references/stage1-output-contract.mdreferences/analysis-checklist.mdSource: Daihaolin201/OperatorOne — distributed by TomeVault.