op1 marketing seo experiment stage1

Security Community

Skill notes

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.json research/stage1_marketing_seo/experiments.queue.latest.json research/stage1_marketing_seo/scoreboard.latest.json

1/2/3 validation run

Use the bundled helper: This executes: Round1 baseline Round2 controlled handoff perturbation Round3 baseline restore + rerun

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 — distributed by TomeVault.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
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.

Author source file SKILL.md

# 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 -->

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.