How do I install the Op1 Marketing Content Publish Stage2 skill?

Run npx skillmds@latest add tomevault-io/op1-marketing-content-publish-stage2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Op1 Marketing Content Publish Stage2 safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Op1 Marketing Content Publish Stage2?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Op1 Marketing Content Publish Stage2 free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Op1 Marketing Content Publish Stage2?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Op1 Marketing Content Publish Stage2 by tomevault-io

Name: Op1 Marketing Content Publish Stage2
Author: tomevault-io

Op1 Marketing Content Publish Stage2

Run and operate OperatorOne Marketing Stage2 content publishing in shadow/review mode. Use when asked to publish content without auto-posting, generate Stage2 drafts from Stage1 SEO outputs, apply manual approve/revision decisions, verify queue integrity, or update marketing_to_sales handoff statuses. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Stage2 Content Publish Operator (Shadow + Manual Review)

Objective

Build and operate Stage2 content publishing as an experiment loop:

Generate drafts from Stage1 SEO queue
Run quality gates
Route items into approved / review_ready / needs_revision
Keep auto publish disabled
Sync ../../handoffs/marketing_to_sales.json

Run Stage2 generation

From workspace root:

./scripts/run_marketing_content_stage2.sh

Useful variants:

# Force recompute
./scripts/run_marketing_content_stage2.sh --force

# Include Stage1 hold candidates
./scripts/run_marketing_content_stage2.sh --force --include-hold

# Raise score floor for stricter QA
./scripts/run_marketing_content_stage2.sh --force --min-score 90

Apply manual review decisions

Use manual review script (no auto publish involved):

# Approve all review-ready items
./scripts/review_marketing_content_stage2.sh --approve-all --note "editorial pass"

# Mixed decision batch
./scripts/review_marketing_content_stage2.sh \
  --approve cnt_a,cnt_b \
  --reject cnt_c \
  --reason "tighten evidence" \
  --note "pass 1"

Validate outputs

Run deterministic contract checks:

python3 {baseDir}/scripts/verify_stage2_contract.py

Interpretation:

checks_failed = 0 => output contract is consistent
non-zero failures => inspect publish.queue.latest.json, content.backlog.latest.json, and run.latest.json

Required artifact set

See references/output-contract.md for full contract.

Primary artifacts:

research/stage2_content_publish/run.latest.json
research/stage2_content_publish/state.latest.json
research/stage2_content_publish/content.backlog.latest.json
research/stage2_content_publish/publish.queue.latest.json
research/stage2_content_publish/qa.latest.json
research/stage2_content_publish/decision_log.latest.md
research/stage2_content_publish/review_log.latest.json
research/stage2_content_publish/drafts/

Guardrails

Keep auto_publish=false in this stage.
Treat Stage2 as generation + review orchestration only.
If Stage1 is unhealthy (run.latest.json.status not passed|no_change), stop and report upstream status.
If completeness gate blocks the run, report missing input requirements from run.latest.json.input_sync.completeness.

References

references/output-contract.md
references/review-playbook.md

Source: Daihaolin201/OperatorOne — distributed by TomeVault.

---name: op1-marketing-content-publish-stage2description: Run and operate OperatorOne Marketing Stage2 content publishing in shadow/review mode. Use when asked to publish content without auto-posting, generate Stage2 drafts from Stage1 SEO outputs, apply manual approve/revision decisions, verify queue integrity, or update marketing_to_sales handoff statuses. Use when this capability is needed.---# Stage2 Content Publish Operator (Shadow + Manual Review)## ObjectiveBuild and operate Stage2 content publishing as an experiment loop:- Generate drafts from Stage1 SEO queue- Run quality gates- Route items into `approved` / `review_ready` / `needs_revision`- Keep auto publish disabled- Sync `../../handoffs/marketing_to_sales.json`## Run Stage2 generationFrom workspace root:```bash./scripts/run_marketing_content_stage2.sh```Useful variants:```bash# Force recompute./scripts/run_marketing_content_stage2.sh --force# Include Stage1 hold candidates./scripts/run_marketing_content_stage2.sh --force --include-hold# Raise score floor for stricter QA./scripts/run_marketing_content_stage2.sh --force --min-score 90```## Apply manual review decisionsUse manual review script (no auto publish involved):```bash# Approve all review-ready items./scripts/review_marketing_content_stage2.sh --approve-all --note "editorial pass"# Mixed decision batch./scripts/review_marketing_content_stage2.sh \ --approve cnt_a,cnt_b \ --reject cnt_c \ --reason "tighten evidence" \ --note "pass 1"```## Validate outputsRun deterministic contract checks:```bashpython3 {baseDir}/scripts/verify_stage2_contract.py```Interpretation:- `checks_failed = 0` => output contract is consistent- non-zero failures => inspect `publish.queue.latest.json`, `content.backlog.latest.json`, and `run.latest.json`## Required artifact setSee `references/output-contract.md` for full contract.Primary artifacts:- `research/stage2_content_publish/run.latest.json`- `research/stage2_content_publish/state.latest.json`- `research/stage2_content_publish/content.backlog.latest.json`- `research/stage2_content_publish/publish.queue.latest.json`- `research/stage2_content_publish/qa.latest.json`- `research/stage2_content_publish/decision_log.latest.md`- `research/stage2_content_publish/review_log.latest.json`- `research/stage2_content_publish/drafts/`## Guardrails- Keep `auto_publish=false` in this stage.- Treat Stage2 as generation + review orchestration only.- If Stage1 is unhealthy (`run.latest.json.status` not `passed|no_change`), stop and report upstream status.- If completeness gate blocks the run, report missing input requirements from `run.latest.json.input_sync.completeness`.## References- `references/output-contract.md`- `references/review-playbook.md`---> Source: [Daihaolin201/OperatorOne](https://github.com/Daihaolin201/OperatorOne) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions