Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →viryazheng/geo-pipeline
Entry point + orchestrator for the recomby-geo GEO (Generative Engine Optimization) workflow on OpenAI Codex CLI.
Passed 16 of 19 test cases with the skill, and 3 of 19 without it.
and 15 more in the full report
15 fixed4 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Does this orchestrator duplicate stage procedure logic directly in its main definition file?
| Checked | Without skill | With skill |
|---|---|---|
| States that orchestration rules route to separate stage specification files rather than duplicating procedure code | Missed | Passed |
The instructions your model reads when the skill loads.
On Claude Code each stage is a bare slash command (/01-intake …
/07-reaudit). Codex CLI has no bare custom commands, so this skill is the
Codex entry point: it carries the orchestration rules and routes to the
per-stage specification files, which are the single source of truth
shared with the Claude Code side. Do not duplicate stage logic here — read
the stage file and follow it.
Per-stage specs (read the one you're running):
commands/01-intake.md, commands/02-audit.md, commands/03-gap.md,
commands/04-content-brief.md, commands/05-production.md,
commands/06-distribution.md, commands/07-reaudit.md (relative to this
plugin's root). Full directory convention + dependency graph:
orchestrator/run.md.
Identify the client folder clients/<slug>/ and the stage the user wants.
Read the matching commands/0X-*.md and execute its Procedure verbatim.
Validate every JSON artifact the stage writes against its schema before moving on (Codex has no built-in schema validation — run it explicitly):
python3 - <<'PY'
import json, jsonschema
pairs = {
"brand_context.json": "brand_context.schema.json",
"visibility_baseline.json": "visibility_baseline.schema.json",
"content_priorities.json": "content_priorities.schema.json",
} # see schemas/ for the full set incl. attribution_diff + review_feedback
# jsonschema.Draft202012Validator(json.load(open("plugins/recomby-geo/schemas/<file>"))).validate(json.load(open("clients/<slug>/<artifact>")))
print("validate each artifact against plugins/recomby-geo/schemas/*.schema.json")
PY
Stop at the human-in-loop points (see rules below).
test cases passed, vs 3 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.