Run growth loop

Skill kimsanguine/signal-to-growth/skills/run-growth-loop

Route an evidence-to-growth workflow by validating artifacts, approval states, blockers, and the next specialist skill. Use when coordinating the full Signal to Growth loop, resuming a paused run, checking 다음 단계, or creating a growth-operations handoff.From its SKILL.md

Install

npx -y skills add kimsanguine/signal-to-growth --skill run-growth-loop

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.3 KB, 630 tokens by cl100k_base, as published. Nobody here has run it

Run Growth Loop

Coordinate state and handoffs. Do not replace the specialist judgment contained in the other ten skills.

Inputs

Require:

workspace or artifact directory;
user objective;
selected policy set;
current run-state.json, if one exists;
approval and blocker context.

Workflow

Validate repository and available artifacts.
Read the run objective, completed skills, approvals, and blockers.
Reconcile stated completion with files and reference integrity.
Identify the first missing or invalid gate.
Route to exactly one specialist skill unless independent work is explicitly requested.
Preserve partial outputs and explain why the run cannot advance.
Ask for human approval at decision and external-action transitions.
Update run-state.json as a new auditable state.
Create a handoff that distinguishes completed, locally validated, externally executed, and outcome-recorded work.

Routing graph

research objective
  → plan-customer-reach → run-switch-interview → synthesize-interviews

configured CS source
  → connect-customer-channels → triage-customer-signals

validated evidence or signal
  → define-growth-metrics → record-growth-decision → design-first-user-loop

approved decision needing build review
  → export-hplan → hplan gates

optional content branch
  → audit-answer-visibility → draft-evidence-content

Route from the stated objective and valid available artifacts, not from a mandatory universal sequence. Keep the manual signal path when no connector artifact exists. Route to connect-customer-channels when any connector artifact exists but the required connection, event, or state artifact is incomplete. Keep visibility and content work optional unless the objective asks for them.

Boundaries

Let the model interpret blockers and propose the next specialist.
Use deterministic checks for artifact existence, schema, references, state transitions, and approval.
Require a person to approve important decisions and every external write.
Do not recreate interview, metric, content, or channel analysis inside the router.
Do not call provider APIs directly or treat an unconfigured connector as a blocker for manual signal input.
Do not mark a run complete because files exist; required validation and approval must also pass.

Outputs

Create or update:

run-state.json
next-action.md
blocked-items.md
handoff.md

Read references/output-contract.md before writing them.

Stop conditions

Stop when a required artifact is invalid, an approval is missing, policies conflict, restricted data cannot be handled safely, or the next action would expand authority.

Verification

Run:

python3 scripts/stg.py validate-artifacts artifacts/
python3 scripts/stg.py validate-connectors artifacts/
python3 scripts/stg.py next-step artifacts/ --objective "현재 사용자 목표"

Treat the CLI result as routing evidence. The user still owns prioritization and approval.

What ships with it: 2 files

1.5 KB alongside SKILL.md

agents/

openai.yaml209 B

references/

output-contract.md1.3 KB