agentsclimarketplace

Run growth loop

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

Evidence-driven skills that turn customer signals into measurable growth.

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.

2 things to look at

  • 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 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.

What its author says it does

Copied from the file, not written here

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.

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

  1. Validate repository and available artifacts.
  2. Read the run objective, completed skills, approvals, and blockers.
  3. Reconcile stated completion with files and reference integrity.
  4. Identify the first missing or invalid gate.
  5. Route to exactly one specialist skill unless independent work is explicitly requested.
  6. Preserve partial outputs and explain why the run cannot advance.
  7. Ask for human approval at decision and external-action transitions.
  8. Update run-state.json as a new auditable state.
  9. 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.

Gives 0 of the 12 instructions most product growth skills give in 630 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 24 of 728, across 15 files
  • define the ideal customer profilein 21 of 728, across 3 files
  • document a rollback plan before deploymentin 21 of 728, across 12 files
  • analyze the codebase to understand the productin 19 of 728, across 1 file
  • ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • search for companies matching the criteriain 19 of 728, across 1 file
  • look for signals of immediate needin 19 of 728, across 1 file
  • assign a fit score from one to tenin 19 of 728, across 1 file
  • identify the target decision maker rolein 19 of 728, across 1 file
  • suggest a personalized contact strategyin 19 of 728, across 1 file
  • provide conversation starters for outreachin 19 of 728, across 1 file
  • format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • validate repository and available artifacts
  • read objective completed skills approvals and blockers
  • reconcile stated completion with files and references
  • identify the first missing or invalid gate
  • preserve partial outputs and explain the blocker
  • ask for human approval at decision transitions

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.