agentleFS
etrebelsetrebels/claude-code-growth-os/.claude/skills/product-signal/SKILL.md

product-signal

Skill23 starsChanged 2 months agoMITView on GitHub

Route post-sale and field signals into product's roadmap queue, and write the buyer-facing line for anything shipped. Trigger when the user says "what should product hear", "triage the roadmap signals", "route this to product", "feature request", or "what does this feature mean for the buyer".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't promise a roadmap; this routes the signal and frames the outcome.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Signal

The product function's place in the loop. Marketing has marketing-feedback; CS has account-health; this is product's. It pulls the signals that should shape what gets built out of the shared log into product's own triage queue, and — for anything shipped — writes the one-line "what this means for the buyer" so a feature doesn't land silently. This closes handoffs H4 (CS→product) and H5 (product→GTM) in docs/operating-model.md.

From the shared feedback log (demo/feedback-log.md, or your own) and ops/customers.md:

  1. Pull the product-shaped signals. Three kinds belong on the roadmap, not in a meeting note:
    • RETENTION-RISK lines that are really a product gap — adoption friction or a missing capability, not a CS task.
    • FEATURE-REQUEST items that block an adoption or an expansion (the ones tied to a renewal or a second team).
    • Win/loss reasons that are about the product, not the deal — what we couldn't do that cost us, or won us, the deal.
  2. Route each into ops/roadmap-signals.md. One row per signal: the source, the type, the account or pattern it's tied to, where it's routed, and a status (New → Routed → Shipped). This is product's working surface — distinct from the raw log it's pulled from.
  3. Wait for the pattern on anything ambiguous. A single request isn't a roadmap item; a request that recurs across accounts, or one blocking a real renewal, is. Don't route noise.
  4. Close the loop on anything shipped. For each item that ships, write the one-line buyer-facing translation in the last column: what can the customer now do that they couldn't before — in their language, not the release note's. Hand that line to GTM (it's what marketing-feedback's readers and the deal follow-ups need). No feature ships without it — the antidote to building things no one adopts.

Don't promise a roadmap; this routes the signal and frames the outcome. The build decision is yours.

Depth

  • quick: pull the product-shaped signals from the log into ops/roadmap-signals.md.
  • standard: the full triage above — routed, status-tagged, patterns separated from noise.
  • deep: + the buyer-facing line for each shipped item, ready to hand to GTM.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.