stage-11-agentics/c11/distribution

Claude Code and agent skill by stage-11-agentics/c11

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Distribution planning and execution for anything shipped — audience definition, channels classified by who can run them (agent-executable / operator-assisted / operator-only), credibility assets, instrumented funnels, and an execution cadence. Code without distribution is code nobody can use. Invoke on "distribution," "go-to-market," "GTM," "how does this reach users," "market this," or "nobody's using it." Standalone; composed once per project by Tone (from the architect stage onward), per candidate by Chord's champions, and retrofittable onto anything already shipped.

Install

npx vskill@latest install stage-11-agentics/c11/distribution

SKILL.md

Distribution

You are designing how a real thing reaches real users — with the same rigor the build got, because distribution left to hope is the most common way a good build dies. The plan is an artifact, not a vibe: DISTRIBUTION.md at the project root (or the candidate's resolution-book entry, in a Chord portfolio), with every claim carrying a channel, an owner class, and a metric.

The skill's one structural insight: the binding budget is operator attention, and channels differ wildly in how much of it they burn. So the core move is classification — making distribution agent-executable wherever it can be, and honest about where it cannot.

The spine

1. Audience. Borrow venture-partner's currency: specificity. Name the person-shaped profile who needs this most — title, what gets them promoted, what keeps them up at night — and where they already gather. Channels are places populated by the audience, not tactics in the abstract; a channel nobody in the audience reads is theater.

2. Channels, classified by delegability. Enumerate candidate channels, then tag each:

  • agent-executable — agents produce and publish end-to-end: content and SEO, landing pages, docs, directories and listings, launch posts, comparison pages, scheduled updates. Accounts and credentials are operator-granted; platform terms are respected; anything that goes public still clears the operator first (publishing is inherently a public act — Stage 11's privacy-by-default rule applies until the operator says ship).
  • operator-assisted — agents prepare everything, the operator approves and sends: outreach drafts under the operator's name, community posts, partnership pitches, replies. The agent's job is to make the human's ten minutes count.
  • operator-only — personal credibility, warm intros, conference hallways, human-only channels (Signal and personal DMs stay human; agents scaffold facts, never ghostwrite the relationship). Irreducibly human reach — the plan budgets it, batched and scarce.

The tags are the attention budget made visible. A plan whose every channel is operator-only is a plan to drown — flag it and redesign toward channels agents can carry, or descope the reach claim honestly. In a Chord portfolio, re-run the distribution-decorrelation check across all K plans: candidates all drawing on the operator's one network and reputation are correlated bets no matter how different their kill-conditions look.

3. Credibility assets. What must exist before any outreach lands: a real site, a demo that works, proof (numbers, testimonials, a public artifact), a pricing page that answers the first question. Almost all agent-buildable; each is ship-blocking for the channels that need it — outreach pointing at a hollow front costs the audience permanently.

4. Instrumented funnels. Every channel gets a measurable entry — UTM, signup source, referral code — wired into the project's instrumentation before the channel goes live, and a pre-registered bar: what this channel must show, by when, to keep receiving effort. A channel with no metric is a belief; pre-registering the bar is what lets you kill it without an argument later.

5. Cadence. The execution rhythm: agents run the agent-executable lanes continuously; operator lanes batch into scheduled sittings that respect attention; the funnel numbers get read on a stated cadence and channels get killed or doubled per their pre-registered bars. Where a resolution book exists (Chord), the cadence and thresholds land there; where it doesn't (Tone, retrofits), DISTRIBUTION.md carries its own review section.

Composition

  • In Tone: invoke from the architect stage onward — the plan's agent-executable items become build-plan tickets like any other work, and credibility assets join the walking-skeleton sequencing.
  • In Chord: each champion authors its candidate's plan; the conductor runs the cross-candidate decorrelation check; plans live in the resolution book.
  • Retrofit: for anything already shipped and languishing, run the spine as an audit — the gap is usually a missing tag-2/tag-3 honesty (everything was implicitly operator-only, so nothing happened).

Honesty clauses

Some reach is irreducibly human, and the skill classifies rather than pretends — an agent-executable lane never launders an operator-only relationship. And distribution work is publishing: nothing goes public, gets posted, or sends outbound without the operator having said so for that surface — the confirmation is part of the plan, not friction on it.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/stage-11-agentics/c11/distribution/badge)](https://verified-skill.com/skills/stage-11-agentics/c11/distribution)

Something wrong with this skill or its page? Tell us.