agentleFS
markoblogomarkoblogo/abvx-agent-skills/skills/product-context/SKILL.md

product-context

Skill16 starsChanged 5 months agoMITView on GitHub

Build or refresh a compact, evidence-backed product context before marketing, positioning, SEO, analytics, sales-enablement, or launch work. Use when an agent needs to understand the product, audience, proof, conversion goal, terminology, and claim boundaries without inventing commercial facts.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a small, durable context artifact that lets later product work start from evidence instead of generic positioning.

    line 12
  2. Distinctive:

    Read existing product docs, public copy, analytics contracts, and relevant implementation surfaces.

    line 22
  3. Distinctive:

    Keep only: product and audience, jobs and conversion action, terminology, proof and known limits, approved voice, prohibited claims, source …

    line 25
  4. Distinctive:

    Ask for confirmation where positioning, ICP, pricing, competitor claims, or proof cannot be established from the repo.

    line 26
  5. Distinctive:

    Never invent customer quotes, metrics, market position, availability, pricing, partner status, or legal/compliance claims.

    line 31
  6. Distinctive:

    Keep personal data and private sales evidence out of a committed context file.

    line 32
  7. Distinctive:

    Treat a product context as a reviewable input, not a source of truth over code, current policy, or human direction.

    line 33
  8. Very specific:

    Use these headings where applicable: Product, Audience and jobs, Conversion action, Proof and limits, Language, Claim boundaries, Source …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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 Context

Create a small, durable context artifact that lets later product work start from evidence instead of generic positioning.

Use When

  • entering marketing, content, SEO, analytics, sales, or launch work in a repo;
  • the product, audience, conversion action, or proof boundary is unclear;
  • existing public copy and internal product behavior have drifted.

Workflow

  1. Read existing product docs, public copy, analytics contracts, and relevant implementation surfaces.
  2. Separate confirmed facts from assumptions, placeholders, and claims needing owner confirmation.
  3. Draft or update docs/product-context.md unless the repo already defines a better canonical path.
  4. Keep only: product and audience, jobs and conversion action, terminology, proof and known limits, approved voice, prohibited claims, source surfaces, and last-reviewed date.
  5. Ask for confirmation where positioning, ICP, pricing, competitor claims, or proof cannot be established from the repo.
  6. Link future work to the context; do not treat it as permission to publish, spend, contact people, or change product behavior.

Guardrails

  • Never invent customer quotes, metrics, market position, availability, pricing, partner status, or legal/compliance claims.
  • Keep personal data and private sales evidence out of a committed context file.
  • Treat a product context as a reviewable input, not a source of truth over code, current policy, or human direction.
  • Preserve domain-specific safety language such as financial, booking, or approval boundaries.

Output Shape

Use these headings where applicable: Product, Audience and jobs, Conversion action, Proof and limits, Language, Claim boundaries, Source surfaces, Maintenance.

Pair With

  • evidence-ledger-research for external facts;
  • social-publishing-gate before distribution;
  • bounded-growth-loop before recurring optimization;
  • loop-readiness-review before scheduling any loop.

Provenance

Adapted from the shared-context architecture in coreyhaines31/marketingskills, narrowed to evidence-backed, product-neutral context with explicit claim boundaries.

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.