product-context
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 co
Install
npx skills add https://github.com/markoblogo/abvx-agent-skills/tree/main/skills/product-context
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install markoblogo-abvx-agent-skills@llmmart
git clone https://github.com/markoblogo/abvx-agent-skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole markoblogo/abvx-agent-skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
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
- Read existing product docs, public copy, analytics contracts, and relevant implementation surfaces.
- Separate confirmed facts from assumptions, placeholders, and claims needing owner confirmation.
- Draft or update
docs/product-context.mdunless the repo already defines a better canonical path. - Keep only: product and audience, jobs and conversion action, terminology, proof and known limits, approved voice, prohibited claims, source surfaces, and last-reviewed date.
- Ask for confirmation where positioning, ICP, pricing, competitor claims, or proof cannot be established from the repo.
- 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-researchfor external facts;social-publishing-gatebefore distribution;bounded-growth-loopbefore recurring optimization;loop-readiness-reviewbefore scheduling any loop.
Provenance
Adapted from the shared-context architecture in coreyhaines31/marketingskills, narrowed to evidence-backed, product-neutral context with explicit claim boundaries.
Files (abvx-agent-skills)
-
agents
-
openai.yaml 222 B
Loading…
-
-
SKILL.md 2.5 KB
--- name: product-context description: 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. license: MIT metadata: abvx_status: experimental abvx_origin: adapted --- # 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. -
SKILL_CARD.md 1.4 KB
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.