product

boshu2/agentops

Create or refine PRODUCT.md by separating evidence from aspiration, users, value, and non-goals.

What is product?

This skill helps you build a product contract that forces every claim into either grounded evidence or labeled aspiration. Use it when defining or refining a product boundary, ensuring clarity between what is proven and what remains unproven hope.

Inspects existing product documentation, README, goals, and evidence sources
Separates proven claims (with resolvable citations) from unproven assumptions and aspirations
Defines mission, users, pains, value, differentiation, and non-goals
Prevents 'aspiration laundering'—unproven hopes masquerading as fact
Preserves existing PRODUCT.md unless explicitly authorized for replacement
Returns a structured document for downstream planning and context

How to install product

npx skills add https://github.com/boshu2/agentops --skill product

Claude Code

Cursor

Windsurf

Cline

How to use product

1.Invoke the skill with 'product', 'create PRODUCT.md', or 'product boundary'
2.Provide or allow the skill to inspect existing product documentation, README, and evidence sources
3.Answer focused questions about decisions that cannot be grounded in existing sources
4.Review the generated PRODUCT.md, ensuring all Proven claims have resolvable citations
5.Refine only the sections you requested changes to; the skill preserves the rest byte-for-byte

Use cases

Good for

Establishing a clear product boundary when launching a new service or feature
Auditing an existing PRODUCT.md to move unsubstantiated claims from Proven to Assumptions
Aligning a team on what is evidence-based versus what remains to be validated
Preventing false premises from cascading into downstream plans and decisions
Documenting the operations layer for agentic systems with clear scope and non-goals

Who it's for

Product managers defining or refining product scope
Engineering leads establishing bounded contexts for services
Teams practicing lean-startup or domain-driven design
Stakeholders needing clarity on proven capabilities versus aspirational goals

product FAQ

What is 'aspiration laundering' and how do I avoid it?

Aspiration laundering occurs when an unproven hope is written in the Proven section without a citation. Detect it by checking that every Proven claim has a resolvable source (README, release, test, or evidence). Move any unsubstantiated claim to Assumptions or cite it.

Should I replace my entire PRODUCT.md or refine it?

Preserve your existing PRODUCT.md unless you explicitly authorize replacement. The skill refines only the sections you ask to change, keeping the rest byte-for-byte intact to avoid losing valid context.

What goes in Proven vs. Assumptions?

Proven contains only grounded claims with resolvable citations. Assumptions holds unproven hopes, evidence gaps, and success signals not yet measured. If you cannot cite a source, it belongs in Assumptions.

Can this skill select work or invoke a loop?

No. This skill creates or refines the product contract only. It does not select work, invoke a loop, repair itself, validate itself, or choose delivery—those are separate concerns.

What if I have no existing PRODUCT.md?

The skill will create one from scratch, starting from your mission, users, pains, value, and non-goals. It will ask only for decisions that cannot be grounded in existing sources like README or release notes.

Full instructions (SKILL.md)

Source of truth, from boshu2/agentops.

name: product description: 'Create or refine PRODUCT.md while separating evidence, aspiration, users, value, and non-goals. Triggers: "product", "create PRODUCT.md", "product boundary".' practices: [lean-startup, ddd-bounded-context] hexagonal_role: domain consumes: [] produces: [PRODUCT.md] context_rel:

kind: supplier-to with: plan skill_api_version: 1 user-invocable: true context: window: inherit intent: mode: task metadata: tier: product dependencies: [] capabilities: [shape_product_boundary] effects: [write_product_document] canonical_status: canonical disposition: keep_specialist output_contract: PRODUCT.md

Product

Create or refine a product contract with the user's authority.

The contract works because it forces every claim into evidence or labeled aspiration; if a reader cannot tell which is which, the document has failed.

Inspect existing product, README, goals, release, and evidence sources.
Ask only for decisions that cannot be grounded safely from those sources.
State mission, users, pains, value, differentiation, and non-goals. For this repository's own product surfaces, start from the canonical category in docs/contracts/ubiquitous-language.md (AgentOps is the operations layer for agentic engineering) and preserve the small ownership boundary — never re-frame AgentOps as an execution orchestrator, factory, or loop.
Separate evidence from hope under two required headings. Put every grounded claim under ## Proven, each carrying a resolvable citation (a README, release, test, or evidence source). Put unproven hopes, evidence gaps, and not-yet-measured success signals under ## Assumptions. A claim that cannot cite a source belongs under ## Assumptions, never ## Proven.
Preserve an existing PRODUCT.md unless the user authorizes replacement.
Return the document to the caller; Plan may use it as intent context.

Named failure mode — aspiration laundering: an unproven hope written in the ## Proven section; once laundered, every downstream plan inherits a false premise. Detector: any ## Proven claim without a resolvable citation is a laundered aspiration — move it to ## Assumptions or cite it.

Anti-pattern: rewriting a healthy PRODUCT.md wholesale because the session has fresh opinions. Corrective: refine only the sections the user asked to change and preserve the rest byte-for-byte.

Product does not select work, invoke a loop, repair itself, validate itself, or choose delivery.