agentsclimarketplace

Product discovery

Skill ZC0325/sol-native-guardrails/plugins/sol-native-guardrails/skills/product-discovery

Five narrowly scoped Codex engineering skills that preserve native model judgment.

Install
npx -y skills add ZC0325/sol-native-guardrails --skill product-discovery

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Clarify consequential product, UI, workflow, or architecture ambiguity. Use when unresolved choices could materially change system boundaries, data contracts, user behavior, acceptance criteria, or create expensive rework; do not use for clear, bounded implementation requests.

SKILL.md

1.9 KB, 302 tokens by cl100k_base, as published. Nobody here has run it

Product Discovery

Preserve Codex's native judgment. Clarify only uncertainty that can materially change the result.

Decision Boundary

Before asking the user, inspect the available repository, artifacts, examples, and conventions. Ask whether a reasonable assumption could change architecture, data contracts, user-visible behavior, acceptance criteria, or meaningful risk.

  • If no, state any important assumption briefly and proceed.
  • If yes, identify the smallest set of decisions that must be resolved.
  • Use a fuller design discussion only when several high-impact choices interact or the user explicitly requests design exploration.

Workflow

  1. Summarize the intended outcome and current evidence.
  2. Separate known requirements, reversible defaults, and consequential unknowns.
  3. Ask focused questions in the fewest useful rounds. Batch related questions when that is easier for the user.
  4. Offer alternatives only when they lead to meaningfully different outcomes.
  5. Conclude with a compact decision record: scope, chosen behavior, acceptance criteria, assumptions, and genuine blockers.
  6. Return control to Codex's native planning and implementation process.

Boundaries

  • Do not require a specification file, design document, commit, worktree, or formal approval gate.
  • Do not ask about details that can be discovered from the workspace or safely decided from established conventions.
  • Do not invent requirements to make the design appear complete.
  • Do not block a clear task merely because more detail could theoretically exist.
  • Do not require another skill after discovery.

What ships with it: 1 file

228 B alongside SKILL.md

agents/

Gives 0 of the 12 instructions most product growth skills give in 302 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

  • read product marketing context before asking questionsin 24 of 728, across 18 files
  • define the ideal customer profilein 21 of 728, across 3 files
  • document a rollback plan before deploymentin 21 of 728, across 12 files
  • analyze the codebase to understand the productin 19 of 728, across 1 file
  • ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • search for companies matching the criteriain 19 of 728, across 1 file
  • look for signals of immediate needin 19 of 728, across 1 file
  • assign a fit score from one to tenin 19 of 728, across 1 file
  • identify the target decision maker rolein 19 of 728, across 1 file
  • suggest a personalized contact strategyin 19 of 728, across 1 file
  • provide conversation starters for outreachin 19 of 728, across 1 file
  • format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • Inspect repository, artifacts, and conventions before asking
  • Identify the smallest set of decisions to resolve
  • State important assumptions and proceed if safe
  • Summarize the intended outcome and evidence
  • Separate known requirements, defaults, and unknowns
  • Batch related questions in the fewest rounds

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.