continuous-discovery

continuous-discovery is a skill for Claude Code from wondelai/skills. It costs 142 tokens per session (2,983 once invoked), scanned A, original, MIT.

A framework for making customer research a regular part of product work. It uses visual maps, assumption checks, and brief interview notes to connect customer needs with product decisions.

In plain words
What is it for?
It is for planning weekly customer conversations, mapping product opportunities, recording interview findings, testing assumptions, and linking features to desired outcomes.
Why use it?
It helps teams avoid relying mainly on guesses, stakeholder opinions, or occasional research. Regular customer conversations provide fresh evidence for deciding what to build.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the product-innovation plugin — 6 skills shipped together

Good fit It is for planning weekly customer conversations, mapping product opportunities, recording interview findings, testing assumptions, and linking features to desired outcomes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wondelai/skills/continuous-discovery
About the project

Wondel.ai Agent Skills is a collection of skills and guided workflows that give coding agents structured methods for business, marketing, UX, website, app, and software-development tasks. It is used with agents such as Claude Code, Codex, Cursor, OpenClaw, and other agents that support the agentskills.io format. The catalogue entries are the project's skills, plugins, instructions, and rule packaged for those agents.

wondelai/skills · 2,132 stars · on GitHub · skills.wondel.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add wondelai/skills --skill continuous-discovery
Clone the repo
git clone --depth 1 https://github.com/wondelai/skills

Made for: Claude Code.

Or install product-innovation, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for continuous-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/wondelai/skills/continuous-discovery/github.svg)](https://agentmods.dev/skills/wondelai/skills/continuous-discovery)
Your own site
<a href="https://agentmods.dev/skills/wondelai/skills/continuous-discovery"><img src="https://agentmods.dev/badge/skills/wondelai/skills/continuous-discovery/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for continuous-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/wondelai/skills/continuous-discovery"><img src="https://agentmods.dev/badge/skills/wondelai/skills/continuous-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,983 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 6 Apr 2026
  • Snyk pass 6 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.02983
Opus 5 $0.00071 $0.01491
Sonnet 5 $0.00028 $0.00597
Haiku 4.5 $0.00014 $0.00298

Measured 10d ago against content hash 44260b572a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

continuous-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

continuous-discovery/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuous Discovery Habits Framework

Framework for building a sustainable weekly practice of customer discovery that keeps product teams progressing toward desired outcomes. Discovery is not a phase before development — it is embedded in the ongoing rhythm of product work so every decision is informed by fresh evidence.

Core Principle

Good product discovery requires a continuous cadence, not a one-time event. Teams that talk to customers every week, map opportunities visually, and test assumptions before building consistently outperform teams that rely on intuition, stakeholder opinions, or quarterly research cycles. The benchmark: at least one customer touchpoint per week, every week, by the product trio (product manager, designer, engineer).

Scoring

Goal: 10/10. Score a discovery practice by the seven Quick Diagnostic rows below — start at 3, add 1 point per row answered "yes" (max 10). Bands: 9-10 = weekly cadence, a living Opportunity Solution Tree, systematic assumption testing, and every shipped feature traceable to a customer opportunity; 5-6 = some discovery happening but ad hoc, PM-only, or disconnected from delivery; ≤3 = intuition- and stakeholder-driven with no regular customer contact. Report the current score, the failing rows, and the specific fix for each.

Framework

1. Opportunity Solution Trees

Core concept: An Opportunity Solution Tree (OST) visually connects a desired outcome (top) to customer opportunities (middle) to potential solutions and experiments (bottom), making implicit product thinking explicit and shared.

Why it works: Most teams jump from business outcome straight to solutions, skipping the customer need entirely; the OST forces understanding of the opportunity space first, preventing features nobody wants.

Key insights:

  • Four layers: Outcome > Opportunities > Solutions > Experiments
  • Opportunities are customer needs, pain points, and desires — framed from the customer's perspective
  • The tree is a living artifact, updated weekly as the team learns
  • Break large opportunities into smaller sub-opportunities to make them actionable
  • Pursue multiple opportunities simultaneously — don't bet everything on one

Read the full file on GitHub · 203 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 203 lines · 142 tokens per session scan A 44260b572a05

Subscribe to this mod's changes

continuous-discovery is a skill published in the GitHub repository wondelai/skills (2,132 stars, last pushed 10d ago), licensed MIT. It adds 142 tokens to every session and 2,983 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dotnet-dependency

This skill should be used when investigating .NET project dependencies, understanding why packages are included, listing references, or auditing for outdated/vulnerable packages.

NikiforovAll/claude-code-rules · 35 tokens

team-review

Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers. This skill should be used when the user says "team review", "review with team", or wants parallel code review with persistent team members for follow-up questions. Similar to /subagent-review but reviewers persist after…

NikiforovAll/claude-code-rules · 65 tokens

codex

Route a task to OpenAI's Codex CLI (codex exec) instead of doing it yourself. Use this skill ANY time the user names codex or types /codex — even for routine work Claude could handle, because the user is choosing to delegate. The intent: 'ask codex', 'have codex review/refactor this', 'check/validate with codex', 'see…

sparklingneuronics/sparkling-skills · 249 tokens

typescript-coder

Implements TypeScript/JavaScript code following established architecture and coding guidelines. Use when implementing features designed by typescript-architect.

DmitriyYukhanov/claude-plugins · 30 tokens

playwright-storybook-flows

Specialization of playwright-harness for AUTHORING and REPRODUCING flows. A flow is a sequence of steps a human or an agent can take inside an application to demonstrate a specific feature; it is written as a Storybook docs page in a conventional location, where a human reads it as a manual walkthrough (issue…

simiancraft/simiancraft-skills · 158 tokens

economist-style

Apply The Economist style guide to written content. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity. Detects weasel words, fillers, passive voice, and style issues.

TAJD/economist-style-guide-plugin · 54 tokens