discovery-workflow
A modular workflow for researching topics, clarifying requirements, and investigating technical uncertainties.
Install
mkdir -p .claude/skills/discovery-workflow && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10735" && unzip -o skill.zip -d .claude/skills/discovery-workflow && rm skill.zipInstalls to .claude/skills/discovery-workflow
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when researching a topic, discovering or clarifying requirements, tracing evidence, or investigating a technical spike (research, investigation, topic research, technology evaluation, domain analysis, findings report, requirements discovery, elicitation, requirements document, feature definition, use case analysis, requirement clarification, scope definition, acceptance, functional boundary, evidence trace, traceability, data mapping, reference mapping, technical spike, evidence gap, option comparison).Key capabilities
- →Research topics
- →Discover requirements
- →Trace evidence
- →Conduct technical spikes
How it works
It routes research tasks to specialized modules based on the nature of the uncertainty.
Inputs & outputs
When to use discovery-workflow
- →Investigating a new technology stack
- →Clarifying vague project requirements
- →Mapping data requirements
- →Conducting a technical spike to solve uncertainty
About this skill
Discovery Workflow
Covers research, requirements discovery, requirements clarification, evidence tracing, and technical spikes — the full knowledge-gathering phase before design begins.
Module Routing
Identify the task, then load only the matching module via read_file before proceeding.
| Task | Module |
|---|---|
| Broad topic, technology, or domain needs structured investigation before requirements | modules/research.md |
| Research findings or stakeholder input needs to become actionable requirements | modules/requirements.md |
| Requirements exist but scope, ownership, or acceptance is ambiguous | modules/clarification.md |
| An explicit evidence map is needed for a service, feature, or design decision | modules/evidence.md |
| One technical uncertainty blocks design or implementation progress | modules/spike.md |
Load exactly one module, then follow its Procedure section.
Typical Flow
research → requirements → clarification
↑ ↑
evidence ← spike (when technical uncertainty blocks)
When Not to Use This Skill
- Scope is settled and the next step is technical design → use
design-workflow - An approved slice is ready for execution → use
execution-workflow - Documents need to be moved, renamed, or archived → use
document-lifecycle-workflow
When not to use it
- →Technical design
- →Execution tasks
Limitations
- →Requires module loading
How it compares
It provides a structured pre-design workflow, ensuring all knowledge gaps are filled before implementation.
Compared to similar skills
discovery-workflow side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| discovery-workflow (this skill) | 0 | 4mo | No flags | Intermediate |
| competitive-intel | 2 | 2mo | No flags | Advanced |
| github-issues | 0 | 3mo | No flags | Beginner |
| scout | 0 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
competitive-intel
alirezarezvani
Systematic competitor tracking that feeds CMO positioning, CRO battlecards, and CPO roadmap decisions. Use when analyzing competitors, building sales battlecards, tracking market moves, positioning against alternatives, or when user mentions competitive intelligence, competitive analysis, competitor research, battlecards, win/loss, or market positioning.
github-issues
vladmandic
Read SD.Next GitHub issues with the literal string [Issue] in the title and produce a phased markdown report: short summary first, then status, then suggested next steps per issue.
scout
baekenough
Analyze external URL to evaluate fit with oh-my-customcodex project and auto-create GitHub issue with verdict
discovery
ValerianGuivarch
>
INDUSTRY_RND
neej4
INDUSTRY_RND — an agent skill by neej4.
product-manager-toolkit
davila7
Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use for feature prioritization, user research synthesis, requirement documentation, and product strategy development.