Delegate independent tasks to specialized agents working concurrently with isolated context.
Discovering Skill
discovering
Use when the what/why is unclear; output is a direction, not a solution.
SKILL.md
Full skill instructions
Discovering Skill
Use when the what/why is unclear; output is a direction, not a solution.
When to Use vs Researching
What's unclear?
├── What/Why (goal, scope, requirements) → Discovering
└── How (technical approach, implementation) → Researching
When to Use
- Idea is vague or underspecified
- Multiple interpretations exist
- Need to align on scope and goals
- Stakeholders have different expectations
Skip if: request is clear and decision-ready (use researching skill instead).
Quick Reference
| Phase | Focus | Output |
|---|---|---|
| Context | Code, docs, recent changes | Current state |
| Intent | Purpose, constraints, criteria | Requirements |
| Directions | 2-3 approaches + trade-offs | Recommendation |
| Confirm | Sign-off | Discovery brief |
Core Rules
- Gather project context first
- One question at a time
- Prefer multiple choice
- High-level directions, not technical solutions
Flow
-
Context — Check code, docs, recent changes
-
Intent — Purpose, constraints, success criteria, scope
-
Directions — 2-3 high-level approaches with trade-offs; recommend one
-
Confirm & Output — Discovery brief:
- Goal (1 sentence)
- Non-goals
- Direction/approach
- Open questions (1-3 bullets)
Get sign-off before proceeding.
Common Mistakes
| Mistake | Fix |
|---|---|
| Jumping to technical solutions | Stay high-level; how comes later |
| Asking multiple questions at once | One question, wait for answer |
| Skipping context gathering | Always check existing code/docs first |
| No clear recommendation | Always pick one direction and explain why |
| Proceeding without sign-off | Get explicit confirmation |
After Discovery
- Technical uncertainty? → Use researching skill
- Direction clear? → Proceed to implementation
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
