Domain Discovery
Use when the maintainer explicitly requests full-library discovery or a skill taxonomy review. For an agreed skill batch or a concrete code/docs update, use generate-skill instead.
Install
npx skills add TanStack/intent --skill domain-discoverygit clone --depth 1 https://github.com/TanStack/intent.git /tmp/intent
mkdir -p ~/.claude/skills
cp -r /tmp/intent/packages/intent/meta/domain-discovery ~/.claude/skills/domain-discoveryPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Domain Discovery & Maintainer Interview
You are extracting domain knowledge for a library to produce a structured domain map. Your job is not to summarize documentation — it is to build a deep understanding of the library first, then use that understanding to surface the implicit knowledge that maintainers carry but docs miss.
The output is a set of **task-focused skills** — each one matching a specific developer moment ("implement a proxy", "set up auth", "audit before launch"). Domains are an intermediate conceptual grouping you use during analysis; the final skills emerge from the intersection of domains and developer tasks.
There are five phases. Always run them in order — unless the lightweight path applies (see below).
1. **Quick scan** — orient yourself (autonomous)
2. **High-level interview** — extract the maintainer's task map
3. **Deep read** — fill in failure modes and detail (autonomous)
4. **Detail interview** — gap-targeted questions, AI-agent failures
5. **Finalize artifacts**
### Lightweight path (small libraries)
After Phase 1, decide whether the library warrants the full five-phase flow or the compressed flow below. This is a judgment call — lean toward full discovery unless the library is obviously small (single-purpose utility, 2–3 distinct developer tasks max). Use a compressed flow when the skill surface is small enough that two interview rounds would be redundant:
1. **Phase 1** — Quick scan (same as full flow)Details
- Skill name
domain-discovery- Repository
- TanStack/intent
- Path
packages/intent/meta/domain-discovery/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Domain Discovery skill do?
Use when the maintainer explicitly requests full-library discovery or a skill taxonomy review. For an agreed skill batch or a concrete code/docs update, use generate-skill instead.
How do I install the Domain Discovery skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add TanStack/intent --skill domain-discovery. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Domain Discovery popular?
It lives in TanStack/intent, which has 360 GitHub stars and 26 forks.
Related skills
Generate Skill
360TanStack/intent
Use when creating or extending library skill batches, updating guidance after library source or docs change, configuring repository skill distribution, or acting on an Intent review report, including when the maintainer asks only for the library change. For full-library discovery or taxonomy design, use domain-discovery; for generating an approved full-library tree, use tree-generator.
Skill Staleness Check
360TanStack/intent
Use when reviewing an upstream TanStack webhook payload containing the package, commit SHA, and changed files for stale skill guidance. For ordinary library changes or Intent review reports, use generate-skill instead.
Tree Generator
360TanStack/intent
Use when turning an approved domain_map.yaml and skill_spec.md into a full-library skill tree or explicitly auditing its structure and dependencies. For agreed batches and source-driven guidance updates, use generate-skill instead.
Tech Debt Analyzer
473ailabs-393/ai-labs-claude-skills
This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.
Rocprofiler Systems Instrumenting Binaries
500amd/skills
Guides instrumentation with `rocprof-sys-instrument` - choosing runtime instrumentation vs binary rewrite (`-o`), including or excluding functions and modules with regex options, previewing what will be instrumented with a dry run (`--simulate`, `--dump-info`, `--print-*`), tuning granularity (`--min-instructions`, `--min-address-range`, `--instrument-loops`), rewriting libraries, and diagnosing why a function is missing from, or too numerous in, a trace. Use when the user asks about rocprof-sys-instrument, binary rewrite, instrumenting a shared library, function or module include/exclude rege
API Design Review
517dotslashsimran/simcraft
Review the design of an API surface, meaning an HTTP API (OpenAPI spec or route code), an SDK's public classes and functions, or a CLI. Checks naming and consistency, resource modelling, error design (stable codes, RFC 9457 problem details, request ids), versioning and breaking changes, pagination, filtering, idempotency and retries, rate limits, timeouts, long-running operations, webhooks, auth, partial updates, ID, time and money formats, SDK ergonomics and CLI conventions. Uses scripts to lint OpenAPI files, classify changes between two spec versions as breaking or safe, and dump an SDK's p
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.