map
Skill25 starsChanged 7 months agoMITView on GitHub
Extract and structure domain knowledge into domain-map.md for product creation. Asks targeted questions, maps expertise for /create and /fill. Use when the creator says 'map', 'map my knowledge', 'extract expertise', or before complex products.
32 other projects use a version of this.
Adopted by
Most recently taken up by
- BilLogic/uno-blueprinttheir own version, first seen Nov 15, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 9, 2026
- SethGammon/Citadeltheir own version, first seen Nov 4, 2026
- uwonu606/claude-skillstheir own version, first seen Nov 1, 2026
- vidit19sharma/neogentstheir own version, first seen Nov 1, 2026
- duthaho/skillhubtheir own version, first seen Oct 31, 2026
Used with
Projects with it also use ultragoal, cost and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Yeachan-HeoSkillultragoal
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
Also in 3 projects that use this
maxvaegaSkillcost
Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how much would this conversation cost on the API", "API cost of my Cowork conversations", "token usage / token count", "cost per conversation", "/cost", or wants to compare subscription vs API pricing.
Also in 3 projects that use this
marylinSkillrecover
Recover work from a crashed or interrupted session. Use when Claude crashed mid-task, after an unexpected exit, when you see 'stale sessions detected', or when you lost context and need to figure out what was happening.
Also in 3 projects that use this
thoughtbotSkilltrace
Run a scenario and record what actually happened.
Also in 4 projects that use this
iovisorSkillevolve
Evolve uBPF through a gated spec-first workflow that propagates approved changes through requirements, design, validation, implementation, and RFC alignment artifacts.
Also in 5 projects that use this
POSTTTTSkilltidy
Clean up and organize a project's file structure — group loose files into logical folders (images/, scripts/, styles/, etc.), remove empty directories, and delete genuinely unnecessary files. Use when the user asks to "clean up the project", "organize the files", "tidy the directory", "sort these into folders", "remove empty folders", or "get rid of junk files". Always understands the project and updates references BEFORE moving anything, never deletes load-bearing files, and gets approval before changing the file tree.
Also in 3 projects that use this
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- baojie/shiji-kb★ 3.4ksame name
- SethGammon/Citadel★ 927same name
- zeuikli/claude-code-workspace★ 155same name
- mbwsims/claude-universe★ 71same name
- yha9806/academic-writing-toolkit★ 54same name
- sea-gold/skills★ 26same name
- ilanbm/kpopper★ 12same name
- Megaprompting/torque-loop★ 10same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
When to use: Before /create for complex products, when creator has deep domain knowledge to encode, or when exploring what to build.
- Very specific: line 27
Read creator.yaml — load creator expertise domains and technical level.
- Very specific: line 28
If $ARGUMENTS provided, use as domain topic seed
- Very specific: line 29
If previous domain-map.md exists in workspace, load as context
- Very specific: line 41
Ask questions in 3 phases.
- Distinctive: line 81
After all questions are answered:
- Distinctive: line 132
After synthesis, offer 3 methods to deepen the map:
- Distinctive: line 143
Before saving domain-map.md, verify:
“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Domain Mapper
Extract domain expertise from conversation and structure it for product creation.
When to use: Before /create for complex products, when creator has deep domain knowledge to encode, or when exploring what to build.
When NOT to use: For simple products where the creator already knows exactly what to build. Skip to /create instead.
Activation Protocol
- Shared preamble: Load
references/quality/activation-preamble.md— context assembly, persona adaptation, deterministic routing rules. - Read
creator.yaml— load creator expertise domains and technical level. If missing → "Creator profile not found. Run/onboardfirst." and stop. - If
$ARGUMENTSprovided, use as domain topic seed - If previous
domain-map.mdexists in workspace, load as context - Begin structured knowledge extraction
- Load voice identity: Load
references/quality/engine-voice-core.md. Every user-facing line in this skill honors the ✦ signature, three tones, and six anti-patterns. 5b. Load UX vocabulary: Loadreferences/ux-vocabulary.md— translate all internal terms before creator-facing output. 5c. Load proactives: Loadreferences/engine-proactive.md— wire #1 (pipeline guidance: after map, suggest /create with domain context).
Core Instructions
KNOWLEDGE EXTRACTION FLOW
Ask questions in 3 phases. Adapt depth to creator's technical level (from creator.yaml).
Phase 1 — Domain Boundaries (3 questions)
1. What specific domain does this product operate in?
(e.g., "code review for React apps", "database migration safety")
2. Who is the target user? What do they know? What do they struggle with?
3. What existing approaches/tools address this? What's missing?Phase 2 — Expertise Mining (4 questions)
4. What are the top 5 things someone MUST know in this domain?
(The non-obvious knowledge that separates experts from beginners)
5. What are the most common mistakes/anti-patterns in this domain?
(Things that seem right but cause problems)
6. What decision framework do experts use?
(How do they decide between options?)
7. What terminology is essential?
(Terms the product must use correctly)Phase 3 — Product Shape (2 questions)
8. What would a perfect output look like for this product?
(Describe the ideal result after using the product)
9. What are the edge cases — situations where the standard approach breaks?SYNTHESIS
After all questions are answered:
- Structure the knowledge into domain-map.md:
# Domain Map: {domain} Created: {date} | Creator: {name} ## Domain Boundaries - Scope: {what's in / what's out} - Target user: {profile} - Competitive landscape: {existing approaches} ## Core Knowledge (5 pillars) 1. {pillar}: {explanation} ... ## Anti-Patterns 1. {mistake}: {why it's wrong} → {correct approach} ... ## Decision Framework {structured decision tree or matrix} ## Vocabulary | Term | Definition | Usage Context | ... ## Ideal Output {description of perfect product output} ## Edge Cases 1. {case}: {how to handle} ... ## Recommended Product Type Based on this domain, I recommend: {type} because {reason} Alternative: {type} if {condition} - Save to
workspace/domain-map.md(orworkspace/{slug}/domain-map.mdif product exists) - Recommend next step:
Domain mapped! Your knowledge covers {N} pillars and {M} anti-patterns. Recommended: /create {type} — this domain maps best to a {type} product. The domain map will be automatically loaded during creation.
Phase 4 — Elicitation Deepening (optional)
After synthesis, offer 3 methods to deepen the map:
- Inversion: "What would make a product in this domain fail completely?"
- Stakeholder Lens: "How would a [beginner/expert] see this domain differently?"
- First Principles: "Strip all assumptions. What's the irreducible core?"
Creator selects one or skips. Apply selected method to enrich the domain map before saving. If skipped, save immediately and proceed to next step recommendation.
Quality Gate
Before saving domain-map.md, verify:
- At least 3 of 5 knowledge pillars have substantive content (not placeholder)
- At least 3 anti-patterns documented
- Decision framework has at least 2 decision points
- Target user clearly defined
- Recommended product type provided with reasoning
Anti-Patterns
- Shallow extraction — Accepting one-word answers. Push for specifics: "Can you give me an example?"
- Domain overload — Trying to map too broad a domain. Narrow: "Let's focus on the most impactful subset."
- Creator fatigue — Too many questions. If creator seems tired, consolidate remaining questions.
- Assumed knowledge — Don't fill in answers the creator didn't give. Ask, don't assume.
- Generic output — If domain-map reads like any AI could generate it, push deeper: "What do YOU know that's specific to your experience?"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

