SemanticSkills
CLAUDE.md14 starsChanged 22 days agoApache-2.0View on GitHub
Concept design, semantic modeling, knowledge organization, visual teaching, and Agent DX tooling. Learning copies, downloaded repositories, process notes, raw outputs and generated eval workspaces belong outside the checkout, normally in a task-specific temporary directory. Delete them when no longer needed. Preserve packaged skills/**/references/ and maintained fixtures/examples. - Update the owning repository; keep sibling projects independent and link rather than copy their skills. - Keep localized pairs, declared source versions and catalog.yml consistent; the catalog is the public version record. English…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- ontology-of-everything/concept-skillsword for word, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 1
- ontology-of-everything/concept-skills★ 14100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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.
In this repository22 other files it gives its agents.
- agent-dx-cliSkill
- architect-4cSkill
- architect-4rSkill
- architect-frontend-feature-firstSkill
- architect-frontend-fsdSkill
- concept-designSkill
- concept-modelSkill
- data-knowledge-architectSkill
- personal-knowledge-architectSkill
- read-it-reframe-it-own-itSkill
- simplify-javaSkill
- agent-dx-cli-cnSkill
- architect-4c-cnSkill
- architect-4r-cnSkill
- architect-frontend-feature-first-cnSkill
- architect-frontend-fsd-cnSkill
- concept-design-cnSkill
- concept-model-cnSkill
- data-knowledge-architect-cnSkill
- personal-knowledge-architect-cnSkill
- read-it-reframe-it-own-it-cnSkill
- simplify-java-cnSkill
The file
We split this CLAUDE.md into the rules it gives an agent
12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Update the owning repository.
- Very specific: line 30
Keep localized pairs, declared source versions and catalog.yml consistent.
- Very specific: line 34
Run ./tools/validate-all.sh for public package checks.
- Very specific: line 35
Run ./tools/validate-all.sh --local-qa only for available local QA.
- Very specific: line 38
Commit and publish only within user authorization.
- Distinctive: line 40
Treat credentials, local installs and caches as local-only.
- Very specific: line 42
Keep qa/, docs/, analysis material and generated reports local.
- Distinctive: line 50
Use these terms consistently in both locales.
- Very specific: line 83
Keep supporting material in references/.
- Distinctive: line 88
Never report syntax checks as semantic proof.
- Distinctive: line 89
Keep decision-record status values and format examples consistent with the checker.
- Very specific: line 92
Keep references/diagram-contract.md and scripts/concept_map.py aligned.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
concept-skills
Concept design, semantic modeling, knowledge organization, visual teaching, and Agent DX tooling.
Repository ownership
| Repository | Owns |
concept-skills | Software concepts, semantic modeling, knowledge organization, visual learning, and Agent DX tooling. |
cloud-concept-skills | Huawei Cloud operations, billing, controlled provisioning, and account onboarding. |
handy-skills | Office workflows, source notes, and Agent DX tooling. |
Directory contract
| Directory | Contract |
skills/en/<name>/, skills/zh-CN/<name>-cn/ | Self-contained install payloads, including required references/, assets and scripts. |
qa/ | Private local validation, fixtures and reports; ignored by Git and absent from public checkouts. |
catalog.yml | Tracked discovery metadata used by QA and publishing tools. |
docs/ | Concise local notes and examples; ignored by Git and never required by QA or distribution. |
tools/, .githooks/, .github/ | Repository tooling, local commit/push gates and CI. |
Learning copies, downloaded repositories, process notes, raw outputs and generated eval workspaces
belong outside the checkout, normally in a task-specific temporary directory. Delete them when no
longer needed. Preserve packaged skills/**/references/ and maintained fixtures/examples.
Change and release rules
- Update the owning repository; keep sibling projects independent and link rather than copy their skills.
- Keep localized pairs, declared source versions and
catalog.ymlconsistent; the catalog is the public version record. English uses the base name andlanguage: en; Chinese adds-cnandlanguage: zh-CN. Pairedtranslation_ofvalues name each other. Translate prose while preserving commands, safety gates and observable behavior. The repositoryVERSIONand per-skill catalog versions have separate scopes. - Run
./tools/validate-all.shfor public package checks; it must work withoutqa/. Run./tools/validate-all.sh --local-qaonly for available local QA; no behavioral or live-service result is implied by public checks. - Set
git config core.hooksPath .githooksonce per checkout. Ignore rules and commit/push/CI hygiene checks keep local-only files out of Git, including files added with force. - Commit and publish only within user authorization. ClawHub publishes the editions enabled in
catalog.yml; Chinese skill IDs retain-cn. Verify remote contents before announcing a release. - Treat credentials, local installs and caches as local-only. Keep only the current release notes; rewriting Git history or deleting remote releases requires explicit user authorization.
- Keep
qa/,docs/, analysis material and generated reports local; exclude them even when force-added.
Skill authoring structure
Organize each SKILL.md around its scope, inputs, steps, and completion checks. Add a heading only when it separates useful content. Keep definitions and specification syntax in the shared contract; load task-specific references as needed. Keep each sentence to one point. Use the same term for the same concept. Use RFC 2119 keywords for testable obligations, not general advice. Keep the concept entry and the other three capabilities compact.
Domain language
Use these terms consistently in both locales. Preserve syntax, file names, quoted source text, and external standard names.
| Term | Chinese | Meaning |
| model | 模型 | The design's concepts, behavior, and composition. |
| specification | 规格 | The written expression of a model. |
| contract | 契约 | Allowed behavior that an implementation must preserve. |
| specification conventions | 规格约定 | This repository's notation and interpretation rules in spec-notation.md. |
| concept | 概念 | An independent software behavior with its own purpose, state, and actions. |
| concept instance | 概念实例 | A particular instance that owns its state. |
| operational principle, OP | 运作原理,OP | A representative history that explains how a concept fulfills its purpose. |
| composition | 组合 | Application-specific coordination outside concepts, organized into cohesive rule groups. |
| synchronization rule | 同步规则 | External coordination of concept actions. Code uses a <BusinessAction>Synchronization name. |
| port, adapter | 端口、适配器 | An inner contract for needed interaction, and its technical implementation. |
| facade | 门面 | The public application entry; each operation forwards once to a synchronization. |
| action invocation | 动作调用 | A request to execute an action. |
| action completion | 动作完成记录 | A declared result of an executed action. |
| action occurrence | 动作发生记录 | An identified execution that connects invocation and completion. |
| runtime flow | 运行时 flow | A root event and its causal descendants. |
| query | 查询 | A read that returns binding rows without an action completion. |
| grain | 粒度 | What one fact record represents. |
| fact, dimension, measure, metric | 事实、维度、度量、指标 | Analytical terms defined by the data skill. They are not Jackson concept categories. |
The personal-knowledge skill uses concept for a reusable method and states that local meaning explicitly. Do not apply one skill family's qualification criteria to a different family. Keep confirmed, proposed, inferred, and unresolved statements distinct. Reuse existing confirmation when its scope and content still apply.
Concept-specific rules
catalog.ymlis the discovery source of truth. After catalog changes, runpython3 tools/skill-catalog.py --write; the validation gate checks generated README sections andskills.sh.json.- Concept Design has one entry per language:
concept-designandconcept-design-cn. The former eight workflows are combined here; the other seven entries are retired, not aliases. The other three capability families remain separate. - Maintain core definitions and principles in
concept-design/SKILL.md; keep specification conventions inreferences/spec-notation.md. Link directly to eachmodes/<mode>.md. Keep supporting material inreferences/; name files by their content and responsibility. There are no shared skill dependencies or generated cross-package copies. - The modes are prompt selectors, not shell commands.
scripts/concept_lint.pyis the actual read-only concept-lint CLI. It checks local specification structure, when/then records, and rule-name uniqueness across supplied files for one app. Unknown/legacy call notation returnsnot_checked/exit 3; onlyformat_checkedexits 0. Never report syntax checks as semantic proof. - Keep decision-record status values and format examples consistent with the checker. Public checks run packaged examples and representative failing inputs.
guard mapgenerates the local Concept and Synchronization Diagram, not Jackson's purpose-dependence diagram. Keepreferences/diagram-contract.mdandscripts/concept_map.pyaligned. Version 1 emits one Markdown document; it shares lexical handling with concept-lint and never fills unknown references by inference.- Diagrams use Mermaid in Markdown. Keep explanation views concise and use the map generator for concept/synchronization diagrams.
- Author locale packages directly under
skills/and register them incatalog.yml; keep QA and generated artifacts local.
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.

