ontology-of-everything
OrganizationOntology, semantic-layer, concept-design, and presentation Agent Skills.
Categories
Indexed Skills (41)
wyx-zh-cn
Declares module boundaries as colocated CONCEPT/PIPELINE/SYNCS specs and detects spec-code drift. Use whenever the user asks for wyx, architecture guardrails, concept specs, coverage audits, drift detection, pipeline invariants, sync maps, or ARCHITECTURE.md（中文：架构护栏、概念规格、规格漂移、模块边界）。
constraint-charter
Persists Uncle Bob's "don't read the code" audit goals, gates, and numeric constraints as a versioned Constraint Charter (GATES.md), settled via grilling and wired into pre-commit/CI so correctness without reading code is part of the software itself. Use when the user says 约束宪章, constraint charter, 把约束固化下来, 立宪, 门禁写进仓库, wants Uncle Bob-style gates as a committed project artifact, or is onboarding a project for agent development under constraints.
claude-md
Creates or prunes CLAUDE.md from verified repository commands, architecture seams, and exceptional conventions, retaining only rules that prevent a concrete agent error.
concept-implementation-cn
Generates a modular-monolith mapping from a confirmed concept model only when the user explicitly invokes $concept-implementation-cn. / 仅在用户显式调用 $concept-implementation-cn 时做模块单体映射。
huawei-cloud-billing-scout
Huawei Cloud BSS billing read-only only (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.
huawei-cloud-cost-estimation
Generate Huawei Cloud pre-order price estimates, safely provision allowlisted resources via hcloud, and guide unsubscribe requests to the console only. Use this skill whenever the user mentions 华为云/Huawei Cloud/hcloud with 报价/询价/价格/quote/pricing/budget, 开通/购买/创建/provision/create, or 退订/unsubscribe. Create requires runtime help, --dryrun, fee review, and confirmation. Never run or emit unsubscribe CLI/API. Refuse other clouds, credentials, payment/renewal/delete, and non-allowlisted writes.
html-slides-cn
Builds a PPT / 胶片 / 汇报 / 授课 deck as a plain single-file 1920×1080 HTML in a pluggable style (Huawei 华为 official light/dark, Apple, generic), confirming outline and per-page table first; optional PPTX export. Use when the user explicitly invokes $html-slides-cn; not for general slide-design questions.
concept-implementation
Implements a confirmed concept model as a modular monolith only when the user explicitly invokes $concept-implementation. Use to map concepts to independent modules, implement synchronization composition, colocate specifications, and verify behavioral and dependency contracts.
concept-audit
Audits concept and application design arguments and optional code conformance only when the user explicitly invokes $concept-audit. Read-only; use for purpose fitness, independence, composition, drift, and product-subset review.
concept-design
Use when the user explicitly invokes $concept-design. Completes a Daniel Jackson concept design with the user. Confirm the alignment, then write the design record.
concept-guardrails
Runs concept-spec guardrails in audit, concept, drift, pipeline, sync, or map mode only when the user explicitly invokes $concept-guardrails. Use to create, backfill, compare, or map colocated concept specifications.
concept-prd
Transcribes a confirmed concept model into traceable PRD and colocated specification files only when the user explicitly invokes $concept-prd. Use to preserve purposes, behavior, synchronizations, assumptions, exclusions, open decisions, and acceptance provenance without redesigning the model.
claude-md-cn
生成或精简 CLAUDE.md，核实仓库命令、架构边界与特殊约定，仅保留能避免具体错误的规则。
html-slides
Builds a presentation as plain single-file 1920×1080 HTML in generic, Huawei, or Apple style, confirming the outline and per-page plan first, with optional PPTX export. Use only when the user explicitly invokes $html-slides; not for general slide-design discussion.
semantic-km-creator
Builds evidence-only Kimball semantic layers from REST/OpenAPI, CLI, or table/database interfaces through an HTML decision workbench, then emits Google OKF or repository YAML. Use for enterprise knowledge modeling, semantic layers, dimensional models, ontology, or OKF.
semantic-pkm-creator
Extracts callable scenes, concepts, and entities from source text for personal knowledge management in two rounds: a deduplicated skeleton for human confirmation, then IPO, decomposition, assembly, and relations with concepts as the hub.
concept-design
Generates Daniel Jackson concept models (purpose, OP, state, actions, syncs) only when the user explicitly invokes $concept-design. / 仅在用户显式调用 $concept-design 时做概念建模。
concept-implementation
Generates a modular-monolith mapping from a confirmed concept model only when the user explicitly invokes $concept-implementation. / 仅在用户显式调用 $concept-implementation 时做模块单体映射。
concept-guardrails
Run concept-spec guardrails (audit, concept, drift, pipeline, sync, map) only when the user explicitly invokes $concept-guardrails. / 仅在用户显式调用 $concept-guardrails 时运行概念规格护栏。
html-slides
Builds a PPT / 胶片 / 汇报 / 授课 deck as a plain single-file 1920×1080 HTML in a pluggable style (Huawei 华为 official light/dark, Apple, generic), confirming outline and per-page table first; optional PPTX export. Use when the user explicitly invokes $html-slides; not for general slide-design questions.
concept-refine
Analyzes and refines existing software concepts. Use when concept designs need evidence-led refactoring for overload, redundancy, narrowness, fragmentation, or synchronization problems.
concept-design-cn
Use when the user explicitly invokes $concept-design-cn. Completes a Daniel Jackson concept design with the user. Confirm the alignment, then write the design record. / 仅在显式调用 $concept-design-cn 时，和用户一起完成概念设计：先确认对齐，再写设计记录。
huawei-cloud-account-onboarding
Checks Huawei Cloud real-name verification (实名认证) status and guides face-scan verification, read-only via hcloud: reads the account's verification state, and when unverified fetches the face-auth QR address, renders it in the terminal to scan by phone, then polls until verified. Use when the user mentions 华为云 / Huawei Cloud plus 实名认证/实名/认证状态/real-name verification, or a Huawei Cloud flow reports verification is required. Face-scan channel only; refuses ID, document, bank-card and SMS-code intake, refuses write operations (enterprise and certificate channels are console-only), and refuses non-Huawei-Cloud identity flows.
semantic-creator
Builds evidence-only Kimball semantic layers from APIs, CLIs, or tables with an HTML decision workbench; emits OKF/YAML. Use this skill when users request semantic layers, dimensional models, ontology, OKF, 语义层、接口转语义、维度建模或本体.
concept-audit-cn
Audits concept-design-cn arguments and optional code conformance only when the user explicitly invokes $concept-audit-cn. / 仅在用户显式调用 $concept-audit-cn 时审查概念设计及实现符合性。
concept-guardrails-cn
Run concept-spec guardrails (audit, concept, drift, pipeline, sync, map) only when the user explicitly invokes $concept-guardrails-cn. / 仅在用户显式调用 $concept-guardrails-cn 时运行概念规格护栏。
concept-prd-cn
Generates PRD files from a confirmed concept model only when the user explicitly invokes $concept-prd-cn. / 仅在用户显式调用 $concept-prd-cn 时转录概念 PRD。
semantic-km-creator-cn
Builds evidence-only Kimball semantic layers for enterprise knowledge from APIs, CLIs, or tables/databases with an HTML decision workbench; emits OKF/YAML. Use when 企业知识、知识建模、KM、semantic-km-creator-cn、semantic-creator、semantic layers, dimensional models, ontology, OKF, 语义层、接口转语义、维度建模或本体.
semantic-pkm-creator-cn
Extracts callable scenes, concepts, and entities from source text for personal knowledge management in two rounds: skeleton with human confirmation, then IPO / decomposition / assembly and relations; concept is the hub. Use when 知识萃取、个人知识管理、PKM、semantic-pkm-creator-cn、sce、三层萃取、IPO、场景/概念/实体.
skill-template
Replace with what the skill does and when to trigger it. Use action verbs and task keywords agents can match.
skill-template
Replace with what the skill does and when to trigger it. Use action verbs and task keywords agents can match.
jackson-concept-design
Models or reviews requirements as Jackson concepts defined by Purpose, OP, State, and Actions, then composes them with Syncs. Use this skill whenever the user asks to discuss requirements, review a concept model, or mentions 概念设计 / 概念建模; stop at model confirmation without producing PRD or code.
jackson-concept-implementation
Maps a confirmed Jackson concept model onto a modular monolith (one module per concept, syncs as mediators or a rule engine). Use this skill whenever the user asks to implement the concept model, 模块单体, or mentions jackson-concept-implementation.
concept-audit
Audits code against a concept model only when the user explicitly invokes $concept-audit. / 仅在用户显式调用 $concept-audit 时做概念审计。
concept-prd
Generates PRD files from a confirmed concept model only when the user explicitly invokes $concept-prd. / 仅在用户显式调用 $concept-prd 时转录概念 PRD。
semantic-km-creator
Builds evidence-only Kimball semantic layers for enterprise knowledge from APIs, CLIs, or tables/databases with an HTML decision workbench; emits OKF/YAML. Use when 企业知识、知识建模、KM、semantic-km-creator、semantic-creator、semantic layers, dimensional models, ontology, OKF, 语义层、接口转语义、维度建模或本体.
semantic-pkm-creator
Extracts callable scenes, concepts, and entities from source text for personal knowledge management in two rounds: skeleton with human confirmation, then IPO / decomposition / assembly and relations; concept is the hub. Use when 知识萃取、个人知识管理、PKM、semantic-pkm-creator、sce、三层萃取、IPO、场景/概念/实体.
concept-refine-cn
Analyzes and refines software concepts. Use when concept designs need refactoring. / 以证据和最小必要改动精炼已有概念，适用于过载、冗余、过窄、碎片化及同步问题。
sce-creator
按两轮流程从原文萃取可��用知识元：先扫骨架（id+define+sources）并等人确认，再回查原文填 IPO/分解/组装与关系。 概念是中枢；场景只编排；实体是实例。Use when 知识萃取、sce-creator、三层萃取、知识组装、IPO、场景/概念/实体.
jackson-concept-audit
Audits an existing codebase against its Jackson concept model (spec drift, boundaries, criteria, composition, dependencies). Use this skill whenever the user asks to audit a concept model, 概念审计, or mentions jackson-concept-audit; read-only.
jackson-concept-prd
Transcribes a confirmed Jackson concept model into PRD documents (overall PRD, one sub-PRD per concept, syncs grouped by flow). Use this skill whenever the user asks for a concept PRD, 规格文档, or mentions jackson-concept-prd; do not invent model content.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.