Claude Skills by yannikzz

github.com/yannikzz

24 skillsA× 23B× 10 installs37 views

Release AppBCut and publish a new NarraCat-app version — bump the version number, build the Windows x64 package in CI, package + sign + notarize the macOS build locally, and publish both platforms into one GitHub Release. Use this whenever the user wants to ship a new version, asks what version is live, or wants to know whether a release is ready to go — 发新版 / 发版 / 发布新包 / 打包发出去 / 上线新版本 / 给用户推更新 / 出个正式版 / 现在线上是哪一版. Also use it for anything that goes wrong before, during, or after a release: notarization o...toolsgobashVotes: 0GitHub stars: 93
Release GuardAView or change NarraCat-app's internal-test release gate / remote kill switch (the release-guard Cloudflare Worker in workers/release-guard). Use when the user wants to check the gate's current status (is it blocking users right now?), set or clear the internal-test deadline, trigger or release the emergency brake (kill switch), raise the minimum allowed version, or edit the block-screen notice. 触发词：内测开关 / 急刹车 / 看后台配置 / 改截止日 / 下线版本 / 释放门控 / release guard.ai-agentsbashnodeVotes: 0GitHub stars: 93
Novel Memory IntegrationAGuide for answering natural language questions about novel content by querying NovelMemory MCP read tools from the main conversation. Use when the user asks about character state, relationships, chapter summaries, arc progress, foreshadowing status, or review verdicts of the current novel project.ai-agentsVotes: 0GitHub stars: 93
Novel Reference Analysis MethodAA reference work analysis method providing text decomposition and five-dimension extraction framework (premise / world / characters / structure / style, with narrator voice sub-framework under style) for distilling injectable guidance from user-provided reference novels. Enforces detextualization (paraphrase mechanisms instead of copying proper nouns, signature lines, or imagery) and refuses any ≥10-character verbatim copying. Use only when /narracat:reference command analyzes texts in bible/...ai-agentsVotes: 0GitHub stars: 93
Novel StructureANarrative structure knowledge for long-form web fiction, covering emotional stakes, tension rhythm, climax layering, foreshadowing payoff pacing, value shifts and event architecture, multi-thread weaving, arc design, and chapter ending hooks. Use when planning outlines.ai-agentsVotes: 0GitHub stars: 93
Novel Style ReferenceAA real-novel writing style reference library backed by the novel_query_style_reference MCP tool. Returns annotated extracts from published Chinese novels indexed by technique × emotion. Use the MCP tool to fetch human-written examples that break AI templated expression patterns during chapter writing or review.ai-agentsexpressVotes: 0GitHub stars: 93
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Novel Web CraftAWeb-fiction craft material library consumed by the /write brief compressor — retention mechanics (hooks, pacing, conflict clarity, dialogue load, payoff delivery, chapter-end pull) kept as translation source material for the chapter brief, plus the pack/persona data assets under references/.ai-agentsVotes: 0GitHub stars: 93
next-issueASurveys the current repo's open GitHub issues, ranks them by triage label and dependency graph, and recommends an optimal execution order; when you pick one to start, it gates on whether the issue is clear enough to execute and routes unclear ones to the grill-with-docs skill before any code is written. It can also render the board as a self-contained HTML map that groups issues into business lines, draws their dependency arrows, and spells out which feature each chain ships once completed. U...datapythonrustVotes: 0GitHub stars: 4
Constraint By TypesAPush rules from prose down into the type system so violations become unwritable rather than merely forbidden. Enumerations in the spec become union types, prohibitions become omissions from those unions with a comment marking them deliberate, and the sync order runs spec first then type then code. Use when a written rule needs to survive contact with future code.designgoVotes: 0GitHub stars: 3
Decision InterviewAInterview discipline for turning a vague intent into decisions the user can defend. One question at a time, each carrying a recommendation and its cost; look facts up yourself and put only decisions to the user; land every conclusion in the authoritative document rather than a separate log that will drift. Use whenever another skill needs to ask a user a series of design or scoping questions.designVotes: 0GitHub stars: 3
Decision RecordARecord why a decision was made, what was excluded, and under what conditions to revisit it — as an ADR that points at the rules rather than restating them. Covers which decisions qualify, why decision categories with different lifecycles get separate numbering spaces, and superseding instead of rewriting. Use when a heavyweight decision has just been settled and the reasoning would otherwise be lost.designgoVotes: 0GitHub stars: 3
Deliverable LanguageAWrite deliverables in the language the user is speaking, and pin one rendering per concept so terminology stays stable across runs. Covers picking the language without asking, recording term choices in the authoritative document, and keeping a translated vocabulary consistent. Use whenever a skill produces written artifacts for a user whose language may not be the skill body's language.ai-agentsgoVotes: 0GitHub stars: 3
Spec Before CodeAKeep a written specification ahead of the implementation it governs. Documents change first and code follows; holes the implementation exposes are written back as rules rather than patched silently; overturned conclusions move to an appendix instead of being deleted. Use when a project has a spec that code is supposed to obey, and change requests are arriving.designgoVotes: 0GitHub stars: 3
Ui Contract AssetsABuild the asset layer that lives in a project's production tree - the region-name allowlist as a RegionId union type, region metadata, and the structural container that stamps a runtime region marker. Long-lived code that business features import from, following the project's own stack. Use after the structural spec exists and before any wireframe or feature code is written.developmentjavascripttypescriptVotes: 0GitHub stars: 3
Ui Contract AuditAHealth-check an existing UI contract for drift. Runs automated checks that region names in code stay inside the allowlist, that the RegionId type is not bypassed by casts, that no color values are hardcoded past the token file, and that design.md carries no literal values - then reports the differences with fix suggestions and fixes nothing automatically. Produces a runnable script that lives in the repo and works in CI. Use when a project already has a layout.md or design.md and someone asks...designgoshellVotes: 0GitHub stars: 3
Ui Contract BaselineAReverse-engineer what a project's interface structure actually is today - the real region tree from code or mockups, structural parameters as found, the gap against what a spec would require - and only then ask how existing code should be treated. Writes as-built.md. Use on a project that already has frontend code, before any structural spec is written.designgofrontendVotes: 0GitHub stars: 3
Ui Contract DesignAAlign an existing visual spec (design.md) against the structural spec - add the division-of-labor statement, move structural content out leaving a pointer, replace old component-style names with allowlist names, and move literal values into the token file so design.md holds rules rather than values. Use when a project has visual conventions that need to become a spec with a clean boundary. Or originate one when there are none at all - choose a brand direction on attributes rather than colours...designgoVotes: 0GitHub stars: 3
Ui Contract EnforceAInstall the enforcement that stops a coding agent putting a new feature in the wrong place - an entry clause in the repo-root CLAUDE.md, a directory-level clause, the region-name allowlist compiled into a union type, and an asset boundary forbidding hardcoded token values and locally-declared structural containers. Use once the structural spec exists.designgoexpressVotes: 0GitHub stars: 3
Ui Contract GlossaryAThe vocabulary of a UI contract - what the structural spec, the visual spec and the wireframe each own, the single cut between them (does it change when the brand skin changes), how to mark the few genuine coupling points, and the canonical term renderings. Use when another ui-contract skill needs to decide which document a piece of content belongs in.designgoawsVotes: 0GitHub stars: 3
Ui Contract LayoutAProduce layout.md, the structural spec - a total placement decision tree, a region-name allowlist where every row states what it must not hold, extension rules, content routing and degradation rules. Everything that does not change when the brand skin changes. Use when a project needs written rules for where a new feature goes.designgofrontendVotes: 0GitHub stars: 3
Ui Contract SetupASurvey what a repo already has before any UI contract work starts - existing visual specs, token sources, structural docs, frontend stack and agent instructions - classify the starting point, and ask only the authorisations that cannot be derived from disk. Writes docs/ui-contract/config.md plus a pointer line in the repo-root CLAUDE.md.designtypescriptgoVotes: 0GitHub stars: 3
Ui Contract WireframeABuild the runnable low-fidelity wireframe that consumes the asset layer - an annotation layer over every region, real copy and real density, degradation rules actually implemented, and the asset layer's brand deliberately overridden to neutral greys. Use when the structural spec exists and a runnable reference is needed before feature code is written - the visual spec is an optional input, not a prerequisite.designgoshellVotes: 0GitHub stars: 3
Ui ContractAEstablish a project's UI contract by interview: layout.md (structural spec - placement decision tree, region-name allowlist, extension rules), design.md (visual spec; the token file holds values), an asset layer in the production tree, a low-fidelity wireframe, and enforcement that stops agents putting features in the wrong place. Use when the user wants a design system or design spec, a layout or structure spec, information architecture (IA), a module or region breakdown, rules for where a n...designtypescriptgoVotes: 0GitHub stars: 3
caramel-puddingA基于「焦糖布丁理论」（Jobs-to-be-Done 任务理论）的文案升维引擎——把产品/功能从「产品维度」升到「用户真实任务维度」，找到不同维度的对手，产出整套官网与运营海报宣传文案。当用户想优化或重写官网/Landing Page 文案、提炼卖点与 slogan、写运营海报/营销文案、觉得现有文案太平/同质化/容易被竞品复制、想从用户真实需求(JTBD)角度重新定位产品，或直接点名「焦糖布丁理论 / 任务理论 / 顾客要的不是电钻是洞」时，都应使用本技能——即使用户只说「帮我把这些功能写成宣传语」「这个产品该怎么宣传」而没点名理论。content-marketinggoVotes: 0GitHub stars: 2