メニュー
Defines the @samchon/lint-plugin-evidence product contract, workspace layout, package boundaries, and canonical commands. Use when orienting in the repository, working inside any package, or choosing a build, test, or format command.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/samchon/lint-plugin-evidence --skill projectコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Defines the review of @evidence and @evidenceExclude for fake citations, for cited requirements the code contradicts, and for exclusions created solely to evade compiler errors, of configuration edited beyond the one permitted activation, and of the compiler and runtime gates each scope must pass. Read only for a review objective; backend.md, frontend.md, and overall.md carry the per-scope configuration and gates.
Defines how an @samchon/lint-plugin-evidence benchmark campaign is set up, launched under frozen inputs, run, supervised, recovered, and reported, from issue creation through pull-request completion. Use whenever operating, supervising, or reporting a benchmark run.
Defines the Evidence Graph tag grammar, truthfulness rules, claim activation, frozen configuration, behavioral proof, citations, exclusions, and the stub marker. Read before Evidence implementation or handling a graph diagnostic; backend.md and frontend.md carry the per-phase claims, placement, examples, and staged unlock.
SOC 職業分類に基づく
SKILL.md を表示中
| name | project |
| description | Defines the @samchon/lint-plugin-evidence product contract, workspace layout, package boundaries, and canonical commands. Use when orienting in the repository, working inside any package, or choosing a build, test, or format command. |
@samchon/lint-plugin-evidence is an evidence-graph lint contributor for @ttsc/lint. It exists so that a claim made in code carries its proof, and so that a missing or dangling proof fails the build rather than waiting to be noticed in review.
@evidence <target> <reason> tag cites a Markdown section, Prisma model or member, Swagger/OpenAPI operation, or TypeScript symbol as the grounds for a declaration. It lives in a JSDoc block, a Markdown HTML comment, or a Prisma /// comment, depending on which artifact claims.@ttsc/lint runs in the check stage and the exit code sums lint and type diagnostics.lint.config.ts.The contract is general-purpose. autobe-mcp proves the idea with a hardcoded, domain-specific graph; it is prior art and a validation target, not the product definition. The evidence-graph skill owns the domain model, and .wiki/references/ holds what the prior art actually does.
packages/evidence: @samchon/lint-plugin-evidence. TypeScript descriptor, plugin metadata, and config-augmentation types in src/; every lint rule as Go source in native/, with its Go unit tests co-located there as *_test.go. The published tarball must ship native alongside the compiled descriptor, or it builds nowhere but here — see the lint-rule-authoring skill.tests/test-evidence: end-to-end feature tests. Materialize a project, run the real binary, assert the diagnostics.config: shared tsconfig base that packages extend..wiki: Korean knowledge base of prior-art research and decisions. Not documentation; see the wiki skill..agents/skills: these skills.TypeScript owns the descriptor, the configuration types, and the e2e tests. Go owns every rule. This is not a preference: @ttsc/lint has no JavaScript rule runtime, and autobe-mcp/packages/lint ships the same hybrid shape. Do not attempt rule logic in TypeScript.
pnpm install
pnpm format
pnpm build
pnpm test:go
pnpm test