メニュー
Use when adding ShapeShift Labs Evidence Kit to a JS/TS project, initializing the full tests/fuzzers/benchmarks/package-boundary/perf-wiki harness, or helping an AI agent establish maximum evidence coverage in another repository.
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。
SOC 職業分類に基づく
Use when creating, adapting, reviewing, or debugging JS/TS fuzzers, corpus fixtures, replay files, shrinkers, repro writers, or deterministic random test harnesses.
Use when mining external JS/TS libraries, runtimes, papers, benchmark suites, bug corpora, or production systems for ideas that should become local tests, fuzzers, benchmarks, or evidence notes.
Use when adapting ShapeShift Labs Evidence Kit to a specific JS/TS project by deriving target-owned source lists, correctness contracts, corpus cases, fuzz generators, benchmark fixtures, source-pass plans, or evidence acceptance criteria from that project's own code, docs, tests, issues, or fetched sources.
Use for JS/TS performance-sensitive changes, benchmark additions, benchmark regressions, benchmark result JSON, or any claim that code is faster, smaller, cheaper, or not slower.
Use when changing JS/TS package exports, startup/import cost, package size, public subpaths, dependency direction, optional peers, tree-shaking, or package-boundary tests.
Use when creating or updating JS/TS performance evidence notes, iteration logs, research notes, generated docs/perf indexes, or searchable benchmark/result summaries.
| name | evidence-bootstrap |
| description | Use when adding ShapeShift Labs Evidence Kit to a JS/TS project, initializing the full tests/fuzzers/benchmarks/package-boundary/perf-wiki harness, or helping an AI agent establish maximum evidence coverage in another repository. |
Use this skill to install the full evidence loop immediately. Do not defer research ingestion, fuzzing, benchmarks, scope checks, package-boundary gates, startup checks, perf search, or perf docs unless the target project cannot run them.
npx evidence-kit inspect --json
If using this repository directly:
node /path/to/agent-evidence-kit/src/cli.mjs inspect --json
npx evidence-kit init --language js
Use --language ts for TypeScript projects. Use --dry-run first if the worktree is dirty or unfamiliar.
Read the generated files and adapt only the project-specific adapters and budgets. Keep the seed/cases/out/check flags intact.
Replace placeholder evidence with a target-owned evidence plan. If the target contract is not obvious, use target-evidence-designer before deep fuzz or benchmark work.
Run:
npm run test:evidence
npm run bench:evidence
npm run docs:perf
npm run research:list
npm run docs:perf:search -- evidence
npm run evidence:full
npm run research:fetch -- source-pass
iterations/. Include what passed, what failed, what was fetched, what was kept, what was rejected, and what remains deferred.