Authoring workflow that turns a feature spec, risk area, or bug cluster into a session-based exploratory testing charter per Jonathan and James Bach's SBTM - frames the one-sentence mission, scopes 3-7 areas, picks a 60 / 90 / 120 min time-box, suggests tours, and wires the PROOF debrief deliverables. Per Bach, exploratory testing is "performing tests while learning things that may influence the testing" - the charter sets the mission while leaving exact steps to the tester's judgment. Use when a feature has too many unknowns to script (new feature / refactor blast-radius / bug cluster) and a session-based exploration is the right approach. Authors the charter only: the ready-to-fill charter card, session vocabulary, debrief template, and session review live in the exploratory-testing skill this workflow composes with.
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見るインストールする前に、エージェントに与えられる指示の中身を確認できます。
A charter is the structured-but-open frame of an SBTM session: it tells the
tester what to learn, not what to click. This skill is the authoring
workflow - from a raw input (spec, diff, incident) to a filled charter card.
The card format itself, the session vocabulary, and the time-box rationale are
owned by exploratory-testing; the
ready-to-fill card is its charter-template reference.
This workflow fills that template - it does not redefine it.
Input: a feature spec / story, a diff / changeset, a bug cluster / incident postmortem, or a backlog item labeled "needs exploration." Output: a charter card the tester executes and reports against.
The mission is the load-bearing field - one sentence telling the tester what to learn. Three patterns:
| Pattern | Example mission |
|---|---|
| New feature | "Explore the new promo-code apply flow at checkout to discover usability issues, edge cases, and integration risks." |
| Refactor / change risk | "Explore cart and checkout after the cart-state refactor to find regressions in state persistence." |
| Bug cluster / risk area | "Explore the Stripe webhook handler with focus on retry / out-of-order delivery after the webhook-replay incident." |
A mission is not "test the checkout page" (too vague) or "verify promo codes apply" (too narrow - that's a scripted test).
Areas (3-7 per 90-min session) scope the exploration; they are what to look at, not what to assert. Derive them from the input: spec sections, diff blast-radius, or the bug cluster's common surface.
Time-box lengths (60 / 90 / 120 min) and their rationale:
exploratory-testing.
Suggested tours, and how many to pick per session: the tours reference in
exploratory-testing.
The charter suggests; the tester picks. For the Bad-data tour, point the
tester at
malicious-payload-bank.
Sessions deliver a structured PROOF debrief into the
exploratory-testing debrief template (its debrief reference); the
debrief fields and the session-sheet structure are owned by that skill.
The charter's deliverables block names three things:
BUG-* format via
bug-repro-builder.Assemble mission (Step 1), areas + time-box + suggested tours (Step 2), and
deliverables (Step 3) into the card format from the exploratory-testing
charter-template reference,
adding the source artifact ("Created from: story / diff / incident"), the
target build / SHA, and an explicit out-of-scope list (performance / load →
k6-load-testing;
a11y → qa-accessibility; cross-browser → qa-web-e2e).
Do not emit a charter that violates any of these:
manual-test-script-author.exploratory-testing debrief reference.bug-repro-builder.exploratory-testing - owns the charter
card template, tour catalog, session sheet, and PROOF debrief this workflow
fills.まだレビューはありません。使ってみた感想をお寄せください。
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
Builds a CI gate that fails the build on **new** WCAG / a11y violations introduced by a PR while grandfathering pre-existing violations on a per-rule / per-page baseline. Aggregates verdicts from axe-core / pa11y / Lighthouse a11y / WAVE / IBM Equal Access scans. Use when a project has accumulated a11y debt and a strict "zero violations" gate would block every PR - the ratchet pattern lets the team ship while preventing regressions.
日本語の概要は準備中です。原文の説明を表示しています。
Workflow skill that builds an A/B-test validity checklist from an experiment proposal, walking the canonical design-correctness gates - pre-registered OEC/power/guardrails, randomization unit + SRM check, assignment integrity, telemetry, peeking discipline, novelty/primacy, post-experiment SRM re-check - into a per-experiment checklist + sign-off form. Use when launching, auditing, or governing an experiment. For pitfall mechanics (guardrails, peeking) see experiment-results-interpreter's references; to read an already-valid result use experiment-results-interpreter; for per-SDK harness tests use experiment-sdk-testing - this gates DESIGN, not SDK code.
日本語の概要は準備中です。原文の説明を表示しています。
The single install-flow skill: the reference contract for the PWA install flow (installability gate fields, `beforeinstallprompt` handshake, per-platform paths - Android WebAPK / iOS Share menu / Firefox no-op - and the `display-mode` post-install signal, in references/install-flow-reference.md) plus the build-an-X workflow that emits the Add-to-Home-Screen suite. Walks the four-stage timeline, emitting one test per gate cell per [web.dev/articles/install-criteria][install-criteria], the deferred-prompt → `prompt()` → `userChoice` chain per [web.dev/articles/customize-install][customize-install], the iOS Safari manual-metadata branch (`apple-touch-icon`) per [web.dev/learn/pwa/installation][learn-pwa], and the post-install `(display-mode: standalone)` MQ assertion. Output: a Playwright spec with per-stage cells plus a coverage matrix. Use when a PWA's manifest, icons, or install handler change, when install conversion drops at an unknown stage, or when triaging a flaky install assertion.
日本語の概要は準備中です。原文の説明を表示しています。
Build-an-X workflow that uses an LLM to map existing tests to spec sections - given a spec doc + the test suite, the LLM identifies which tests cover which sections, surfaces uncovered sections (gap), and recommends specific tests to add. Output is a coverage matrix per spec ID. Scope is mapping tests that already exist and naming the gaps, not authoring tests for new acceptance criteria. Use when a spec doc and a test suite both exist but nobody can say which requirements are actually covered - before a release sign-off, an audit, or a decision about where to spend the next round of test effort.
日本語の概要は準備中です。原文の説明を表示しています。
Generates tests from natural-language specs (acceptance criteria, user stories, requirements) using an LLM, with confidence scoring per test case (LLM self-assessment plus heuristics: assertion quality, naming, completeness), batching uncertain cases for human review, and integration with the team's existing test framework. Use when the user asks to generate unit tests from acceptance criteria, convert user stories to test cases, automate test creation from requirements, or augment a spec-driven test suite with AI-generated stubs that are then curated before merge.
日本語の概要は準備中です。原文の説明を表示しています。
Configures Allure Report (test-runner adapter install, `allure-results` directory wiring, `categories.json` for failure classification, `history-trend.json` retention via the copy-history-between-runs pattern), runs the Allure CLI to convert `allure-results` to a static HTML site, and uploads the report as a CI artifact. Use when the team needs richer test reporting than JUnit XML - step-level attachments, per-test history, retry tracking, and severity / epic / feature labeling across framework-agnostic adapters (pytest, Jest, JUnit, TestNG, NUnit, Mocha). As a rich static HTML report generator, it is the open-source alternative to the sunset ExtentReports (JVM/.NET per-test HTML narrative); for hosted cross-run flakiness analytics rather than a static per-run report use currents-integration.
日本語の概要は準備中です。原文の説明を表示しています。