st4ck

Plugin st4ck from marketplace st4ck-marketplace in edo-ceder/st4ck-plugin. Commands read from the repo's manifest — 3 days ago.

Skills (16)

• bootstrap-components

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

• impact

  Phase 5 §5.2 — agent-driven test impact analysis. Reads the local git diff, calls get_tests_affected_by_diff, creates test_design_change dev_tasks per affected component. Optionally invokes the propose subworkflow to attach proposed component diffs. Triggered explicitly via `/st4ck:impact` or auto o

• migrate-agentic-to-v2

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

• plan-author

  Create comprehensive implementation plans for features including phased tasks, security analysis, test strategy, and migration files. Use when transitioning from approved requirements to implementation.

• prd-from-source

  Author a Product Requirements Document from an existing codebase, code export, or unpacked low-code project — by reading source rather than asking the user. Use when the user wants a PRD generated from imported elements, exported builders (Bubble, Webflow, Retool), screen recordings, or any "code-fi

• prd-review

  Review a Product Requirements Document end-to-end in iterative rounds — self-review + three independent reviewer agents (PO / QA / Dev angles) — and converge when findings reach diminishing returns. Pairs with the `prd-from-source` skill but is reusable for any PRD authored in the file-based, source

• qa-testing-bootstrap-components

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

• qa-testing-debug

  Use this skill when a test or component has FAILED and needs diagnosis + fix. Triggers on phrases like "this test is failing", "debug this test run", "the runner is erroring", "fix this component", "selector is wrong", "block N failed", "test X broke". Reads the execution log, classifies the failure

• qa-testing-migrate-agentic-to-v2

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

• qa-testing-migration

  Migrate legacy tests to the v2 component format. Triggers on "migrate these tests", "convert to component format", "modernize tests", "upgrade components". Classifies each test's shape via classify_test_migration_shape, then runs the appropriate internal branch (agentic re-author OR component-upgrad

• qa-testing-regression

  Use this skill when the user wants to author regression tests that protect shipped behavior. Triggers on phrases like "create regression tests for", "protect this module", "regression coverage for", "add regression suite". You — the current session agent — are the authoring lead; you dispatch one `q

• qa-testing-upgrade-components-v1-to-v2

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

• qa-testing-version

  Use this skill when the user wants to author version tests for in-development features — tests that go GREEN as implementation completes phase-by-phase. Triggers on phrases like "write tests for this feature", "version tests for this plan", "test coverage for this implementation", "author tests for

• requirements-authoring

  Create or materially revise product requirements in a st4ck project from authoritative conversations, decisions, designs, existing specifications, and evidence. Use when the user asks to author, extend, edit, or restructure canonical requirements, or explicitly requests a requirements-quality review

• st4ck-semantic-layer

  Use when authoring or updating a st4ck project's MCP semantic-layer docs (under the project's st4ck/docs/MCP — the business-language-to-data guide an LLM reads before answering questions about that project's live data). Trigger after any data-model change (new/renamed field, option set/enum, table,

• upgrade-components-v1-to-v2

  Forwarding stub. This skill was consolidated into qa-testing-migration on 2026-04-26 (plan §13.2, mid-12). Activate qa-testing-migration instead — it covers Path A (heavy re-author) AND Path B (light component-upgrade) inline, with classify_test_migration_shape selecting the branch per test.

Slash commands (16)

• /st4ck:build

  Plan or build a major feature as a st4ck build plan.

• /st4ck:debug

  Debug and fix bugs with role-separated agents — research, test gaps, fix, verify green. You are the dev manager.

• /st4ck:impact

  Phase 5 §5.2 — agent-driven test impact analysis. Reads the local git diff, surfaces every QA test whose components cite the changed lines, queues test_design_change dev_tasks for QA. Optionally generates proposed component updates with --propose.

• /st4ck:implement

  Full feature lifecycle — requirements → plan → code → QA → deliver. Role-separated agents with human gates.

• /st4ck:migrate-tests

  Migrate legacy tests to v2 component format. Activates the qa-testing-migration skill, which classifies each test by shape (agentic / components_v1 / components_v2 / mixed) via classify_test_migration_shape and runs the appropriate internal branch (agentic re-author OR component-upgrade) inline. Per

• /st4ck:open-project

  Open the st4ck project connected to this folder.

• /st4ck:po-research

  PO feature research — explore codebase, challenge requirements, surface logic gaps, present solution options with effort/risk.

• /st4ck:prd-from-source

  Author a Product Requirements Document by reading source code rather than asking the user. Source-grounded, self-contained, works with or without an app.st4ck.io connection.

• /st4ck:prd-review

  Review a PRD end-to-end. Self-review → 3 parallel independent reviewers (PO / QA / Dev) → known-gaps-vs-code → bug-routing. Converges on diminishing returns.

• /st4ck:qa-testing-debug

  Diagnose and fix a failed test or component. Reads the execution log, classifies the failure, proposes a scoped fix, and drives the fix to green without scope creep.

• /st4ck:regression-author

  Author regression test suites for shipped features — protects what already works. Explicit form of the qa-testing-regression skill.

• /st4ck:regression-run

  Execute signed regression test suites and report results with evidence. Observe-only — does not attempt to fix code.

• /st4ck:st4ck-browse

  Drive a real browser one IPC primitive at a time via the `st4ck browse` CLI. Each subcommand is one Bash invocation; the wrapper hides the runner + FIFO behind the scenes. Multi-session out of the box. Optional `--record` saves the trace as a deterministic md test you can replay with `st4ck run`.

• /st4ck:st4ck-run

  Execute a deterministic test case using the st4ck runner. Handles agentic block handoff via IPC pause and rerun from failure.

• /st4ck:supervise

  Pause and regroup — reviews the session transcript and reminds you what we're doing, what you said, and what's left.

• /st4ck:version-author

  Author version tests for in-development features — tests that go GREEN as implementation lands phase-by-phase. Explicit form of the qa-testing-version skill.

Subagents (10)

• code-agent

  Use this agent to implement features from the plan's task list. Writes code, unit tests for pure functions, and runs quality gates. Never writes or reviews QA tests.

• code-reviewer

  Use this agent to review code changes for bugs, logic errors, security vulnerabilities, and adherence to project conventions. Returns findings with confidence scores.

• codebase-explorer

  Use this agent to explore and understand a codebase — traces architecture, patterns, dependencies, similar features, data models, and git history. Returns structured findings for planning.

• prd-reviewer-dev

  Independent developer reviewer for a Product Requirements Document. Verifies source provenance, spot-checks claims against the cited source code/export, and identifies dead-code claims or shallow decomposition. Used as one of three reviewer angles by the prd-review skill. Cannot modify the PRD — rea

• prd-reviewer-po

  Independent PO/stakeholder reviewer for a Product Requirements Document. Reads the PRD from a non-technical product-owner perspective and reports findings with severity and source citations. Used as one of three reviewer angles by the prd-review skill. Cannot modify the PRD — read-only with structur

• prd-reviewer-qa

  Independent QA reviewer for a Product Requirements Document. Reads the PRD from a test-engineer perspective focused on testability, coverage, and state-transition verifiability. Used as one of three reviewer angles by the prd-review skill. Cannot modify the PRD — read-only with structured report out

• qa-author

  Primary authoring teammate. Drives a single Session per test journey, captures primitives, decomposes the trace into save_component(s) + create_test_case at the end of the drive. Same prompt for feature, version, regression, and migration authoring. Cannot modify code files.

• qa-reviewer

  Use this agent to review and sign QA test cases it did not author. Verifies UI strings, routes, and assertions against the actual codebase. Cannot modify code files.

• qa-runner

  Use this agent to execute one or more signed QA tests against a target environment. Drives the `st4ck` CLI (`npx st4ck@latest run`) — handles agentic-block IPC pauses inline and returns structured per-test verdicts (passed/failed/blocked, execution_id, evidence). Cannot author tests, modify componen

• solution-analyst

  Use this agent to analyze implementation approaches for a feature and present effort/risk/trade-offs in PO-friendly language. Translates technical architecture into decision inputs.

Hooks (2)

• UserPromptSubmit

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/supervisor-extract.sh"

• PostToolUse

  bash "${CLAUDE_PLUGIN_ROOT}/hooks/sub-agent-verify-reminder.sh"

Similar plugins