菜单
Use when a framework command needs to inspect the project's visual-regression baseline store — the codePath-native tests/visual/ snapshot tree. Reads the store defensively via scripts/screenshot-store-read.sh and returns structured JSON. Never blocks on malformed input.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when creating Claude Code plugins - covers skills, commands, agents, hooks, MCP servers, and plugin configuration. Use when user says "create plugin", "make a skill", "add command", "add hooks", "skill authoring", "SKILL.md", "plugin components", "package reusable behavior", "distribute skills", "scaffold plugin", "plugin structure", "write a skill description". NOT for: using existing plugins, installing plugins, plugin marketplace browsing. !`ls .claude-plugin/ 2>/dev/null`
Use when starting a new development project — creates memory folder structure with project_state.md (including codePath), architecture scaffolding, and registers project. Accepts optional code_path argument.
Use when checking code quality, running security audits, testing coverage, finding SOLID/DRY violations, or setting up quality tools. Use when user says "audit this code", "check security", "run PHPStan", "code quality", "find violations", "SOLID check", "DRY check", "test coverage", "lint this", "security review", "is this production ready", "check for vulnerabilities", "code review", "grade this code", "watch mode lint", "deep review", "ultrareview", "schedule quality sweep". Supports Drupal (PHPStan, PHPMD, Psalm, Semgrep, Trivy, Gitleaks via DDEV) and Next.js (ESLint, Jest, Semgrep, Trivy, Gitleaks). Use proactively before deployment or after significant code changes.
Use when an orchestrator must run a task's work-orders CONCURRENTLY behind the same gate floor as the sequential loop — the DB-free parallel sibling of work-order-loop. Each round it reconciles from disk (L1-light), selects a disjoint-file ready batch (wo-parallel-batch.sh), builds every batched WO at once in its OWN ephemeral git worktree branched off the integration HEAD (N parallel build atoms in ONE message), runs /review --headless + the work-order-critique rung per worktree, derives every verdict from disk, and merges each CLEAN WO back into the integration branch with a LOCAL git merge (wo-merge-back.sh — NOT a PR merge), pruning each ephemeral worktree after its verdict. The per-WO retry cap stays the SOLE responsibility of wo-run-state.sh dispatch; terminal-HALT precedence, disk-is-truth, and no-auto-merge are preserved verbatim. At the end it runs ONE integrated /review on the integration branch and opens ONE PR through wo-pr-open.sh (re-runs the merge gate, NEVER merges). MUST be invoked inline (ne
Use when an orchestrator must run the autonomous per-task run-loop behind the gate floor — the thin native glue (③ lifecycle_controls). Resumes from disk (L1-light), drives a ready-queue over the work-orders (a WO is ready when all blocked_by are done), dispatches ONE build atom per WO in clean context, runs /review --headless + the work-order-critique rung per WO, owns EVERY WO status transition via wo-compile.sh set-status, bounds the verify→fix loop with a crash-safe retry cap (wo-run-state.sh), and at the end opens a PR through the wo-pr-open.sh choke point that re-runs the merge gate and NEVER merges. Reads every decision from disk; treats builder transcripts as untrusted data; honors a budget/kill-switch call-site. MUST be invoked inline (never Task-dispatched). Prints a ready-to-paste /goal string; never runs /goal itself.
Use when an orchestrator must run the opt-in adversarial-critique rung on ONE built work-order — the absent-human review layered ABOVE the deterministic gates. Derives the work-order's risk tier (wo-risk-classify.sh), decides whether critique is required (forced-on for high-risk-unattended; else the per-task/per-project dial), spawns risk-scaled INDEPENDENT fresh-context wo-critic agents that re-derive the verdict from artifacts (git diff + gate envelopes), aggregates fail-closed (wo-critique-aggregate.sh) into a per-WO _critique.json, and writes a wo-NN.HALT marker when blocking. Fan-out is the unattended primitive; never edits /review's _review.json. A judgment layer, not a gate — gates always run first.
| name | screenshot-store-reader |
| description | Use when a framework command needs to inspect the project's visual-regression baseline store — the codePath-native tests/visual/ snapshot tree. Reads the store defensively via scripts/screenshot-store-read.sh and returns structured JSON. Never blocks on malformed input. |
| version | 1.2.0 |
| user-invocable | false |
| model | inherit |
| allowed-tools | Bash |
| disallowed-tools | Write, Edit |
Thin wrapper around ${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-read.sh.
The script inspects the codePath-native visual-regression store —
<codePath>/tests/visual/*.spec.ts-snapshots/ — and emits structured JSON per
references/screenshot-store-schema.md v1.0. This skill gives the reader a
Skill-tool-callable name and documents the invocation contract.
The store moved to codePath in v4.13.0 (Task C). Baselines are committed
Playwright snapshots; .meta.json provenance sidecars travel with each PNG.
Input: the absolute codePath (the project root). Optional
--legacy-path <memory_project_folder> adds a legacy_store_present boolean
when a v3.13.0 .screenshots/ directory still exists there.
Output: single JSON object to stdout per references/screenshot-store-schema.md. Exit code always 0 except for unrecoverable read failures.
Fields:
schema_version — JSON string, currently "1.0"project_path — the codePath passed instore_path — <codePath>/tests/visual; present whether or not it existsstore_exists — boolean (tests/visual/ present)legacy_store_present — boolean; emitted ONLY when --legacy-path is givencomponents[] — per-surface array of {name, viewports[]} where each
viewport has {viewport, has_current, has_previous, meta, previous_meta, warnings}warnings[] — store-level warningsname is the spec-file stem (the surface id). viewport is the viewport
name (desktop), parsed from the baseline filename's visual-chromium-<name>
project segment — not WIDTHxHEIGHT.
| Input state | Warning code | Level |
|---|---|---|
| codePath missing | error | store |
tests/visual/ does not exist | store_missing | store |
baseline PNG exists without .meta.json | component_missing_meta | viewport |
.meta.json invalid JSON or missing required v1.0 fields | meta_schema_mismatch | viewport |
.meta.json.sha256 differs from actual PNG hash | hash_mismatch | viewport |
.meta.json exists without a PNG sibling | orphan_meta | store |
| Unrecoverable read failure (permission, IO) | error | store |
"${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-read.sh" "/abs/path/to/codePath"
"${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-read.sh" "/abs/codePath" --legacy-path "/abs/memory/project"
Parse with jq. Examples:
OUT=$("${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-read.sh" "$CODE_PATH")
STORE_EXISTS=$(jq -r '.store_exists' <<<"$OUT")
SURFACE_COUNT=$(jq '.components | length' <<<"$OUT")
# Has a specific baseline?
HAS_HERO=$(jq -e '.components[] | select(.name == "home-hero") | .viewports[] | select(.viewport == "desktop" and .has_current)' <<<"$OUT" >/dev/null && echo true || echo false)
# Surfaces with a missing-meta or hash warning:
jq -r '.components[] | .name as $n | .viewports[] | select((.warnings|length)>0) | "\($n)/\(.viewport)"' <<<"$OUT"
.previous tierIn the v3.13.0 memory-project store, an intentional change rotated the prior
baseline to .previous.png. The codePath-native store has no .previous
files — git history IS the baseline history, and Playwright's
--update-snapshots overwrites in place. The reader keeps has_previous and
previous_meta in the output for contract-compatibility, but they are always
false / null. The prior baseline's hash is still carried in the current
sidecar's prior_hash field.
/ai-dev-assistant:validate-visual-regression — checks has_current /
warnings before running; reports missing baselines as a loud failure/ai-dev-assistant:validate-all — enumerates surfaces for the
visual-regression coverage check; reads legacy_store_present to surface
migration status/ai-dev-assistant:setup-visual-regression — checks which surfaces
already have baselines before the bootstrap promptFuture consumers needing screenshot-store data should call this skill rather than parsing the store directly.
--update-snapshots); provenance sidecars by
scripts/screenshot-store-write.sh write-baseline-codepath.warnings[] as a blocking error — warnings are
observations.store_exists, then
filter components[].${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-read.sh — the reader${CLAUDE_PLUGIN_ROOT}/scripts/screenshot-store-write.sh — the writer
(write-baseline-codepath for sidecars; legacy write-baseline /
write-parity-reference retained for migration + parity)references/screenshot-store-schema.md — canonical layout + .meta.json v1.0 schema, warning codesreferences/validation-gate-result.md — the result envelope visual gates emitalignment-reader / project-state-reader skills — same design pattern