This skill handles first-time installation, digest verification, version checking, and missing-runtime troubleshooting. It hands off to skills in the same package by name, can be used when installed alone, and does not read sibling directories. Use this project's local orchestration CLI; upstream ArtCraft is a Tauri application, and this skill does not install or impersonate an official CLI of the same name.
Execution implementation is consolidated in the built-in artcraft-harness skill (installed bundled with the plugin; for standalone installation use npx skills add full-aigc-skills/artcraft-skills --skill artcraft-harness). Set HARNESS_DIR to the directory where that skill is actually loaded (absolute path); this skill's SKILL_DIR is used only to read its own examples/ and references/, and script execution paths always use $HARNESS_DIR/scripts/。
Inputs and Deliverables
Inputs are the user-confirmed task, materials, project or object, output directory, and modification scope; when an existing project is needed, verify the digest first. Return the actual CLI results, the saved native project, the required derived outputs, and the verification record. Report installation success, command directory existence, and creation task completion separately.
First Use and Public Entry Point
Locate the real directory of the current SKILL.md. Currently supports macOS arm64 and Python 3.11+; the base entry point installs a pinned Node and orchestration package; workflow.py installs the required domain skill sources and native CLI according to the task graph, without requiring a global Node. When an existing task authorization covers the necessary dependencies, execute this skill's installer directly and do not create a separate approval process.
Set SKILL_DIR to the directory (absolute path) containing this SKILL.md that is actually loaded by the host. User-level installations may be located at ~/.agents/skills/artcraft-cli-setup, project-level ones may be located at .agents/skills/artcraft-cli-setup, and plugins may be located in their skills/artcraft-cli-setup or the host cache directory; use the actual loaded path as the standard, do not guess based on the current working directory, and do not search and then arbitrarily choose among duplicate versions. The skill directory and the CLI's user data installation directory are two independent locations.
: "${SKILL_DIR:?请先设置为本 SKILL.md 的实际所在目录}"
python3 -I -B "$HARNESS_DIR/scripts/bootstrap.py" --runtime-only
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- --version
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- --help
CLI argv comes after -- , and the native subcommand must come first. Installation parameters go before the separator;--runtime-home can isolate the cache. Stop when locking the artifact digest fails, the installation is corrupted, or the platform is unsupported; do not modify PATH and do not perform floating upgrades. The native help entry point is --help; the launcher's own --help only describes startup parameters.
Scenario Operations
First read the system/architecture, Python version, and the user's existing authorization; run this skill's bootstrap.py with --runtime-only as described above; to manually preinstall a selected domain, you may explicitly use --plugin; omitting the selection parameter is the full-installation compatibility entry point, not a necessary step for every project. Verify the executable path, digest, and version in the JSON receipt; do not rely on the shell PATH. Repeated calls reuse the pinned installation; on failure, stop and record the specific error.
This project's --help defines run/status/cancel/package/verify-package; semantic planning goes through workflow.py, and upstream Tauri's account/vendor methods must not be treated as orchestration CLI commands.
Do not modify PATH and do not use sudo; keep corrupted versions and report an error, do not automatically upgrade.
Native composition and source project revisions use the artcraft-harness skill's scripts/workflow.py; read the workflow contract, and the templates are in this skill's examples. Modify only authorized objects; keep native projects and dependency materials; for derived format loss, read the exchange report。
Verification and Recovery
A non-zero command exit does not count as completion; it is necessary to inspect the actual saved project, export, dimensions, and media decoding. Timeout results are marked unknown; first inspect the original task/project, and the edit cannot be automatically replayed. Recovery and packaging are performed according to this skill's references/recovery.md and references/project-package.md respectively; review_ready only indicates technical readiness.
On-demand reference and handoff
- Actual command evidence: Fixed-version observations, used only as routing and parameter reference; real-time results take precedence, and disabled items are not executed.
- Workflow contract: Combined operations, native save, dependency collection, and revision.
- When installation/diagnostics are needed, hand off to artcraft-cli-setup, and hand off complete task routing to artcraft-use; when a skill is missing, use
npx skills add full-aigc-skills/artcraft-skills --skill <skill-name>. Do not load other skills through adjacent file paths.
This skill does not provide a fictional login interface; local headless does not require a cloud account. Complete GUI, cross-editor fidelity, and creative quality are stated according to actual evidence.
When the finished product needs to be verified through the existing Video Factory, read this skill's public verification handoff. This adaptation preserves NOT_RUN and does not replace creative review or the native project.
When the result after saving is unknown, follow this skill's references/recovery.md to verify failure.json, the original staged project, and stopping evidence; the same task is not replayed, and a failed staging is not a successful delivery.
Complete domain command handoff
When native operations beyond the template are needed, read this skill'scomplete domain command component, use the included domain_commands.py to query 2646 commands, the actual MCP parameters, and hand off the selected domain. Each skill includes examples for creating/reworking across the four domains; unknown is not replayed, and component receipts do not replace native DAG delivery and acceptance.
Native gradient, multiple fill, and source project recoloring rework: use this skill's Vector Appearance Guide。
Native parent, transparency expressions, and source project rework: use this skill's Effect Expression Guide。
For Photo native adjustment layers, selection masks, and trusted source rework, see Local Adjustment Guide。
When domain GUI commands need to be launched independently, see own desktop handoff。
Mixed-task reference Business Scenario Manual, first confirm dependencies and input versions, then execute subprojects, local rework, and delivery verification.
When installation fails, read First-Use Diagnostics, and use the receipt to locate the setup entry point of the current skill itself; handle installation failures and native invocation failures separately.
For real dubbing recognition and mixed subtitle tasks, please read this skill's Mixed ASR Guide / Mixed ASR guide, and execute according to fixed domain dispatch and the persistent model directory; for planning, rework, and acceptance, retain dependencies, native project, and execution evidence respectively.
For task identity and rejection details, follow Task Receipt Description for reading; node summaries do not replace actual execution receipts.
Before reworking mixed posters, covers, and source projects, read Photo Complete Delivery, and distinguish host-independent plugins from Art-internal fixed dependencies.
For cross-artifact observations with fixed brand and subject references, see this skill's Consistency Review Contract; acceptance of source candidates and released fixed versions is reported separately.
Runtime upgrades and legacy ledgers
When encountering runtime_upgrade_busy , keep the old runtime, the original project, and the ledger; do not delete leases or forcibly modify state. First complete or reliably stop tasks with the old version, then migrate according to the new version; old budget markers that are read-only status indicate historically untracked. For details, see this skill'sUpgrade Guide。
For the checksum and mode boundaries of native command execution, see Command Contract Boundaries。
For the classification, parameter differences, and rejection boundaries of mode directory candidates, seeMode Directory Usage; repeated commands in Vector desktop/bridge have not yet completed execution eligibility and cannot fall back according to the headless directory.