This skill is responsible for checking task status, canceling the original task, and recovering after the scheduler exits. 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 only used to read its own examples/ and references/, and script execution paths always use $HARNESS_DIR/scripts/。
Inputs and Deliverables
Inputs are the user-confirmed task, assets, project or object, output directory, and modification scope; when an existing project is needed, verify the summary first. Return the actual CLI results, the saved native project, the required derived outputs, and verification records. Report installation success, command directory existence, and creative task completion separately.
First Use and Public Entry Point
Locate the real directory of the current SKILL.md. Currently supports macOS arm64 and Python 3.11+; the base entry point installs a pinned Node and orchestration package; workflow.py installs the required domain skill sources and native CLI according to the task graph, and does not require a global Node. When existing task authorization covers the necessary dependencies, run this skill's installer directly and do not create a separate approval process.
Set SKILL_DIR to the directory (absolute path) containing this SKILL.md that the host actually loads. User-level installations may be located at ~/.agents/skills/artcraft-cli-recover, project-level ones may be located at .agents/skills/artcraft-cli-recover, and plugins may be located in their skills/artcraft-cli-recover or the host cache directory; use the actual loaded path as the standard, do not guess based on the current working directory, and do not search and then arbitrarily choose among duplicate versions. The skill directory and the CLI's user data installation directory are two independent locations.
: "${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 locked artifact digest verification 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
Verify this scenario's inputs, native project, target object, version, and output boundaries. According to the scenario guide , select the current command, save an independent checkpoint, then execute; after completion, reopen the native project and check the actual outputs and non-target content.
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.
First query the original ledger and attempt; unknown/worker crashes retain the write lock, and do not resubmit just because the PID has disappeared.
Native composition and source project revisions use the artcraft-harness skill's scripts/workflow.py; read the workflow contract, and templates are in this skill's examples. Modify only authorized objects, preserve the native project and dependent assets, and for derived format loss read the exchange report。
Verification and Recovery
A non-zero command exit does not count as completion; you need to inspect the actual saved project, export, dimensions, and media decoding. Mark timeout results as unknown; check the original task/project first, and do not automatically replay edits. Perform recovery and packaging according to this skill's references/recovery.md and references/project-package.md respectively; review_ready only indicates technical readiness.
On-demand references and handoff
- Actual command evidence: fixed-version observation, used only as routing and parameter reference; real-time results take precedence, 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; for full task routing hand off 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 via adjacent file paths.
This skill does not provide a fictitious login interface; local headless does not require a cloud account. Full GUI, cross-editor fidelity, and creative quality are stated according to actual evidence.
When a finished piece 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.
Reports for failed domains that have been stopped can be queried via status; read this skill'srecovery contract; error diagnosis does not authorize replaying the original task.
When the result is unknown after saving, verify according to this skill's references/recovery.md the failure.json, the original staged project, and the stopping evidence; do not replay the same task, and a failed staging is not a successful delivery.
Full domain command handoff
When native operations beyond the template are needed, read this skill'sfull domain command component, use the included domain_commands.py to query 2646 commands, actual MCP parameters, and hand off the selected domain. Each skill includes creation/rework examples for the four domains; unknown is not replayed, and component receipts do not replace DAG native delivery and acceptance.
For native gradients, multiple fills, and color-change rework of the source project: use the current skill's Vector appearance guide。
For native parenting, transparency expressions, and source project rework: use the current skill's Effect expression guide。
For Photo native adjustment layers, selection masks, and trusted-source rework, see local adjustment guide。
When you need to independently launch domain GUI commands, see own desktop handoff。
Mixed-task reference business scenario manual; first confirm dependencies and input versions, then execute sub-projects, local rework, and delivery verification.
When installation fails, read first-use diagnostics, and use the receipt to locate the current skill's own setup entry point; handle installation failures and native invocation failures separately.
For real voice recognition and mixed subtitle tasks, please read this skill's Mixed ASR guide / Mixed ASR guide, and execute according to the fixed domain dispatch and persistent model directory; planning, rework, and acceptance respectively preserve dependencies, the native project, and execution evidence.
For task identity and rejection details, read according to task receipt description ; node summaries do not replace actual execution receipts.
Before reworking mixed posters, covers, and source projects, read Photo full delivery, and distinguish host-independent plugins from Art's internal fixed dependencies.
For cross-artifact observation with fixed brand and subject references, see this skill's Consistency Review Contract; source candidates and acceptance of published fixed versions are reported separately.
Runtime upgrades and legacy ledgers
When encountering runtime_upgrade_busy , retain the old runtime, original project, and 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; read-only status 's legacy budget markers indicate historically untracked. See this skill'sUpgrade Guide。
For validation and mode boundaries of native command execution, see Command Contract Boundaries。
For classification, parameter differences, and rejection boundaries of mode catalog candidates, seeMode Catalog Usage; Vector desktop/bridge duplicate commands have not yet completed execution qualification and cannot fall back according to the headless catalog.