This skill handles first-time installation, digest verification, version checks, and missing-runtime troubleshooting. It hands off to skills in the same package by name, can be used when installed on its own, and does not read sibling directories. It invokes the fixed release of filmcraft-cli and preserves native editing projects.
Trusted Directory Permissions
Legacy cli.py Project reading and editing via native forwarding also require a separate root parameter before -- ; only exact version/help/no-project-directory queries are compatible with legacy invocation. Model downloads must separately use --model-maintenance, see this skill's Execution Permissions。
Public workflow.py and commands.py run must explicitly provide --read-root READ_DIRECTORY --write-root WRITE_DIRECTORY(repeatable); the root must be an existing canonical real directory, authorized by the user/host, and must not be derived from plans or asset metadata. Plans, assets, and source deliverables must be located under the read root, and deliverables and their parent directories must be located under the write root.--runtime-home is the installation maintenance directory and must be located under a separate, explicitly authorized write root; editing native processes is always prohibited from modifying this cache, the skill, registration inputs, and source projects. Current root-isolated execution supports macOS headless; the desktop entry must simultaneously isolate the signed application and MCP client owned by this session, exposing only the allocated loopback control port. External bridges whose isolation cannot be confirmed are explicitly rejected. The low-level Python test API is not a public authorization entry point. For detailed boundaries see Execution Permissions。
Inputs and Deliverables
Inputs are the user-confirmed task, assets, project or object, output directory, and scope of modification; when an existing project is needed, verify the digest 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 Points
Locate the real directory of the current SKILL.md. Currently supports macOS arm64, Python 3.11+; the fixed CLI is installed to the user data directory. When existing task authorization covers the necessary dependencies, directly execute this skill's installer without creating a separate approval process.
Set SKILL_DIR to the directory (absolute path) of this SKILL.md actually loaded by the host. User-level installations may be located at ~/.agents/skills/filmcraft-cli-setup, project-level ones may be located at .agents/skills/filmcraft-cli-setup, and plugins may be located in their skills/filmcraft-cli-setup or host cache directory; use the actual load 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.
: "${SKILL_DIR:?请先设置为本 SKILL.md 的实际所在目录}"
python3 -I -B "$SKILL_DIR/scripts/bootstrap.py"
python3 -I -B "$SKILL_DIR/scripts/cli.py" -- --version
python3 -I -B "$SKILL_DIR/scripts/cli.py" -- commands --json
In CLI argv, after -- , the native subcommand must come first. Installation parameters go before the separator;--runtime-home can isolate the cache. Stop when the pinned 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 explains startup parameters.
Scenario Operations
First read the system/architecture, Python version, and the user's existing authorization; run this skill's bootstrap.py. Verify the executable path, digest, and version in the JSON receipt; do not rely on shell PATH. Repeated calls reuse the fixed installation; on failure, stop and record the specific error.
describe <id> verify the parameters, then use exec <id> <JSON> or run <JSONL>; write commands must be saved in the same batch or used together with --save-as。
Do not modify PATH and do not use sudo; keep corrupted versions and report an error, do not auto-upgrade.
Native composition and source project revisions use the scripts/workflow.pyincluded with this skill; read workflow contract, with templates in this skill's examples. Modify only authorized objects; native projects and dependency assets are retained, and derived-format loss is read from 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. Existing native workflows support Save As revisions; refuse to overwrite when the corresponding project summary does not match.
On-demand reference and handoff
- Actual command evidence: fixed-version observations, used only as routing and parameter reference; live results take precedence, and disabled items are not executed.
- workflow contract: composition operations, native save, dependency collection, and revisions.
- Hand off to filmcraft-cli-setupwhen installation/diagnostics require it, and hand off full task routing to filmcraft-use; when a skill is missing, use
npx skills add full-aigc-skills/filmcraft-skills --skill <skill-name>. Do not load other skills through 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.
Full native command usage
The current skill includes parameter descriptions and same-session entry points for the complete catalog, and is not limited by the creative template allowlist. Read the full usage guide, and consult the command referenceas needed; each instruction has a skill route, prerequisite observations, and acceptance status.
: "${READ_ROOT:?Set READ_ROOT to an existing independently authorized directory}"
: "${RUNTIME_HOME:?Set RUNTIME_HOME to an existing independently authorized directory}"
: "${SKILL_DIR:?Set SKILL_DIR to an existing independently authorized directory}"
: "${WRITE_ROOT:?Set WRITE_ROOT to an existing independently authorized directory}"
python3 -I -B "$SKILL_DIR/scripts/commands.py" list --filter QUERY
python3 -I -B "$SKILL_DIR/scripts/commands.py" describe COMMAND_ID
python3 -I -B "$SKILL_DIR/scripts/commands.py" run "$SKILL_DIR/examples/commands-advanced.json" --output /absolute/new-command-result --runtime-home "$RUNTIME_HOME" --read-root "$SKILL_DIR" --read-root "$READ_ROOT" --write-root "$WRITE_ROOT" --write-root "$RUNTIME_HOME"
Before executing a new entry point, check the actual registry and current executable status, retain return-value references and step-by-step receipts; do not pass off semantic errors or timeouts as success. Catalog coverage and direct native usage do not mean all instructions, GUI, delivery, or Art orchestration have been accepted.
For the complete workflow command gateway, see usage instructions. For the fixed CLI, the version and artifact digest are based on the scripts/runtime.lock.json included with this skill; the skill package version is based on the corresponding release tag. Independent installation re-verification and full command-by-command acceptance are recorded separately; release does not replace acceptance.
For GUI tasks, you can first use the fixed desktop installationincluded with this skill; installation, startup, and actual GUI editing are verified separately.
For this skill's tasks, first read the specialized task template, and execute according to the corresponding inputs, first task, failure boundaries, local revisions, and verification. When combining across capabilities, then read the complete business scenario。
If 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 same-target execution contention and interruption registration, see this skill's execution registry; the skill source dev.29 includes the implementation, and plugin fixed-installation acceptance is recorded separately.
For continuous operations, prefer the task-level sessionincluded with this skill: start once, check, save, and rework plan by plan, sharing the same FilmCraft instance; exit only when the task ends. A single run still retains its original compatible behavior.