SuperAPI AI Directory

vectorcraft-cli-selection

Design & creation

View repository

Updated 10-15 21:47

About this skill

Vectorcraft object selection

This skill handles object selection along with its native delivery and local rework. Hand off with same-package skills by name; it can be used installed on its own and does not read sibling directories. Call the fixed official vectorcraft-cli and preserve the native editing project.

Inputs and delivery

The inputs are the user-confirmed task, materials, project or object, output directory, and modification scope; when an existing project is needed, verify the summary first. Return the actual CLI result, the saved native project, the required derived outputs, and the verification record. Report installation success, command directory existence, and creative task completion separately.

First use and common entry points

Locate the real directory of the current SKILL.md. Currently supports macOS arm64, Python 3.11+; the fixed CLI installs into the user data directory. When existing task authorization covers the necessary dependencies, execute this skill's installer directly; do not create a separate approval process.

Set SKILL_DIR to the directory (absolute path) of the actually loaded SKILL.md in the host. User-level installations may be located in ~/.agents/skills/vectorcraft-cli-selection, project-level ones may be located in .agents/skills/vectorcraft-cli-selection, and plugins may be located in its skills/vectorcraft-cli-selection or the host cache directory; go by the actual loaded path, do not guess based on the current working directory, and do not search and then arbitrarily pick a duplicate version. The skill directory and the CLI's user data installation directory are two independent locations.

Implementation is consolidated in the built-in vectorcraft-harness skill (bundled and installed with the plugin; for standalone installation use npx skills add full-aigc-skills/vectorcraft-skills --skill vectorcraft-harness). Set HARNESS_DIR to that skill's actual loaded directory (absolute path); this skill's SKILL_DIR is only used to read its own examples/ and references/。

: "${SKILL_DIR:?请先设置为本 SKILL.md 的实际所在目录}"
python3 -I -B "$HARNESS_DIR/scripts/bootstrap.py"
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- --version
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- commands

For CLI argv, after -- , the native subcommand must come first. Put installation parameters before the separator;--runtime-home can isolate the cache. Stop when artifact digest locking 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

By object selection scenario , verify the real object, parameters, and task boundaries.

First query the current version and command directory; record read-only and editing calls separately. After reading the current project state and the command's enabled/params, construct argv; consecutive steps that require creating objects must be executed in the same session, and the returned ID must not be guessed.

commands returns the JSON parameter catalog;run --in <工程> --cmd <id> --params <JSON> ... --export <新工程.vectorcraft>, resolve object IDs in the same batch; convert outputs by extension.

Native composition and source project revision use the vectorcraft-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 materials; 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 actually saved project, exports, 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; real-time results take precedence, and disabled items are not executed.
  • Workflow contract: composite operations, native save, dependency collection, and revision.
  • Hand installation/diagnostics to vectorcraft-cli-setupwhen needed, hand full task routing to vectorcraft-use; when skills are missing use npx skills add full-aigc-skills/vectorcraft-skills --skill <skill-name>. Do not load other skills via adjacent file paths.

This skill does not provide a fictional login interface; local headless does not require a cloud account. Full GUI, cross-editor fidelity, and creative quality are stated based on actual evidence.

The current runtime is the maintained build v0.2.0 based on the official 0.2.0-craft.2, published by full-aigc-skills/vectorcraft-skills ; installation records clearly distinguish the maintained build source. The SVG workflow isolates artboards according to native drawing boundaries, conservatively preserving groups, clipping, and unknown-scope dependencies.

The PDF workflow is bound to the project creation date; when the creation date is missing, the first export date record is retained.pdf-export-date.json is written into the delivery manifest, and that record is verified during rework; native project dates and revision history remain traceable.

Complete native commands use

The current skill includes its own complete directory of parameter descriptions and same-session entry points, and is not restricted by the creative template allowlist. Read complete usage guide, and consult command referenceas needed; each instruction has a skill route, prior observation, and acceptance status.

python3 -I -B "$HARNESS_DIR/scripts/commands.py" list --filter QUERY
python3 -I -B "$HARNESS_DIR/scripts/commands.py" describe COMMAND_ID
python3 -I -B "$HARNESS_DIR/scripts/commands.py" run "$SKILL_DIR/examples/commands-advanced.json" --output /absolute/new-command-result

Before executing a new entry point, check the real registry and current executable status, retain return value references and step-by-step receipts; do not pass off semantic errors or timeouts as success. Directory coverage and direct native use do not equal acceptance of all instructions, GUI, delivery, or Art orchestration.

For the complete workflow command gateway see usage instructions. The version and artifact digest of the pinned CLI are based on the scripts/runtime.lock.json included with the vectorcraft-harness skill; the skill package version is based on the corresponding release tag. Independent installation re-verification and full per-command acceptance are recorded separately, and release is not used as a substitute for acceptance.

For native gradients, global palette linkage, multiple fills, and explicit active row scenarios, use this skill'sexecutable creation/rework instructions。

For GUI tasks, you may first use the pinned desktop installationincluded with this skill; installation, launch, and actual GUI editing are verified separately.

Complete attribution commands are listed by command family in categorized usage list; each item can be viewed through this skill's commands.py describe to check parameters; the general CLI list also retains all commands not assigned to specialized skills.

Business tasks start from scenario operation manual , and are executed by input checks, template adaptation, native delivery, local rework, and result verification.

If installation fails, read first-use diagnostics, and use the receipts to locate the current skill's own setup entry point; handle installation failures and native invocation failures separately.

For related creative tasks, read object selection and transformation scenarios, and check native parameters, object context, local rework, and delivery boundaries.

For object layout, state, and path editing, first read this skill's own object operation guide, and check authorized objects, boundary types, and original project retention requirements.

Same-target execution protection

Before invoking a public workflow, read this skill's execution registration and interruption handling. For competing or unknown states, do not delete registrations, automatically replay, or switch targets to bypass verification.

Operation contracts and routing policies

Read this skill'sinput, precondition state, side effects, results, recovery, and acceptance contracts on demand. Examples referenced by the contract are divided into creation and rework, and are bound to the current source project and real receipts before use; the standard workflow and the full command plan format are handled separately. Hosts that support invoking the policy are routed by default via vectorcraft-use , and specialized skills may explicitly invoke it; other hosts dispatch according to their actual capabilities.