This skill is responsible for creating selections, inverting, feathering, and local selection. It hands off by name with skills in the same package, can be installed and used on its own, and does not read sibling directories. It calls the fixed maintenance version photocraft-cli and preserves the native editing project.
Inputs and delivery
The 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
Execution implementation converges in the built-in photocraft-harness skill (installed bundled with the plugin; for standalone installation use npx skills add full-aigc-skills/photocraft-skills --skill photocraft-harness). Set HARNESS_DIR to the actual loading directory of that skill (absolute path); this skill's SKILL_DIR is only used to read its own examples/ and references/。
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, directly execute this skill's installer and do not create a separate approval process.
Set SKILL_DIR to the directory (absolute path) where this SKILL.md actually loaded by the host is located. User-level installations may be at ~/.agents/skills/photocraft-cli-selection, project-level may be at .agents/skills/photocraft-cli-selection, plugins may be in their skills/photocraft-cli-selection or host cache directory; use the actual loading path as the standard, do not guess based on the current working directory, and do not search and then arbitrarily select a duplicate version. 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"
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- --version
python3 -I -B "$HARNESS_DIR/scripts/cli.py" -- commands --json
CLI argv comes after -- , and the native subcommand must be placed 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 explains startup parameters.
Scenario operations
First read this skill's persistent selection and channel scenario guide, and select commands by category; creation/reopen/rework plans are in this skill's examples.
Verify this scenario's inputs, native project, target object, version, and output boundaries. Select the current command according to the scenario guide , save an independent checkpoint, and then execute; after completion, reopen the native project and inspect the actual output and non-target content.
Read params from commands --json --filter <关键词> ;run <工程> --cmd <id> --params <JSON> ... --out <新工程.pcraft>, each --params belongs to the preceding --cmd; serve/MCP can maintain a single session.
The selection source and boundaries must be verified; directory entries such as subject/sky do not automatically equal accepted AI segmentation.
Native composition and source project revisions use the built-in photocraft-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; the actual saved project, export, dimensions, and media decoding need to be checked. Timeout results are marked unknown; first check the original task/project, and do not automatically replay edits. The existing native workflow supports Save As revision; when the corresponding project summary does not match, refuse to overwrite.
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 saving, dependency collection, and revision.
- When installation/diagnostics are needed, hand off to photocraft-cli-setup, and hand off complete task routing to photocraft-use; when a skill is missing, use
npx skills add full-aigc-skills/photocraft-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. The PhotoCraft bridge's control-token is local application access control, which is different from cloud login. Full GUI, cross-editor fidelity, and creative quality are stated according to actual evidence.
Complete native command usage
The current skill includes the parameter descriptions and same-session entry points for the complete catalog, and is not restricted by the creative template allowlist. Read complete usage guide, and query as needed command reference; each instruction has a skill route, prerequisite observations, 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, and retain return value references and step-by-step receipts; semantic errors or timeouts must not be passed off as success. Catalog coverage and direct native use do not mean that all instructions, GUI, delivery, or Art orchestration have been accepted.
For the complete workflow command gateway, see usage instructions. For the fixed CLI's version and artifact summary, refer to the built-in photocraft-harness skill's scripts/runtime.lock.json ; the skill package version is based on the corresponding release tag. Independent installation re-verification and full command-by-command acceptance are recorded separately, and release is not used as a substitute for acceptance.
For editable local adjustments and source rework, see mask adjustment usage instructions; paired plans are in this skill's examples, with source candidates and fixed installation evidence kept separate.
For GUI tasks, you can first use this skill's built-in fixed desktop installation; installation, startup, and actual GUI editing are verified separately.
Complete attribution commands are listed by command family in categorized usage list, and each item can be viewed through this skill's commands.py describe to inspect parameters; the general CLI list also retains all commands not assigned to specialized skills.
Business tasks start from scenario operation manual , and are executed according to input checks, template adaptation, native delivery, local rework, and result verification.
When installation fails, read first-use diagnostics, and use the receipt to locate the current skill's own setup entry point; installation failures and native invocation failures are handled separately.
For product local filter, background blur, and output sharpening tasks, read filter scenarios, distinguish editable filters from baked pixels, and verify selections, layers, and non-target content.
Same-target execution protection
Before invoking a public workflow, read this skill's execution registration and interruption handling. In cases of contention or unknown status, do not delete the registration, automatically replay, or switch targets to bypass verification.
Before delivery, moving packages, or source project rework, follow Delivery Integrity Verify all files and the exchange identity in the checklist; read-only checks require no runtime installation.
Scenario Contracts and Routing
Per scenario contract , verify inputs, objectives and protection scope, recovery, and acceptance. For a complete task, select the shortest skill chain by name; when a known result is unknown, first verify the original task and do not replay. For explicit intent, you may use the built-in photocraft-harness skill's scripts/route.py INTENT query entry point; this is a contract query and does not prove that host model dispatch has passed.
PSD delivery requires explicit necessary characteristics; observed loss/degradation and unknown necessary items will block success. When the user explicitly accepts, record it under the same source version and actual observation summary; do not accept automatically; see this skill'sPSD Exchange and Acceptance Gate。
When a flat export requires explicit color/ICC/transparency requirements or preservation of externally generated asset provenance, read this skill's Flat Export and Provenance Contract。
For runtime/backend identity and capability drift issues, read this skill's Capability Snapshot and Rejection Contract。
Continuous Tasks and Instance Reuse
When the same user task is continuously checked, edited, saved, reopened, and reworked, use this skill's Task-Level Session and the built-in photocraft-harness skill's scripts/task_session.py, maintaining the same foreground process and input handle. After a failure/unknown, first verify the original receipt and project; do not start a substitute instance for replay.