This skill handles filters and local processing along with its native delivery and local rework. Hand off to skills in the same package by name; it can be installed and used standalone and does not read sibling directories. Call the fixed maintenance version photocraft-cli and preserve the native editing project.
Inputs and delivery
The inputs are the user-confirmed task, assets, project or object, output directory, and scope of changes; when an existing project is required, 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 creation task completion separately.
First use and public entry points
The execution implementation converges on 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 directory actually loaded by 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 and Python 3.11+; the fixed CLI is installed to the user data directory. When 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 in ~/.agents/skills/photocraft-cli-filters, project-level ones may be located in .agents/skills/photocraft-cli-filters, and plugins may be located in their skills/photocraft-cli-filters or host cache directory; base it on the actual loaded path, do not guess from 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
After -- in the CLI argv, 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
Follow filter and local processing scenarios to verify the real objects, 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 enabled/params, construct the argv; consecutive steps that require creating objects must be executed in the same session, and returned IDs must not be guessed.
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.
For native composition and source project revisions, use the built-in photocraft-harness skill's scripts/workflow.py; read workflow contract, the template is within this skill's examples. Modify only authorized objects, preserve the native project and dependent assets, and for derived format losses read exchange report。
Verification and recovery
A non-zero command exit does not count as completion; it is necessary to inspect the actually saved project, exports, dimensions, and media decoding. Timeout results are marked 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 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.
- Hand off to photocraft-cli-setupwhen installation/diagnosis is needed, hand off full 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 via 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, different from cloud login. Full GUI, cross-editor fidelity, and creative quality are stated according to actual evidence.
Full native command usage
The current skill includes in itself complete directory parameter documentation and same-session entry points, and is not limited by the creative template whitelist. Read Complete Usage Guide, and consult on demand command reference; each instruction has skill routing, 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; semantic errors or timeouts must not be passed off as success. Directory coverage and direct native use do not mean all commands, GUI, delivery, or Art orchestration have been accepted.
For the full workflow command gateway, see Usage Instructions. The version and artifact digest of the pinned CLI are based on 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; release does not replace 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 pinned installation evidence kept separate.
For GUI tasks, you may first use this skill's built-in pinned desktop installation; installation, startup, and actual GUI editing are verified separately.
Full attribution commands are listed by command family in the categorized usage list, and each item can be viewed via this skill's commands.py describe for parameters; the general CLI list also retains all commands not assigned to specialized skills.
For business tasks, start from Scenario Operation Manual and execute according to input checks, template adaptation, native delivery, local rework, and result verification.
When installation fails, read First-Use Diagnosisand use the receipt to locate the current skill's own setup entry point; handle installation failure and native invocation failure 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 case of contention or an unknown state, do not delete the registration, automatically replay, or switch targets to bypass verification.
Before delivery, moving a package, or reworking a source project, verify all files and exchange identities according to the delivery completeness checklist; read-only checks do not require installing a runtime.
Scenario contract and routing
According to Scenario Contract Verify input, target and protection scope, recovery, and acceptance. For a complete task, select the shortest skill chain by name; when a known result is unclear, verify the original task first and do not replay. An explicit intent can 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 required features; observed loss/degradation and unknown required items will block success. When the user explicitly accepts, record it under the same source version and actual observation summary, and do not accept automatically; see this skill'sPSD exchange and acceptance gate。
When flat export requires explicit color/ICC/transparency requirements or retention 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 refusal contract。
Continuous tasks and instance reuse
When continuously checking, editing, saving, reopening, and reworking the same user task, use this skill's task-level session and the built-in photocraft-harness skill's scripts/task_session.py, keeping the same foreground process and input handle. After failure/unknown, verify the original receipt and project first, and do not start a substitute instance for replay.