jianying-inspect

JianYing Inspect

Read material and draft facts without changing files. All subsequent plans should reference the results of this probe.

When to use

The user explicitly requests the CapCut capability corresponding to this skill's title and accepts processing through the unified Rust jianying CLI.
The user needs auditable planning, execution, or verification evidence, rather than just a conceptual answer.
When the requirement is not yet clear, first hand it to jianying-use routing; this skill should not be used to handle other editors, general video knowledge Q&A, or speculative execution that lacks the necessary materials.

Capability boundaries

✅ Can do: Generate deterministic plans based on real paths and probe results; when capability is supported , execute operations in this domain; output the evidence level actually achieved.
⚠️ Requires conditions: Writes must use isolated copies; costs, external services, and native application actions must have precise approval; playback or export conclusions must have corresponding runtime evidence.
❌ Out of scope: Do not automatically install or upgrade the CLI, do not generate Python draft scripts, do not invoke external headless checkout, do not overwrite source drafts, and do not fabricate resource IDs, media facts, or success states.

Step 1 — Establish a factual baseline

Record the user's goal, absolute paths, host platform, target deliverables, and allowed side effects; when information is insufficient, first provide a read-only diagnostic plan and list the missing facts item by item.

Step 2 — Handshake capabilities

Run version, doctor, and capabilities checks. Meeting the version requirement does not mean the capability is available;partial、external_dependency or a missing state must enter the degraded path.

Step 3 — Validate inputs

Probe media, drafts, configuration, or task status; reject nonexistent paths, out-of-range times, unknown schemas, mismatched hashes, and approvals that cannot be bound to a target.

Step 4 — Form a deterministic plan

Write the operations, parameters, output paths, risk levels, confirmation points, and expected evidence into the plan. Order multiple tasks as "read-only facts → reversible writes → external/native actions".

Step 5 — Execute or stop before the gate

Execute only steps that are supported and authorized. When output is ambiguous, times out, or partially succeeds, retain the task ID, audit log, and artifacts, and do not automatically retry.

Step 6 — Verify and deliver

Run structural validation, then append cold reopen, playback, or native export evidence according to the target; report the actual level, failed fields, recoverable actions, and unverified items.

Rules

The material duration, dimensions, streams, hashes, and draft version in the plan must come from tool output.
Approval must be bound to the command, parameters, target, validity period, and budget; if any field changes, reconfirm.
User data is processed only within local target paths and the declared external Provider boundary; unrelated credentials must not be collected, uploaded, or recorded.
When current evidence is insufficient, use UNVERIFIED、BLOCKED or AMBIGUOUS, and do not fill in results by inference.

Gotchas

Treating version as capability: Always check the specific capability; do not execute directly just because the CLI version is new enough.
Treating structural validation as final acceptance: project verify It only proves the structural layer; playback and native export require independent evidence.
Directly modifying the source draft: First create an isolated copy and record the input hash; any in-place overwrite request must stop and be changed to a new output.
Automatic retry for ambiguous: First query the task, audit, and external artifacts; only after confirming no side effects occurred may the user approve a retry.
Filling in resources or times from memory: Resource IDs come from the catalog, and times come from probe/ASR/project data; if they cannot be obtained, block explicitly.
Vaguely requesting more information: First provide an executable read-only plan, then explicitly list the gaps such as paths, delivery level, or authorization.

Verification checklist

CLI identity, version, and capability have been recorded.
All input paths, media facts, and hashes are reviewable.
Write targets are isolated from source drafts, and confirmation points are precisely bound.
Failure and ambiguous paths retain task ID, logs, and recovery suggestions.
The final wording is consistent with the actual evidence level.

Run contract

Trigger conditions: the user wants to view media information, draft structure, version, differences, reference integrity, or verification level.
Required capability:media.probe、project.inspect、project.verify。
Minimum CLI version:1.6.0; record the actual version and capability status in the result.
Default risk:read_only。
Input facts: absolute path of the media or draft, target inspection question, expected evidence level, and host platform.
Confirmation points: read-only inspection requires no confirmation; cold reopen, playback, or native export are independent external actions.
Success evidence:structural; unless actually executed, it cannot be elevated to cold_reopen/playback/native_export.
Prohibited actions: do not generate Python draft scripts, do not call external headless checkout, do not modify the draft, treat file existence as content correctness, or use planned duration to impersonate measured duration.

Workflow

jianying media probe <media> --json Obtain duration, dimensions, streams, and type.
jianying project info|version|inspect <draft> --json Obtain a stable summary.
jianying project verify <draft> --json Check references, timeline, and bundle integrity.
When comparison is needed, use project diff, and clarify which differences are expected edits.
Report facts, failed fields, and the current highest evidence level.

See the checklist and evidence meanings in references/workflow.md. For read-only Jobs, see examples/minimal-job.json。

Progressive materials

On first execution, load normal path to obtain the end-to-end order.
When encountering failure or unknown status, load failure recovery and error recovery table。
When the user requests privilege escalation, overwrite, or automatic retry, load boundary refusal。
Before delivery, complete item by item verification checklist, and do not claim completion based only on a plan or file existence.