dreamina-opencli-text2video

dreamina-opencli-text2video — Jimeng text-to-video (opencli / standard member)

Forwithout dreamina CLI standard members. Only opencli jimeng subcommands are allowed,forbidden dreamina text2video、query_result and dreamina-cli-text2video。

video prompt provided by dreamina-prompt-text2video ; execution uses opencli jimeng generate-video（type=video workspace DOM automation).

opencli commands

Subcommand	Purpose
generate-video <prompt>	Text-to-video (default --wait=120）
generate-image2video <prompt>	Image-to-video (required --image single reference image)
generate-audio / generate-digital-human / generate-action-copy	Voiceover / digital human / motion imitation
history	--type=video check works
new --type=video / workspaces	Session management
user_credit	Credit check

Without dreamina's --duration、--model_version=seedance* and other parameters.

Core workflow

1. PROMPT  → dreamina-prompt-text2video
2. SESSION → 可选 opencli jimeng new --type=video
3. GEN     → opencli jimeng generate-video "<prompt>" [--workspace ...] [--wait 180]
4. VERIFY  → opencli jimeng history --limit N --type=video

Allowed opencli examples

opencli jimeng generate-video "镜头缓慢推进，橘猫跳下沙发" --wait=180
opencli jimeng new --type=video
opencli jimeng history --limit 10 --type=video --format json
opencli jimeng user_credit

Prohibitions

• Must not use the dreamina CLI to submit or poll video tasks.
• Must not use generate（type=image) to impersonate video generation.

Division of labor with dreamina-canvas-cli-text2video

Users who have installed the dreamina-canvas CLI use dreamina-canvas-cli-text2video(the old dreamina text2video stopped being maintained in 2026-11, do not route to it again); readers of this skillmust notswitch to dreamina.

Agent specifications

• Video takes a long time: multiple history is normal, shell infinite loops are prohibited; the agent calls in rounds history。
• Duration matches action complexity (see the prompt skill); the seconds are selected by the user on the web side.
• Insufficient credits and compliance blocks are prompted on the web page; opencli cannot user_credit query.

Gotchas

1. history The columns are mainly image-to-video history interface fields; video entries are subject to what the web page actually displays; when there are no records, the user's browser state prevails.
2. Standard members are subject to the web page plan and queueing, unrelated to the dreamina VIP queue.
3. First/last frames / multiple storyboards must be operated on the web page; single-image image-to-video uses generate-image2video --image。

When to use (when to use)

When the user needs to execute generation or write operations after clear input, budget, and delivery constraints load this skill. First extract the goal, input, constraints, delivery format, and acceptance criteria from the request; the description summary is: Use when the user is a standard member without the dreamina CLI and needs Jimeng text-to-video through opencli jimeng. Covers generate-video (type=video), history, new, workspaces, and account commands. Pair with dreamina-prompt-text2video for motion prompts. Never invoke dreamina or jimeng-cli execution skills..

Rules

• Read before write: first confirm the current state and real capabilities, then execute actions that change external state.
• Least privilege: only use the files, tools, accounts, and network scope needed to complete the current step.
• Evidence first: when run results, resource IDs, versions, hashes, or test output are missing, explicitly mark them as NOT_VERIFIED。
• Idempotency first: retain request identifiers and stage state; when the result is unclear, query first instead of blindly retrying.
• Privacy and security: logs, examples, receipts, and error messages must not contain tokens, cookies, keys, or personal sensitive data.

Workflow

Step 1: Clarify intent

Confirm whether this skill matches the goal; if it is only an adjacent need, hand it off to a more precise skill.

Step 2: Run pre-checks

Validate inputs, model/tool capabilities, output paths, budget caps, and approval status; if any key condition is unknown, stop at the read-only stage.

Step 3: Form a plan

List the tools to be invoked, the objects that will change, the success criteria, and the safe exit method after failure.

Step 4: Execute actions

Execute once per approval and record the request identifier; for ambiguous results, query first instead of resubmitting; retain an associable status or receipt for every external call.

Step 5: Verify delivery

Verify artifact existence, format, hash/identifier, cost status, and quality gates, and state facts, inferences, and unverified items separately.

Validation checklist

• The skill trigger conditions match the user's intent, and adjacent tasks were not misrouted to this skill.
• Inputs, target objects, versions, and output locations are all specified, and no guessed values were used in place of required values.
• All write, paid, publish, or irreversible actions are within the scope of user authorization.
• Results have been verified with independent checks; "the command succeeded" or "the file exists" alone does not count as complete acceptance.
• The output includes actual evidence, failed/skipped items, remaining risks, and executable next steps.

Gotchas

1. Mistaking the plan for the result: documentation or a prompt does not equal actual execution; the actual execution level must be stated.
2. Incorrect retry: a timeout or lost response may already have produced remote state; query first before deciding whether to retry.
3. Implicit scope expansion: batch, full-scale, publish, overwrite, and paid actions are not natural extensions of ordinary read/write operations.
4. Version drift: when referencing external resources, record the version, tag, or commit; do not treat a mutable branch as release evidence.
5. Stale evidence: caches, old screenshots, and historical tests cannot prove the current environment; refresh key evidence before delivery.

Non-applicability and boundaries

Paid, publish, overwrite, upload, or external write actions must use the explicit authorization of the current task; do not automatically expand the number of times or the budget. If the request requires another skill, do not copy its body; hand off by skill name and preserve the current task context.

Progressive disclosure

• When it is necessary to determine inputs/outputs, status, and authorization points, read references/workflow-contract.md。
• When self-checking before delivery is needed, read references/validation-checklist.md。
• When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
• For first runs, denial of privilege escalation, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。