dreamina-shot-annotator

Dreamina Shot Annotator

Annotate only. This Skill produces shot_annotation.schema.json content and nothing else.

Example request

Use dreamina-shot-annotator on the supplied contact sheet and analysis version.
Return only a shot_annotation.schema.json payload; do not change measured timings
or make an acceptance decision.

Capability Boundaries

✅ Can do

• Read contact sheets and keyframes produced by the analysis step.
• Describe each shot's subject, action, camera behaviour, continuity, and preservation constraints.
• Emit annotations that match shot_annotation.schema.json exactly.

⚠ Requires materials

• A completed machine analysis version and its contact-sheet artifacts.
• The caller's machine fingerprint, so the annotation can be bound to it.

❌ Out of scope

• Do not produce shot_evaluation.schema.json. Accept-or-reject decisions belong to dreamina-video-evaluator.
• Do not edit measured timestamps, motion, media identity, or boundary provenance.
• Do not assert rights.

Workflow

1. Receive the contact sheets and the machine analysis version.
2. Describe each shot using only the closed fields in shot_annotation.schema.json.
3. Return the annotations with the machine fingerprint it was written against.

Never do

• Never write measured values; those come from the machine analysis.
• Never emit an evaluation verdict.
• Never widen the annotation schema.

When to use

Load this skill when the user needs to select and execute a verifiable, recoverable professional workflow for the current request . First extract the goal, inputs, constraints, delivery format, and acceptance criteria from the request; the description summary is: Use when labelling contact sheets or keyframes with shot semantics before a Dreamina redesign, producing shot_annotation.schema.json content only.

Rules

• Read before write: first confirm the current state and real capabilities, then perform actions that change external state.
• Least privilege: only use the files, tools, accounts, and network scope required 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 phase state; when results are unclear, query first and do not retry blindly.
• Privacy and security: logs, examples, receipts, and error messages must not contain tokens, cookies, keys, or personally 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 prechecks

Confirm the goal, inputs, constraints, available tools, success criteria, and failure boundaries; if any key condition is unknown, stop at the read-only stage.

Step 3: Form a plan

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

Step 4: Execute actions

Execute in minimal sufficient steps and record evidence at key state changes; retain an associable state or receipt for every external call.

Step 5: Verify delivery

Output results, verification evidence, unfinished items, risks, and clear next steps, and state facts, inferences, and unverified items separately.

Validation checklist

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

Gotchas

1. Mistaking a plan for a result: a document or prompt does not equal real execution; the actual execution level must be stated.
2. Retrying on error: a timeout or lost response may already have produced remote state; query first before deciding whether to retry.
3. Implicit scope expansion: batch, full-volume, publishing, overwriting, and paid actions are not natural extensions of ordinary reads and writes.
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

Do not exceed the scope given by the user; write, payment, publish and irreversible actions require explicit authorization. If a request requires another skill, do not copy its body text; hand off by skill name and preserve the current task context.

Progressive disclosure

• When input/output, state, and authorization points need to be determined, read references/workflow-contract.md。
• When pre-delivery self-checks are needed, read references/validation-checklist.md。
• When encountering timeouts, partial success, or recovery scenarios, read references/error-recovery.md。
• For first run, privilege escalation refusal, and failure recovery, refer respectively to examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。