short-drama-review-normalizer
Internal deterministic consent gate for meta-short-drama. Normalizes draft review and post-revision confirmation replies, and fails closed before external image/video generation.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/short-drama-review-normalizer && cp -r /tmp/short-drama-review-normalizer/src/opensquilla/skills/bundled/short-drama-review-normalizer ~/.claude/skills/short-drama-review-normalizerSKILL.md
# short-drama-review-normalizer Internal, deterministic consent boundary used by `meta-short-drama` after its free-form draft review and before any image/video provider call. Its `canonical_script_snapshot` phase also freezes the final in-memory script; it never re-reads the user-editable `script.txt`. The initial-review phase accepts the verbatim `review` string and emits a bounded decision block. Explicit approval proceeds without overrides. A recognizable, short-drama-specific adjustment emits `DECISION: revise` and is preserved verbatim as `NEW_NOTES`; it never authorizes a provider call. After the revised script is shown in a second `user_input` preview, the `media_approval` phase requires a new, standalone explicit approval. Missing, ambiguous, off-topic, or additional-edit replies hold; explicit cancellation cancels. Explicit external-transfer restrictions also hold, even when the same reply contains an otherwise valid adjustment. This includes negated transfer verbs, requirements that content remain on-device or local-only, and prohibitions on an external recipient seeing, accessing, or receiving the content. Ordinary local edits to a character, scene, shot, lighting, or style are not treated as privacy restrictions without one of those explicit constraints. This helper does not call a model or the network. The final `media_approval` `DECISION` output is the sole authority for downstream paid media conditions; a language model never gets to promote an edit or unclear reply to consent. The snapshot phase requires exactly one final `DECISION: proceed|hold|cancel`, accepts at most 200,000 UTF-8 bytes, and echoes the supplied script without consulting disk. Only `proceed` can unlock the separate paid-step conditions.
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'