Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation…
Socratic spec refinement — clarify WHAT a phase delivers with ambiguity scoring before discuss-phase.
Retroactively verify threat mitigations for a completed phase — from produtoramaxvision/maxvision
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit — from produtoramaxvision/maxvision
Generate UI design contract (UI-SPEC.md) for frontend phases — from produtoramaxvision/maxvision
Owner-only — detects upstream drift of this plugin and applies the update via `claude plugin update` CLI (CC-native auto-update).
Manually install the maxvision statusline. Copies wrappers to ~/.claude/hooks/ (stable user-scope location) and writes the absolute path to ~/.claude/settings.json…
Retroactively audit and fill Nyquist validation gaps for a completed phase — from produtoramaxvision/maxvision
Create a clean PR branch by filtering out .design/ and .planning/ commits. Code-review-ready branch for the design implementation work.
Manual plugin-update check. Shows cached state by default; --refresh bypasses the 24h TTL; --dismiss hides the nudge until a newer release ships; --prompt spawns…
Background-dispatch variant of execute-phase. Spawns one `claude --bg --agent maxv-executor` session per plan (with auto-worktree) instead of running waves of in-process Agent…
Dispatches a long-running task to a maxv-* subagent in background via Claude Code's Agent View (`claude --bg`).
Coordinates a repo-wide mechanical migration (rename X → Y across N files, bump dependency version across a monorepo, port a deprecated API call site by site) by dispatching the…
Creates a custom maxv-<task> skill in ~/.claude/skills/ by combining capabilities from multiple already-installed source skills.
Use when projetar/operar features que tocam dado pessoal — definir o que é PII no contexto do plugin, entender o que armazenamos, retenção, direitos do titular (LGPD art.
Use when the user asks for Japanese media-forge video-prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms…
Goal-backward phase verification + UAT conversational verification, consolidated. Use when checking phase achieves promised goal before milestone.
EN: Triggered when user says "restore context", "continue", or similar in English. ZH: 当用户说中文"恢复上下文"、"恢复"、"接着"、"继续之前的工作"时触发。 IT: Si attiva quando l'utente dice "ripristina…
Use when the user asks for Korean media-forge video-prompt examples, Korean prompt patterns, example rewrites, or safe versions of working Korean video-generation prompts, for any…
Use when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for…
Compares the locally installed version of a skill or subagent against its upstream source (sha or semver) and reports whether an update is available. Cache-aware (1-hour TTL).
Use when a media-forge video request is a long story, connected set of clips, multi-generation scene, campaign sequence, dense storyboard, continuation-ready plan, or any idea…
Use when the user asks for visual style, art direction, render feel, period aesthetic, texture, animation style, realism level, or style-safe alternatives to studio or franchise…
Use when the user asks for Spanish media-forge video-prompt wording, Spanish cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms…
Use when the user asks for a compact media-forge video prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language, for any…
Audits the user's local skill collection (personal + plugin + project) for redundancy, broken descriptions, missing `paths` filters, skill bloat, and outdated components.
Use when the user asks for body action, choreography, physics, object movement, movement timing, action continuity, stunt direction, or motion-reference mapping, for any…
Use when the user wants creative guidance, story development, scene planning, or a director interview to turn a media-forge video idea into a production-ready prompt for any…
Installs a Claude Code subagent on-demand from the FTS5 catalog (`~/.claude/cache/maxv-orchestration/index.db`) into `~/.claude/agents/<name>.md` (user scope) or…
Detects whether a user task contains multiple independent subtasks and splits it into a JSON array. Internal helper for orchestrate Phase 0.5; uses session credentials (no API…
Model x params capability cheatsheet. Static reference; read by all media-forge agents.
Use when a media-forge video output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause…
Use when the user asks to write, improve, translate, compress, or debug a media-forge video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides…
Ranks candidate skills/agents by task fit using Sonnet LLM-as-judge AND classifies task complexity (model + effort) in same call.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions — from…
Multi-image scene composition with role-labeled refs (up to 14). Triggers: scene compose, composition, multi-image scene.
Use when the user asks for Chinese media-forge video-prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX,…
Use when the user asks for Korean media-forge video-prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into…
Removes a locally-installed Claude Code subagent from `~/.claude/agents/` (user) or `.claude/agents/` (project). Deletes the `.md` file and the `.maxv-source-<name>.json` sidecar.
Looks up a skill by name, keyword, or domain in the curated catalog (skill-sources.json). Returns the source repo, tier of trust, install methods supported, and any guardrails…
Use when the user asks for lighting design, atmosphere, time of day, color temperature, shadow, reflections, weather light, practical lights, or mood transitions, for any…
Installs a Claude Code skill from a curated source via one of three methods (sparse-clone, plugin marketplace, or npx antigravity filtered).
Use when the user asks for Chinese media-forge video-prompt examples, Chinese prompt patterns, example rewrites, or safe versions of working Chinese video-generation prompts, for…
Use when the user asks about workflow operations, API planning, provider/router surfaces, China-facing surfaces, post-production, stitching, batch workflow, or integration…
Use when the user asks for character consistency, character tags, identity lock, multi-character blocking, wardrobe continuity, hand safety, expression control, or…
Higgsfield prompting playbook — MCSLA formula, DoP camera verbs, Cinema Studio lens dictionary, Soul ID lifecycle, Marketing Studio templates.
Self-test the maxvision-orchestration plugin after install. Runs five read-only checks (index, cheatsheets, gh auth, jq+sqlite3 in PATH, sample BM25 query) and reports…
Use when the user asks for media-forge video audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven…
Removes a locally-installed skill from ~/.claude/skills/ (user scope) or .claude/skills/ (project scope). Deletes the skill folder and its .maxv-source.json sidecar.
Extend existing video via Veo 3.1 +7s hops. Triggers: extend video, longer video, continuation.
Use when the user asks for a media-forge video template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or…
Use when the user asks to continue, extend, make the next part, repair the tail, bridge between known frames, re-anchor drift, or create a successor prompt from accepted footage,…
Kling V3 (Standard / Pro / Master 4K / Omni multi-shot) prompt engineering. 5-part spine (Camera-Scene-Action-Vibe-Time), per-mode cookbook, model-tier selection.
Use when the user wants a fast media-forge creative brief, a short interview, a compressed intake flow, or a quick director-style clarification before prompt writing, on any…
Use when the user asks for Russian media-forge video-prompt wording, Russian cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms…
Decides which subagent and which skills should handle a task by reading CLAUDE-agents.md and CLAUDE-skills.md, applying the routing-rules.json heuristics, and returning a…
Use when an English media-forge video prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production…
Looks up subagents by keyword/domain across all installed plugins (voltagent, pr-review-toolkit, feature-dev, code-review, superpowers, etc.) plus user-level agents.
Re-fetches metadata for catalog sources (`skill-sources.json`) and updates fields like `last_updated`, star counts, latest commit sha, and license.
Save decision, bet, or learning to the context registry