Claude Skills by mocchalera

github.com/mocchalera

30 skillsA× 29B× 10 installs33 views

Analyze FootageAMUST USE when source footage or a material folder is provided and material understanding or 03_analysis generation is needed. Trigger not only on explicit analysis requests ('分析して', '素材を見て') but also when the user points at footage and says things like 'この動画で', 'この素材で', or any request that requires understanding the provided media before planning or editing.ai-agentsbashapiVotes: 0GitHub stars: 3
Build BlueprintAUse when selects_candidates.yaml exists and the user asks to design structure, build an edit blueprint, or create 04_plan/edit_blueprint.yaml.ai-agentsgobashVotes: 0GitHub stars: 3
Compile TimelineAUse when edit_blueprint.yaml and selects_candidates.yaml are ready and the user asks to compile the rough cut, generate timeline.json, or apply a review patch.ai-agentsbashVotes: 0GitHub stars: 3
Crop PhotosAMUST USE when the user asks to crop, reframe, trim, or improve composition of still photos, especially selected event photos, album photos, portraits, speakers, panels, workshops, or group photos. Use after photo selection or correction when the task is composition improvement rather than selecting images.ai-agentsbashVotes: 0GitHub stars: 3
Design IntentAMUST USE when starting a new video project, when the user provides footage and asks to edit/create a video, or when 01_intent/creative_brief.yaml does not yet exist. This skill interviews the user to understand their intent before any editing begins. Never skip this step.ai-agentsbashVotes: 0GitHub stars: 3
Evaluate EditAUse after changing prompts, skills, the compiler, or editorial policies — or when the user asks to measure edit quality, run regression evals, check agreement with approved edits, or says '評価して', '一致率を測って', 'eval を回して'. Compares agent output against human-approved golden projects.ai-agentsgobashVotes: 0GitHub stars: 3
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Export PremiereAUse when timeline.json exists and the user asks to export the rough cut or an editable handoff packet to Premiere Pro.ai-agentsswiftbashVotes: 0GitHub stars: 3
Finish Business ShortAFinish an existing Japanese business talking-head, lecture, interview, or testimonial rough cut as a credibility-first vertical social video. Use when the user wants an SNS short that preserves the speaker's meaning while tightening repeated ideas, adding a first-second thesis, readable full captions, restrained punch-ins, speaker identification, a registered CTA card, dialogue-first audio, and retention QA.ai-agentsVotes: 0GitHub stars: 3
Finish InterviewAApply repeatable dialogue MA, Studio-based or automatic portrait reframing, overlay-safe rendering, and loudness/sync QA to an existing interview or talking-head rough cut. Use when the user asks to make speech easier to hear, perform MA, enlarge or rebalance a person in frame, crop or punch in an interview, automatically propose framing, or prepare a finishing preview before final approval.ai-agentsVotes: 0GitHub stars: 3
Full PipelineAUse when the user wants an end-to-end run from source footage to a rough cut or final packaged video, or asks "素材から動画を作って", "全自動で", "編集して", or "粗編集を作って". Prefer the official full-pipeline entrypoint, then fall back to individual stage Skills for recovery.ai-agentsbashapiVotes: 0GitHub stars: 3
Import PremiereAUse when an edited Premiere Pro FCP7 XML should be compared against timeline.json or imported back into the project.ai-agentsbashnodeVotes: 0GitHub stars: 3
Re EditAUse when the user asks to modify an existing rough cut — shorten, lengthen, remove a clip, reorder, change BGM, adjust pacing. Works by generating a review_patch and re-compiling.ai-agentsbashVotes: 0GitHub stars: 3
Render VideoAUse when the user wants a final packaged video from an approved project and the project satisfies Gate 10 packaging prerequisites.ai-agentsswiftbashVotes: 0GitHub stars: 3
Review RoughcutAUse when timeline.json exists and the user asks to review the rough cut, critique the edit, or generate review_report.yaml and review_patch.json.ai-agentsgobashVotes: 0GitHub stars: 3
Select ClipsAMUST USE when 01_intent/creative_brief.yaml and 03_analysis artifacts exist and the user asks to choose clips, extract candidate segments, run triage, or build 04_plan/selects_candidates.yaml. Use before /blueprint whenever selects are missing, and re-run when the brief or analysis changes.ai-agentsbashVotes: 0GitHub stars: 3
Select PhotosAMUST USE when the user provides a photo ZIP, photo folder, or still-image event material and asks for photo selection, album selection, highlights, digest photos, curation, or quality filtering. Use this instead of analyze-footage when the source is primarily still photos and the requested work is selecting images rather than editing or video planning.ai-agentspythonbashVotes: 0GitHub stars: 3
Setup EnvironmentBMUST USE when the user is setting up this project for the first time, when dependencies are missing, API keys are not configured, or when 'npm run demo' fails. Triggers on: 'セットアップ', '環境構築', 'setup', 'install', 'API key', 'ffmpeg not found', 'GEMINI_API_KEY', 'cannot find module'.ai-agentspythonbashVotes: 0GitHub stars: 3
Short Sound DesignADesign and verify audio finishing for Japanese or English short-form social video. Use for 短尺SNS, BGM/効果音, テンポ調整, 意味ベース配置, dialogue-first mixing, or existing rough cut audio finishing with pinned local assets and internal-review QA.ai-agentsVotes: 0GitHub stars: 3
Troubleshoot ErrorAUse when a pipeline step fails, an error occurs, schema validation fails, ffmpeg crashes, or API returns an error. Diagnose the root cause and attempt automatic recovery.ai-agentstypescriptbashVotes: 0GitHub stars: 3
Finish Creator ShortAFinish an existing Japanese creator, challenge, comeback, vlog, or community-building vertical social rough cut as an evidence-grounded short-form story. Use for strong opening declarations, identity and struggle arcs, crisis-to-goal recovery, multi-source B-roll and evidence stills, emotional typography, semantic punch-ins, pinned SFX, dialogue-first audio, platform-added music delivery, and creator-short retention QA.ai-agentsgobashVotes: 0GitHub stars: 3
Vertical Social CompositionAResolve registered vertical composition inputs from source-grounded framing evidence, source A/V identity, layout anchors, and safe degradation. Use when a blueprint contains framing candidates or visual intents for a vertical delivery.ai-agentsVotes: 0GitHub stars: 3
Vertical Social Platform DeliveryASelect an evidence-backed platform delivery profile, preserve organic and ads scope boundaries, and produce safe-zone QA input with an explicit human preview gate when evidence is unknown or stale.ai-agentsbashVotes: 0GitHub stars: 3
AuthorshipAai-agentsVotes: 0GitHub stars: 3
Missing NpmARun `npm run absent`.ai-agentsVotes: 0GitHub stars: 3
Missing ScriptARun `npx tsx scripts/absent.ts`.ai-agentsVotes: 0GitHub stars: 3
Missing TemplateAValid references are `vos:content.good/v1` and `vos:overlay.good`. Invalid reference: `vos:content.not-real/v1`.ai-agentsgoVotes: 0GitHub stars: 3
Unknown FlagARun `npm run good -- --bad`. Run `npm run indirect -- --bad`. Run `npm run good -- --asset-id <asset-id>`; promotion-only flags must not leak into this command.ai-agentsgoVotes: 0GitHub stars: 3
ProducerA```bash python .agents/skills/producer/scripts/make.py \ --output projects/demo/03_analysis/photo_<asset_id>.json npm run demo swift run --package-path apps/studio ```ai-agentspythonswiftVotes: 0GitHub stars: 3
Finish Creator ShortAfixtureai-agentsVotes: 0GitHub stars: 3
ArtifactA- `09_output/not-produced.json`ai-agentsVotes: 0GitHub stars: 3