plan-craft

You MUST use this when lasting learnings from the current session should be recorded for future agents - pitfalls hit, mistakes the user corrected, conventions found, or commands that finally worked, whatever the conversation language - including when the user asks to write down what the session taught and at the end of the agentflow chain after finalize. Records them without asking in the project's gitignored docs/session-learnings/AGENTS.md; on a separate request, triages the accumulated notes into AGENTS.md, CLAUDE.md, the user's global instructions, or a stronger enforcement such as a check or a test, applying only the approved edits. Not for auditing or restructuring instruction files (maintaining-agent-context). Not for general memory or improvement requests for skills.

You MUST use this when a change needs an independent review before it moves on - a finished task, a feature branch, a pull request, work-in-progress or uncommitted changes since a given ref, or a spec or plan document that needs review - in any programming language. Replaces devflow review-request. Pins the exact target and its tree fingerprint, gathers intent and constraints, and dispatches a read-only reviewer that returns separate verdicts and evidence-backed findings.

You MUST use this when the user asks to take a GitHub issue through the agentflow workflow, with manual stage approvals or a single --auto invocation. Owns intake, clarification, planning, implementation, review, handoff and resumable orchestration. Delivery consumes the installed owner's G3 helpers through explicit current project callbacks and proofs; unknown delivery contracts block their actions. Not for writing a standalone spec, executing an existing plan without issue orchestration, or bypassing project permissions.

You MUST use this when an existing implementation plan is to be executed, either directly in the current session or through subagents, including resuming an interrupted execution from the plan's execution record, or when one or two edits with an obvious approach need doing without a plan. Covers task-by-task execution with evidence, drift handling and blockers, and a resumable execution record. Replaces devflow inline-plan-dev and subagent-plan-dev. Not for writing a plan (plan-craft), checking finished work (verify), acting on review findings (cr-received), or merging, pushing, or opening a pull request (finalize).

Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.

Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.

Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.