Half Clone Conversation

Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

Bulk-extract every candidate flag from a binary namespace, build an extraction inventory with occurrence counts and call-type tags, cross- reference against a documented set, and track completeness across probe campaigns until the undocumented remainder reaches zero. Covers namespace prefix harvesting, gate-vs-telemetry disambiguation at the call-site level, completeness metrics, DEFAULT-TRUE population reporting, and a final completion confirmation scan. Use upstream of probe-feature-flag- state when you need a complete catalog rather than a sample, or when a prior wave-based campaign needs a verifiable end condition.

Review a proposed Agent Skill for structural validity and content quality before publishing. Runs the skill-validator CLI to check for structural issues, scores the skill with an LLM judge, and interprets results to advise SMEs on what to address. Use when a user wants to review, validate, or quality-check an Agent Skill.

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

Plan a software release cycle with milestones, feature freezes, release candidates, and go/no-go criteria. Covers calendar-based and feature-based release strategies. Use when starting planning for a major or minor version release, transitioning from ad-hoc to structured release cadence, coordinating a release across multiple teams or components, defining quality gates for a regulated project, or planning the first public release (v1.0.0) of a project.