Automation

Syncs your biji.com (Get 笔记) notes into dated local Markdown and turns video, podcast or local media into transcripts using Get's transcription quota.

Writes a tight 8-line handoff note (done, open, next, decided, rejected) and saves it to project memory for the next chat or teammate.

Finalizes a completed OpenSpec change by verifying artifacts, tasks and delta specs before moving it into a dated archive folder.

Publishes a finished HTML article plus cover image to a WeChat Official Account as a draft or a live mass-send via the official API.

A file-based continuity harness that saves your project's current state, rules, and milestones so any session can pick up exactly where you left off.

Generates a structured album progress dashboard with per-phase completion percentages, a track status table, and blocking items.

Orchestrator skill that runs task waves across isolated git worktrees, verifies each worker branch by evidence, merges sequentially, and ends with a single PR.

An AI-led interview that writes and validates the prd-taskmaster plugin config at .atlas-ai/config/atlas.json so you never hand-edit JSON.

An autonomous 13-step loop that pulls the next TaskMaster task, dispatches a complexity-tiered subagent, and only marks it done after evidence-gated triple verification and a reachability sweep.

Prepares per-package CHANGELOG.md entries before tagging a Ratel release — git-cliff draft, human curation, then write.

A cc-fleet skill that spawns long-lived third-party LLM teammates in tmux panes and coordinates them across turns via SendMessage.

Delegates one-shot or flat parallel batches of work to cc-fleet provider models (DeepSeek/GLM/Kimi/Qwen/MiniMax/Codex/Claude) via the headless `cc-fleet subagent` CLI.

Teaches Claude to author and run multi-phase, resumable JS orchestration scripts over cc-fleet provider subagents.

Author a JS script that orchestrates multi-phase, resumable runs across many cc-fleet provider subagents, off the main context.

Runs headless provider LLMs (DeepSeek, GLM, Kimi, Qwen, MiniMax) via the cc-fleet CLI for one-shot answers or lock-free parallel fan-out.

Challenges whether a new requirement is worth doing, forces a verifiable expected outcome, then creates a Feishu requirement doc and a Meegle work item cross-linked to each other.

The control tower for the dontbesilent toolbox: it reads your conversation, picks and sequences the right skills, and starts executing in the same turn.

Rules that keep subagent transcripts out of your main context by running agents in the background and passing results through files.

Enforces a strict output contract for claude-mem observer jobs on Grok Bot: either skip_summary or exactly one observation XML, never prose.

Judges an exact implementation subject against its acceptance criteria and returns a single PASS/FAIL/NOT_PROVEN verdict with evidence.