Coding & Development

QiJu(起居) Local-first, lossless session records for AI coding agents.

🐙 Connect every device with every AI model—macOS, Windows, Linux, iOS, Android, servers & edge nodes—so each model can do what it does best.

Reusable Codex skills and repository starter packs

A predictions ledger with forced settlement for AI agents: log every judgment as a bet, settle it against reality, distill recurring biases into rules. Learns from outcomes, not corrections.

Claude Code + Grok plugin marketplace — 18 curated plugins & MCP servers. One-command install.

Thin nput wrapper for placing agent skills

Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, and subagent roles — synced to Claude Code, Codex, Droid, Hermes, and Pi. Commit-pinned and audited.

Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.

Apply an approved sub-skill grouping by moving user-specified skills into a parent bundle, with timestamped backups of every modified directory.

Discover and reorganize the skill inventory into hierarchical sub-skill bundles. Use when the user asks to review, group, or consolidate skills into a parent bundle.

Use after a release succeeds, when maintainers need to sync apps/kimi-code/CHANGELOG.md into docs/en/release-notes/changelog.md and docs/zh/release-notes/changelog.md, then open a PR on a dedicated branch.

Use when generating changesets in the kimi-code repository, including package bump selection, internal package and CLI bundle handling, bump levels, major confirmation, and English changelog wording.

Invoke only when the user explicitly asks to review code through the "single level of abstraction / layered error handling" lens — a function does only its own layer's business logic while errors are handled above or below. The agent reports detections, raw-count measurements, and move directions. Apply only when the user explicitly requests this lens.

Think like Fable 5 — natural, flowing, purposeful reasoning distilled from 4,665 real chain-of-thought traces with mathematical precision. Use this skill EVERY TIME before writing code, making decisions, or taking action.

Verify like Fable 5 — obsessive, systematic, evidence-based quality assurance woven into your reasoning. Use this skill when you have just written or modified code, need to confirm something works, are running tests, or need to validate output against requirements.

Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done", "finish while I am away", "do not ask questions unless truly blocked", or similar. Convert ordinary ambiguity into stated assumptions, proceed through implementation and validation, stop only for true blockers, and end with a clear recap of decisions, changes, verification, and residual risk.

Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, inspect what the agent actually changed and verified, report gaps, and optionally make scoped fixes when the user authorizes repair.

Turn a sentence into a real Claude Skill — generated, validated, and trigger-tested against your own model. The only skill generator that measures whether the skill actually fires.

Recently updated agent-skill-related GitHub repository: tinyepicaccess-hash/claude-skills.

可信 Agent Skills 与 MCP Hub 平台设计与实现

将游戏 PRD、UI、配置、协议和参考图片转换为可执行测试用例与原生 XMind 脑图的 Codex Skill。

Community connectors and skills for Use Brian: MCP servers and agent skills the assistant can load.