Productivity

Authors a workstream brief for dispatching multiple parallel build agents across one codebase, with per-lane file ownership, shared-ground warnings, and a derived DO-NOT list. Use whenever work is about to be split across concurrent agents, workers, lanes, or waves — even if the user does not say "write a brief". Trigger phrases include "fan out", "parallel agents", "orchestrate this", "split into lanes", "workstreams", "run these in parallel", "review-gated build". Produces the brief; does not dispatch.

Run a structured multi-perspective review of a decision instead of getting one agreeable answer. Use when the user says run a council, get me perspectives on this, should I do X, stress-test this decision, or is this a good idea.

Triage an email inbox — sort what needs a reply, draft the replies, flag what needs a decision, and surface what can be ignored or unsubscribed. Use when the user says triage my inbox, do my email, what's in my inbox, or clean up my email.

Use this skill after completing a coding, deployment, config, database, or release task, when the user says 记一下 / 记一条 / 沉淀一下 / 总结到知识库 / 更新知识库 / 记到 Obsidian / 写发版文档, or asks where this week's finished work should be recorded. Records only landed, release-relevant facts (scripts, configs, paths, validation, rollback) as durable notes in the Obsidian vault and maintains the weekly release note (发版) — only when there are landed facts, not plans or speculation. Do NOT use for note editing, creating, moving, renaming, reviewing, MOC maintenance, weekly reports, or general what-I-did-this-week summaries — use `obsidian-personal-knowledge-base` for those. Do NOT use for brainstorming or speculation.

Render Markdown from templates and structured data using Knap CLI. Use when the user asks to apply a Knap template, turn JSON or CSV data into notes, batch-generate Markdown files, or format Defuddle output into a note.

当某件事靠模型自己完成预计会消耗大量 token，但人类只需几秒、不费力气就能解决时，用提问把它交给人类，节省 token 与时间。适用于需要反复猜测、多轮试错、大范围搜索，或只有用户掌握答案的时刻。Use when a subtask would burn many tokens yet a human can settle it effortlessly.

Use when the user wants to post or schedule to a Telegram channel or group through Publora, using a bot. Covers Telegram markdown, silent delivery, link previews and forward protection. Bot API caps media captions at 1,024 characters and videos at 50 MB. Not for other platforms (each has its own skill).

Four output-discipline rules for AI agents: Implicit-Need Fill (surface the request behind the request before answering), Structured Output (conclusion first, no rambling), 3-Option-Plus-Premium (non-code tasks get >=3 compared options plus one premium recommendation), Assumption-Circuit-Breaker (pre-send logic check, explicit assumptions, coverage statement, fallback plan). Invoke with /four-rules; L3 blocks are internal-only, never upload.

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Claude skills by Alex Zapadenko — free SKILL.md files, mirrored from product.inc/skills

Reusable Codex skill for CPWRR project review and interview storytelling

A Claude skill that turns a folder into a collaboration knowledge base for you, your AI, and your humans

A Codex skill for GitHub repository and collaboration workflows

Self-hosted Discord bot bridge and Codex Skill for a selected Codex Desktop task. Experimental Windows preview.

Codex skill for sourcing and validating two different-source appliance B-roll previews

A Codex skill for pnpm release-age gates, lockfile verification, and reviewed version-pinned build permissions.

Codex skill for cautious speaker-labeled meeting transcripts and grounded summaries.

Agent skills for my projects

Hook-free Codex Skill for proportional development workflows and cross-session continuity

A Codex skill for creating source-grounded Chinese paper-reading and lab-meeting PPTX decks.

A portable agent skill for screening, drafting, independently reviewing, and archiving Upwork proposals.

PhanesLight, manual install: multi-agent orchestration and durable project memory for Claude Code. One prompt turns a repository into a wired, opinionated agent team. Plugin version at Aloim/phanesplugin.

A lightweight Codex skill that adds OpenAI GPT-6 Astra guidance to project-level AGENTS.md initialization.

A Codex skill for Luna execution, Sol reasoning, and controlled model escalation.