Productivity

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.

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).

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.

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.

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

A Codex skill for GitHub repository and collaboration workflows

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

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

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

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

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 Luna execution, Sol reasoning, and controlled model escalation.

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 skill that turns a written recipe into an execution-order cooking timeline.

Codex Skill for discovering and explaining local projects with zvec-grep

Codex skill for Harbor and Terminal-Bench batch PR delivery, QC tracking, dual review, and acceptance checklists.