Claude Code / Codex CLI skills I actually run in a PM work week — metric attribution, PRD review panel, cross-model GO/NO-GO gate, blind AB testing, audience-tailored briefs, decision triage, session handoff, Lark meeting notes, comment loops, peer-feedback drafting. Runnable engines, not prompt snippets.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use before launching any large agent orchestration (fan-out) — roughly ≥20 subagents or an estimated ≥1M subagent tokens — and while such a fleet is in flight. Covers: quoting the cost to the human before dispatch, refusing to launch during unstable API connections, in-flight budget stop-loss, T+60s batch health…
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A message-writing guide for turning a finding, change, status update, or plan into a ready-to-send Feishu or Lark message. Feishu, also called Lark, is a workplace messaging and collaboration app.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A workflow for comparing two versions of a prompt, skill, or piece of text without revealing which one is the new version. Separate agents create the versions, and a person scores them without seeing their labels.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use when the user has to decide which of several candidate changes are worth doing, or when this session is about to propose two or more optional changes and needs the user to pick scope, cost, or priority. Decision triage / cost-benefit / backlog prioritization: force every candidate into a fixed table whose first…
aaronartistzhang-afk/DailyWork
Skill Codex
A read-only review checkpoint that asks another coding model to inspect a plan, code change, SQL query, or externally published numbers and return a GO or NO-GO decision.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A conversation-based method for reviewing a PRD, a product requirements document, as if it were being examined by a product group. It produces entry and review decisions plus P0, P1, and P2 findings.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A runnable tool for simulating a product-group review of a PRD, a document that explains what a product should do and why. It uses several review stages and produces a two-part decision plus prioritized issues.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A workflow for processing unresolved comments in a Lark document, especially comments created after a chosen time such as today. It groups the comments, proposes edits, and handles replies and resolution according to the selected mode.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use when a person who holds a FORMAL evaluation/feedback responsibility (inside an HR process) wants to draft an evidence-based, first-cut peer-feedback write-up from their OWN visible Lark/Feishu collaboration records. The skill uses lark-cli to assemble first-hand facts (1:1 work chat + a user-confirmed whitelist of…
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
A tool that turns a Lark or Feishu meeting-minutes link into concise meeting notes, including @mentions for responsible people, and sends them to a group or direct message.
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use when a metric moved between two periods (week-over-week, month-over-month, pre/post, A-vs-B) and you need to attribute WHY — which dimension members, segments, or factors drove it, ranked and drilled to root cause. Covers ratio/rate metrics (reach rate, CTR, conversion, retention, win rate, ARPU) and additive…
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use when work must be handed from this AI coding session to another session on the same machine, or to a later session of the same person. Session handoff / context handoff: produce a fixed three-line header (state / what you do next / what you decide) plus a six-section HANDOFF.md so the receiver sees 'fixed or not…
aaronartistzhang-afk/DailyWork
Skill Claude CodeCodex
Use when sedimenting a lesson from a real run into an existing skill, or when a skill was just edited and needs a post-change regression before it ships. Post-edit regression / skill evolution: locate the smallest section to change, propose the diff first, then run five classes of behavior tests (routing / regression…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: