Final submission gate combining full verification, score enforcement, and submission checklist.

Plan reproducible ML experiment runs with parameters and metrics tracking

Systematic prompt engineering methods for AI-assisted academic research workf...

Core methods for empirical social science research including surveys and expe...

Set up RSS feeds and alerts to track new publications in your research area

AI-powered scientific writing workflow from outline to polished draft

Checklist-driven academic English polishing and Chinglish correction

Implement user skill change requests with optimization pattern evaluation

Measure what matters with proper event tracking, funnels, cohorts, and metrics. Use when setting up analytics, tracking features, or understanding behavior.

1. [Purpose](#purpose)

Status: Backlog

Documents the reasoning behind design decisions including alternatives considered, trade-offs evaluated, and principles applied. Use when making significant UX decisions, aligning with stakeholders on design direction, or preserving design context for future reference.

Cross-meeting archaeology skill. Consumes multiple meeting recaps (or raw notes) over a period and surfaces patterns invisible in any single meeting. Shows how decisions evolved, who has been saying what, where threads are stalling, and where contradictions have emerged. Produces a plain-text timeline, themes with confidence markers, stakeholder position tracking, consolidated decision list, contradiction flags, open items, narrative summary, and prioritized follow-ups.

Documents a strategic pivot or persevere decision with the evidence, analysis, and rationale. Use when evaluating whether to change direction on a product, feature, or strategy based on market feedback.

Audits an existing pm-skills skill against structural conventions and quality criteria. Produces a structured validation report with pass/fail checks, severity-graded findings, and actionable recommendations. Use when checking whether a skill meets repo standards before shipping or after making changes.

>

>

>

Score content against the 10 GEO criteria with evidence and prioritized fixes. Use when users ask to score, rate, evaluate, or estimate ranking strength.

Take a competitor's public GitHub repo. Fetch their open issues. Filter noise locally. Cluster into 6 demand categories. Score by real engagement. Output a ranked demand gap report and GTM messaging b

Interactive conversational setup wizard for instar. Walks users through initial configuration and identity bootstrapping conversationally.

Spawn, monitor, and communicate with persistent Claude Code sessions running in the background. Use when a task needs to run without blocking the current session, when the user asks to do something in the background, or when a long-running task needs its own context window. Trigger words: background task, spawn session, persistent, run in background, parallel, separate session, async task.

This skill should be run only when the user explicitly invokes it. Orchestrates end-to-end task implementation — understands the task, assesses complexity, implements directly or via a team of subagents for complex work, and always finishes with a code-polish pass.

**Company:** Series B Healthcare SaaS (80 people)

A product leader trapped in back-to-back meetings faces a compounding problem: every meeting demands decisions, and every decision depletes a finite cognitive resource. The result is decision fatigue

**Organization:** B2B Analytics SaaS

**Prepared for:** Mid-level PM (3 years experience) at a 500-person enterprise SaaS company

**Title:** Q1 All-Hands: What We Shipped, What's Next, and Where We Need Help

**Prepared for:** Director of Product, 200-person fintech startup

- **Date type:** Fixed external deadline

**Role:** Product Lead (IC/people-manager hybrid typical of product leadership)

Create a Pricing Strategy Pack (value metric, packaging, price points, conversion mechanics, rollout).

- **Product:** Team collaboration SaaS

- **Product**: Team collaboration SaaS

**Decision statement (one sentence):**

**Prepared for:** New Product Lead, 5 direct reports (3 PMs, 1 Designer, 1 Data Analyst)

**Team:** Product Team (10 people, remote-first)

Since the user did not provide answers to intake questions, the following explicit assumptions are made. Open questions that could change the ship decision are listed in Section 8.

**Feature:** Role-Based Access Control (RBAC) for Admin Users

Align stakeholders and secure buy-in: stakeholder map, pre-brief plan, decision summary.

**Company:** AI Support Copilot (E-commerce)

**Date:** March 2026

**Remote Cross-Functional Team: Reduce Chaos, Increase Decision Velocity**

**Context:** 12-person remote team (PM, Design, Engineering, Data) seeking to reduce chaos and increase decision velocity.

Create an Amazon-style PR/FAQ plus a backcasting launch plan.

Draft and edit written artifacts (email, memo, doc) with a quality gate.

>

Create a GitHub release. Follow the steps below in order.

Controller skill for the autopilot: triage, dispatch, integrate, and keep work moving via AgentBus.

Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.