Installable skills for people who manage AI work
Give your AI staff a process, not another prompt.
Copy complete, inspectable SKILL.md files for Claude Code, Cursor, Codex and other agents that support the Agent Skills standard. Built for knowledge workers and AI managers who need workflows they can trust, version and reuse.
skills/
prompt-refiner/
SKILL.md
decision-framer/
SKILL.md
meeting-to-actions/
SKILL.md
calibrated-forecasting/
SKILL.md
decision-memo/
SKILL.md
teachback/
SKILL.md
+8 more
---
name: prompt-refiner
description: Turn vague requests into executable briefs.
---
# Prompt Refiner
Extract the outcome, context, constraints, output and success checks before execution.
Install
A folder your agent can discover.
Each skill is a folder with a SKILL.md entry file — the same open format your coding agent already understands. Copy from any skill page, place it in your project, then describe the task normally.
- 01
Copy
Create a folder named after the skill and save its content as SKILL.md.
- 02
Place
Use .cursor/skills/ for Cursor, .claude/skills/ for Claude Code, or the equivalent path for Codex.
- 03
Ask
Describe the task normally. Your agent loads the skill when its description matches.
Featured skills
Start with the workflows AI managers reach for most.
Briefs, decisions, meeting follow-through, premortems and focus tradeoffs — each one a complete SKILL.md you can inspect before your agent runs it.
/prompt-refiner
Prompt Refiner
Turns a vague request into an executable brief without silently inventing missing requirements.
/decision-framer
Decision Framer
Separates the real choice from noise, then tests options against explicit criteria and uncertainty.
/meeting-to-actions
Meeting to Actions
Converts messy notes into decisions, owned actions, deadlines and unresolved questions.
/decision-memo
Decision Memo
Structure a real, consequential decision as a written narrative memo — full sentences and paragraphs rather than bullet points, forcing the logic to be checked rather than gestured at, plus explicit classification of whether the decision is reversible (a "two-way door") or not (a "one-way door")
/premortem
Premortem
Run a premortem — imagine a plan has already failed and work backward to explain why, which surfaces risks that forward planning misses because it counteracts the social and psychological pressure to seem confident
/focus-and-tradeoffs
Focus and Tradeoffs
Cut a bloated plan, roadmap, or list of priorities down to the one or two things that actually matter — real focus means saying no to a thousand things
The skill set
14 skills, grouped by the work they support.
Read every line before your agent does. Copy one into a skill folder, adapt it to your team's workflows and keep it under version control.
Briefing & framing
Turn vague asks into executable briefs and clarify what progress someone is trying to make.
Prompt Refiner
Turns a vague request into an executable brief without silently inventing missing requirements.
prompt-refiner/SKILL.md
Jobs to Be Done
Diagnose what "job" a customer is actually hiring a product, service, or workaround to do, using the Jobs-to-be-Done framework — progress in a specific circumstance, forces of progress, switch interview, job statements, and desired-outcome scoring
jobs-to-be-done/SKILL.md
Decisions & judgment
Frame choices, stress-test plans, and make uncertainty explicit before you commit.
Decision Framer
Separates the real choice from noise, then tests options against explicit criteria and uncertainty.
decision-framer/SKILL.md
Decision Memo
Structure a real, consequential decision as a written narrative memo — full sentences and paragraphs rather than bullet points, forcing the logic to be checked rather than gestured at, plus explicit classification of whether the decision is reversible (a "two-way door") or not (a "one-way door")
decision-memo/SKILL.md
Calibrated Forecasting
Turn a vague prediction or unstated confidence level into an explicit, calibrated probability estimate, using superforecasting practices — breaking questions into sub-questions, checking base rates, updating in small increments as new information arrives, and tracking predictions against outcomes
calibrated-forecasting/SKILL.md
Premortem
Run a premortem — imagine a plan has already failed and work backward to explain why, which surfaces risks that forward planning misses because it counteracts the social and psychological pressure to seem confident
premortem/SKILL.md
Agent staff ops
Follow-through from meetings, focus tradeoffs, and learning from outcomes.
Meeting to Actions
Converts messy notes into decisions, owned actions, deadlines and unresolved questions.
meeting-to-actions/SKILL.md
Focus and Tradeoffs
Cut a bloated plan, roadmap, or list of priorities down to the one or two things that actually matter — real focus means saying no to a thousand things
focus-and-tradeoffs/SKILL.md
Postmortem / Retro
Extract a specific, reusable lesson after something succeeded or failed, following the principle that pain plus reflection equals progress — outcomes only compound into better judgment if they're deliberately converted into a written, checkable lesson rather than just felt and moved past
postmortem-retro/SKILL.md
Learning & sense-making
Build real understanding and apply cross-disciplinary thinking tools.
Teachback
Test and build genuine understanding of a concept using teachback — explain it as simply as possible, notice exactly where the simple explanation breaks down, and treat that break point as the thing to actually go learn
teachback/SKILL.md
Mental Models
Apply a latticework of cross-disciplinary thinking tools (inversion, second-order effects, incentives, circle of competence, opportunity cost, base rates) to frame a vague or general problem
mental-models/SKILL.md
First Principles
Rebuild a problem from fundamental truths (physics, economics, unit costs, what's actually true regardless of convention) rather than by analogy to how things are normally done
first-principles/SKILL.md
Strategy & stakeholders
Competitive positioning, negotiation prep, and stakeholder conversations.
Moat Analysis
Assess whether a competitive advantage is durable (a real "moat") or temporary, by checking it against the standard sources of durable advantage — switching costs, network effects, economies of scale, brand/trust, and regulatory or IP protection — rather than taking "we're ahead right now" at face value
moat-analysis/SKILL.md
Negotiation Prep
Prepare for a high-stakes negotiation or hard conversation using tactical-empathy techniques — labeling emotions, calibrated open-ended questions, mirroring, and getting to genuine "that's right" rather than a grudging "yes."
negotiation-prep/SKILL.md
Free samples are provided for personal and commercial use under the MIT licence, without warranty.
Get oriented
Practical notes, not invented blog posts.
Honest starting points for people managing AI work — written in the open on Substack.
Updates
What's new in the open catalog.
No invented version history — just honest notes on catalog changes and practical writing from How I Grok Bot.
Sep 2026
Catalog refresh: 14 free skills for AI managersRestored the full open catalog — briefing, decisions, agent ops, learning and strategy skills you can copy today.
Aug 2026
How I Grok Bot: AI staff, in the openNotes on running AI agent staff in the open, plus alerts when new skills land.
Quick answers
About Agent Skills
What is a SKILL.md file?
It is the entry file for an Agent Skill: a portable package of instructions that tells a compatible AI agent what the skill does, when to use it and how to perform the workflow.
Who are these skills for?
Knowledge workers and people managing AI agents who want repeatable processes instead of one-off prompts — briefs, decisions, meeting follow-through and similar work.
Do these work in Claude Code, Cursor and Codex?
Yes. They use portable SKILL.md files supported by Claude Code, Cursor and Codex. Other agents may support the same open format, but installation paths vary.
Can I adapt these for my team?
Yes. Each skill is a plain SKILL.md file under the MIT licence. Copy it, edit the wording for your workflows and keep it under version control.