en un clic
personal-agent
personal-agent contient 20 skills collectées depuis andi-canva, avec une couverture métier par dépôt et des pages de détail sur le site.
Skills dans ce dépôt
Prepare for a 1:1 — pull context from goals, meeting notes, Slack, and tasks to generate talking points
Auto-generate or update description, type, topics, aliases, and graph-backed relationship fields for a file.
Build a focused plan for today based on goals, tasks, and recent activity. Reads from the weekly plan if it exists and updates it.
Check system health — metadata gaps, graph integrity, alias sync, and referential integrity.
Weekly review + compound learnings — review progress, surface blockers, distill insights into Memory
Cross-initiative alignment checker — surfaces misalignment, gaps, duplication, dependency risks, and synergy opportunities across active initiatives in the company and your groups roadmap. Complementary to /pulse (broad discovery); /align focuses on whether your initiatives are pulling in the same direction and have synergies with other company groups. Run ad-hoc or before key decisions.
Autonomously optimize any Agent skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoeval on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
Draft the weekly plan — top 3 priorities, meeting triage, daily pre-plans, risks, and success metrics. Run on Monday morning. Creates the week scratchpad that /today reads all week.
Sharpen a product idea into a discovery-ready opportunity brief through critical questioning, strategic framing, and hypothesis formulation. Used by PMs to define the opportunity space before committing to solution work.
Weekly company Slack digest — chief-of-staff style. Scans the past 7 days of broad Slack activity and surfaces: goal-relevant discussions, crossover threads, water-cooler connection opportunities, provocations (things moving without your input), and backlog triggers (dormant initiatives that current Slack activity could re-activate). Designed to surface what a great chief-of-staff would bring unprompted. Run every Monday morning. Trigger on: 'weekly pulse', 'company digest', 'what's happening across the org', 'water cooler', 'run pulse', '/pulse', 'morning briefing', 'what did I miss this week', 'check my backlog against Slack'.
Weekly skill maintenance — mine corrections, identify underperforming skills, run bounded autoeval loops, and report improvements. The weekly wrap equivalent for skill quality. Run on Friday or Monday.
On-demand bias audit — check a decision, plan, or situation against your Marlee motivational profile blind spots
Draft content in your voice — emails, Slack messages, strategy docs, posts
Pre-flight checklist before human EPD review. Catches missing elements so reviewers don't waste time on incomplete docs.
Sync a PRD after prototype changes — updates scope, features, golden examples, and changelog to keep the PRD as a living document.
Fetch and triage unactioned Slack messages — classify as Tonight (time-sensitive) or Tomorrow (can wait). Use when asked to check unread messages, triage Slack, or see what needs attention.
Diagnose a stalled task and suggest the smallest next action to get it moving
Stress-test any product document (PRD, strategy doc, initiative, goal, pitch deck) using tailored critique lenses grounded in Lenny's Newsletter and Podcast content. Use when the user asks for a steelman, blind spot hunt, stress test, alternative framing, or exec-readiness review.
Audit and repair cross-references in this personal-agent workspace. Use this skill whenever the user asks to "check links", "audit references", "connect files", "fix orphaned files", or wants to make sure everything is discoverable. Also trigger for "make sure everything is connected", "are there broken links", "tidy up the workspace", or "audit my tasks/context/docs". Unlike a generic vault auditor, this skill understands the two-hub structure of personal-agent: AGENTS.md governs Context/ docs, and Weekly Kanban.md governs Tasks/. It skips Tasks/Done/ (archived), BACKLOG.md (raw inbox), and .gitkeep files.
Run a structured onboarding interview to populate GOALS.md with goals and profile context