Best Claude skills for productivity
Productivity skills change how your agent works with you: shorter answers, persistent memory across sessions, file-based plans that survive crashes, and tools for notes apps like Obsidian. Caveman, which cuts output tokens dramatically, is one of the most installed skills anywhere.
624 productivity skills · ranked live · November 2026
The top 10. Ranked by the Alyn Score.
- 1#1
- 2#2
Matt Pocock
Writing For Agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
Pack321k33MScore 95 - 3#3
affaan-m
Agent Self Evaluation
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion…
Pack301k1.7MScore 93 - 4#4
Chief Of Staff
Pursue a long-running goal in a single session by co-ordinating subagents.
Pack321k33MScore 93 - 5#5
JuliusBrussee
Caveman Learn
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's…
Pack119k4.8MScore 90 - 6#6
Agent Architecture Audit
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering…
Pack301k1.7MScore 89 - 7#7
Agent Payment X402
Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent…
Pack301k1.7MScore 89 - 8#8
Caveman Compress
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger…
Pack119k4.8MScore 89 - 9#9
Caveman Setup
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Pack119k4.8MScore 88 - 10#10
Corey Haines
Marketingskills
Corey Haines
Cold Email
When the user wants to write or run B2B cold outbound, or asks whether an opener, reason to reach out, or email works or why nobody replies: cold emails, follow-ups, sending domains…
Pack60k6.3MScore 88
What makes a great productivity skill.
Measurable savings (tokens, time) rather than vague promises.
Plain files you own (Markdown) instead of lock-in.
Easy to turn off when you need detail.
All 624 productivity skills.
zubair-trabzada
AI Marketing Claude
zubair-trabzadamarket-emails
You are the email marketing engine for /market emails <topic/url. You generate complete, ready-to-send email sequences with subject lines, body copy, timing, and segmentation strategies…
zubair-trabzada
AI Marketing Claude
zubair-trabzadamarket-launch
1. What are you launching? (product, service, feature, course, event) 2. Who is the target audience? (demographics, pain points, existing list size) 3. What is the primary launch goal?…
zubair-trabzada
AI Sales Team Claude
zubair-trabzadasales
You are a comprehensive AI sales intelligence and outreach system for Claude Code. You help founders, sales teams, agency owners, and solopreneurs research prospects, qualify leads…
zubair-trabzada
AI Sales Team Claude
zubair-trabzadasales-followup
You generate strategic follow-up email sequences for prospects after initial contact has been made. This is NOT cold outreach — these are follow-ups after a meeting, demo, proposal, or…
zubair-trabzada
AI Sales Team Claude
zubair-trabzadasales-objections
You generate comprehensive objection response scripts that salespeople can use in real-time during calls, meetings, and email exchanges. Every objection response is word-for-word ready to…
Matt Pocockgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Matt Pocockto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Matt Pocockclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
affaan-magent-security-hardening
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building…
affaan-magentic-os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management…
affaan-marchitecture-decision-records
Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an index README. Use when the user says 'record this…
affaan-mautonomous-agent-harness
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes…
Matt Pocockgrill-me
A relentless interview to sharpen a plan or design.
Matt Pocockhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Matt Pocockwait-what
Stop. That last message did not land: re-pitch it.
affaan-magent-runtime-gateway-smoke-test
Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.
affaan-magentic-engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.
affaan-mblueprint
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects: one-PR-sized steps with self-contained context briefs, dependency graph…
Corey Haines
Marketingskills
Corey Hainesrevops
When the user wants to design revenue operations, or asks when a lead is ready for sales or why sales and marketing disagree on lead quality: lifecycle stages, MQL and SQL, scoring…
Corey Haines
Marketingskills
Corey Hainessms
When the user wants SMS, MMS, or WhatsApp marketing, or asks whether texting is worth it or a message is allowed: abandoned cart, win-back, and promo texts, WhatsApp templates and windows…
affaan-magent-eval
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or…
JuliusBrusseecaveman-discover
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
JuliusBrusseecaveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or…
JuliusBrusseecaveman-optimize
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs…
JuliusBrusseecavecrew
When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output…
JuliusBrusseecaveman-evidence-review
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
JuliusBrusseecaveman-explore
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns…
JuliusBrusseecaveman-manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
JuliusBrusseecaveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
JuliusBrusseecaveman-help
Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
JuliusBrusseecaveman-review
Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
JuliusBrusseemegacave
Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until "stop caveman" or "normal mode".
JuliusBrusseeultracave
Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".
JuliusBrusseecaveman-stats
Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.
JuliusBrusseelean-build
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
JuliusBrusseeinvestigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Productivity skills, explained.
Also searched as: productivity skills, obsidian skills, planning skill, memory skill claude, caveman skill.
What are the best Claude skills for productivity?
Right now the top-ranked productivity skills on Alyn are Teach (Matt Pocock), Writing For Agents (Matt Pocock), Agent Self Evaluation (affaan-m). Rankings combine GitHub stars, installs, freshness and depth, and update live.
What is the Caveman skill?
A viral skill and proxy by JuliusBrussee that makes coding agents answer in far fewer tokens. Its motto: "why use many token when few token do trick."
Are there official Obsidian skills?
kepano/obsidian-skills is published by Obsidian's CEO and covers Markdown, Bases, JSON Canvas and the Obsidian CLI.
How do I install a productivity skill?
Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.
More in Work & life
Productivity skills for your agent