Trim the instructions your model outgrew
Audit Claude Code instructions, preserve project requirements, and test a smaller setup against the work you already trust.
09/15/26 instruction filesClaude CodeverificationThe whole catalogue
All guides
Make skills improve after each run
Use failed runs to repair skill descriptions, scripts, and checks. Test each change before keeping it, with Harness Firmware as a working example.
09/13/26 skillsverificationinstruction filesCompare AI agents on your own work
Compare agents on one repeatable task, check the tools each can use, and keep your skills usable when you switch.
09/12/26 model choiceskillsverificationinstruction filesLearn a work skill with AI
Choose a task you need to do, learn from checked sources, then test your understanding by doing the work and explaining your decisions.
09/10/26 careerknowledge basesverificationSet up an AI that knows your business
An AI operating system is a folder of files your agent reads before every message. The four parts it needs, in build order, and the habits that fill it from your head.
09/07/26 knowledge basesinstruction filesCodexKeep Claude automations working
Turn a tested task into a reusable skill, choose where it runs, and catch failed work before it wastes more time.
09/07/26 automationskillsverificationMove design work into Claude Design
Claude Design asks the questions a designer would, keeps your colors and fonts in a design system your whole team reuses, and fixes whatever a teammate circles in a comment. When it beats a plain chat, and the path from brand system to finished asset.
08/28/26 designteamsTake a problem apart before AI solves it
A language model reaches for the most familiar answer, and the better it sounds the less you check. Four staged prompts force the opposite: break the problem into parts, sort facts from assumptions, recombine the checked parts, and design cheap tests. You keep the judgment.
08/27/26 writing promptsplanningAudit what your agent saved to memory
Theo let Claude Code save memories on its own, then audited them: 45 files, written three times more often than read, most never opened again. How to run the same audit on your machine, the three ways saved memories rot, the ladder that finds a better home for each lesson, and what a harness built to pass the audit looks like.
08/25/26 memoryinstruction filesClaude CodeFour shapes an AI workflow can take
Agent workflows run one step after another by default, which is the slowest shape. Ask at each step whether it needs the result of the step before it, then re-shape the work: fan out independent steps, route requests down branches, loop until a check passes, and cap what each shape can waste.
08/20/26 automationplanningcost controlOne skills library for your whole team
Skills built on one person's machine stay there, and the copies you send around go stale the moment anyone edits one. Put the team's skills in one GitHub repository, install it as a plugin, and every edit reaches every teammate's agent.
08/19/26 skillsteamsFour steps from chatting to hands-off AI
Boris Cherny, who created Claude Code, maps four steps between chatting with an AI and a system that starts work you never assigned. Find your step from the bottleneck you feel, and make the one change that moves you up.
08/17/26 delegationautomationMake your agents proactive
Allie K. Miller runs 34 AI agents, and her day is reviewing what they propose, deciding, and handling escalations. What an agent needs before it can start work you never assigned (written goals, fresh context, tools, triggers), the four-stage ramp from one agent to a workforce, and the watchdog jobs worth assigning first.
08/12/26 delegationteamsautomationGrok Bot runs a team of always-on agents
Grok Bot, the new beta app from SpaceXAI and Cursor, gives you a team of AI agents that keep working with your laptop shut, each on its own cloud computer. How work gets routed between them, how recorded skills and triggered routines run themselves, and which work should stay at your desk.
08/11/26 automationdelegationteamsBuild an agent that finds your customers
Cody Schneider builds agents that find leads and post content while nobody watches. The method: turn the human process into scripts on a schedule, and call the model only where a judgment is needed. Both of his builds, tool by tool.
08/05/26 automationcost controlClaude CodeOne chat can run all your other chats
In ChatGPT, any chat can search every other chat, send work into them, and collect the results. How to find a lost conversation by asking, delegate work between chats, publish a result to a shareable page, and reach it all from your phone.
08/05/26 delegationcost controlCodexRehearse the interview with an AI coach
Nearly everyone gets anxious before a job interview, and practicing out loud is what lowers it. Give an agent the real documents, a skeptical interviewer to play, and your voice, then have it break character and coach you.
08/04/26 careerDelegate to your agent in stages
A new agent should not run your inbox on day one. Give it one job with read-and-draft access only, check its work until your corrections stop, then add the next tool, and let it run unattended only after it has earned that.
08/04/26 delegationagent safetyBuzz puts AI agents in your team chat
Buzz is an open-source team chat from Jack Dorsey's Block where AI agents are members of the channel. What that buys you (swap the model, keep the context), what it can already do, and whether your team should try it yet.
08/04/26 teamsmodel choiceAssume your agent uses every tool it has
An agent sent a discount code to 150,000 people because a to-do item looked like an instruction. A rule in the prompt is a suggestion; a rule built into the tools is a restriction. Scope every key to the least the task needs.
08/04/26 agent safetydelegationScore your agent on known good answers
One successful run proves an agent worked once. Collect real examples with answers a person already judged good, grade each run with a script or a judging model, and rerun the set after every change so you know whether it helped.
08/04/26 verificationSplit big AI tasks into steps and checks
One big question in one chat makes the model decide, research, write, and grade itself in a single pass. Map the work instead: parallel research jobs, a checker that did not write the answer, a merge, and your approval before anything expensive.
08/03/26 planningdelegationverificationWhat still pays when AI does the work
When a model can finish the task in minutes, what people will pay you for changes: choosing the task well, doing things others do not know AI can do, feeding your results back into your tools, and proving you can deliver.
08/03/26 careerDefend your agent from prompt injection
Anything your agent reads (a web page, a resume, a calendar invite) can carry hidden instructions it will follow. Why the attack has no clean fix, and the five defense layers that shrink what a successful one can do.
08/03/26 agent safetyWhy AI makes slop and how to catch it
Models got good where the work grades itself, and they aim at the most likely answer, which in design and writing is the average one. The fix: break your quality standard into checkable rules and keep human judgment for taste.
07/31/26 model behaviorverificationLoop the agent until the work passes
A rerun loop makes the agent redo its own work until a check passes. Script the repetitive half of a skill, end it with a pass or fail verdict, wrap both in a loop, and keep a human at the checkpoints where errors are expensive.
07/23/26 automationverificationKeep a growing knowledge base accurate
Wrong agent answers usually trace to the files the agent reads. The four ways a growing knowledge base drifts from reality, and the habits (a router file, read-only audits, scheduled pulls, backtracking) that catch the drift.
07/23/26 knowledge basesverificationPower start sessions with /enhance-prompt
An enhance-prompt skill turns a rough request into the full prompt the model will actually run, and shows it to you first. Reading that rewrite catches misunderstandings before any work starts.
07/22/26 writing promptsplanningTurn repeated fixes into rules
When an agent hits the same problem twice, encode the fix as a lint rule, CI check, or steering-file instruction that every future session inherits.
07/21/26 instruction filesautomationClaude CodeAutomate a workflow as a Claude routine
A routine is a saved instruction Claude runs on its own, on a schedule or an incoming signal. What it replaces, and why an unattended run has to be written tighter than one you watch.
07/19/26 automationSharpen the prompt or brainstorm first
Two ways to start an AI task: deepen a rough prompt when you know the goal, or brainstorm first when the goal or the tradeoffs are still open. A quick test for which one you are in.
07/19/26 writing promptsplanningBuild a knowledge base your team can ask
Retrieval augmented generation in plain terms: put the relevant facts in front of the question. How to feed the chat, docs, and code your team already uses into a knowledge base anyone can ask, and why weighting beats volume.
07/19/26 knowledge basesteamsRecheck your model choices each release
When a new model family ships, treat your routing as expired. Re-measure which size and effort give the most score per dollar, spot the size you can skip, and drop the speed modes that do not pay.
07/19/26 model choicecost controlCodexJudge whether AI has original ideas
Whether AI can have original ideas is a debate that keeps moving the goalposts. A way to judge it honestly: read the trend line, and see why learning to predict text can build real understanding.
07/19/26 model behaviorStop hitting your token limit
Your limit is a compute budget: tokens consumed times the model that reads them. Audit where a session spends, trim the context every chat preloads, and send grunt work to cheaper models so the budget lasts the day.
07/18/26 cost controlClaude CodeThe design concept does the work
The prompt and the reusable skill file behind the about page on this site, with the reason each part earns its place.
07/18/26 skillsAutomate the step that slows you down
Automating the bottleneck means finding the constraint that sets your pace and pointing Claude at it: four working rules distilled from Anthropic's own engineers.
07/18/26 automationverificationClaude CodeClaude and OpenAI, one prompting playbook
OpenAI and Anthropic prompting guides are one playbook when read side by side: lean out the prompt. Where they converge, where they diverge, which habits to drop.
07/17/26 writing promptsGive your agent a memory
A memory store is a workspace-scoped directory your agent reads and writes with normal file tools, carrying preferences and prior mistakes across sessions.
07/17/26 memoryGuardrails for hours-long agent runs
Guardrails are the support structure that keeps an hours-long agent run honest: an audit instruction, a memory that survives resets, and fresh-eyed verifiers.
07/17/26 verificationmemoryagent safetyStop shouting at the model
The newest Claude models are highly responsive to system prompts, so shouting backfires: soften trigger language, migrate deprecated levers, keep the model in bounds.
07/17/26 writing promptsBrief the model like a brilliant new hire
Claude is a brilliant new hire with no context on your job. Brief it like one: explicit instructions with motivation, examples, XML tags, roles, and context ordering.
07/17/26 writing promptsThe new Claude lineup and what it breaks
Claude's July 2026 lineup is four models: Fable 5, Glasswing-gated Mythos 5, Sonnet 5 at intro pricing, and Opus 4.8, plus the three migration changes that bite.
07/17/26 model choicemodel behaviorEvery new repo starts with your lessons
AI Firmware is a boot layer of kernel rules, installable skills, and committed memory that makes every new agent repo start senior instead of relearning old lessons.
07/17/26 instruction filesskillsClaude CodeCodexThinking on a budget
Reasoning tokens are billed at the output rate and re-read every turn after. How to compress what a model says without compressing what it knows.
07/17/26 cost controlExpertise you can install
A skill file is career-long judgment packaged as instructions your agent can run. How to adopt someone's method, and why you scan it like untrusted input first.
07/17/26 skillsagent safetyCapture the model's discipline
Models get repriced, capped, and retired; their way of working can be kept. Extract the top model's discipline into skill files, routing tables, and planner-and-worker setups any model can run.
07/17/26 skillsmodel choice