Tip · Prompting
Correct with 'No, what I meant was…'
When Claude misunderstood, lead the correction with 'No, what I meant was…' — it's shorter than re-explaining everything and Claude takes the cue cleanly.
Tips
Patterns I keep reaching for
, gotchas, and workflow recipes — clustered by theme so you can skim the area you need. Opinionated and plainspoken.
Prompting
How to ask — phrasing, structure, what to include.
-
-
Tip · Prompting
Any output can level up into an interactive page — one sentence does it
The upgrade that works on every report, CSV, or checklist Claude produces — "turn this into a single self-contained interactive HTML file I can open by double-clicking." No server, no installs, no IT ticket; the file travels by email and opens in any browser.
-
Tip · Prompting
Bad vs. good openers
A useful names the file, the symptom, the repro, and the desired action. Vague prompts get vague results. The five-part shape gives Claude what it needs on the first try.
-
Tip · Prompting
Brief Claude like a colleague (the 5-line template)
A one-line gets one-line-quality work. Brief Claude with Role + Goal + Task + Constraints + Context — the same shape you'd hand a colleague who's helping with the task.
-
Tip · Prompting
Describe the business value, not the steps
Tell Claude what you want the outcome to be, not which functions to call. Claude is better at finding the right code path than you are at prescribing it.
-
Tip · Prompting
Iterate, don't restart
When Claude's answer is wrong, don't `/clear` and start over. Tell it what's wrong and let it adjust — you keep all the context you've already built up.
-
Tip · Prompting
One thing per prompt
A with five asks gets five mediocre answers. Break work into one focused step at a time, accept it, then move to the next.
-
Tip · Prompting
Pin the constraints, not the method
When you really do need to constrain Claude, pin the *requirements* (must run in under 200ms, must work offline, must not break the public ) — not the implementation choices Claude can pick freely.
-
Tip · Prompting
Show, don't describe
A screenshot of a broken UI beats four paragraphs of describing it. Drag the image into the — Claude will see what you see.
-
Tip · Prompting
"think harder" and `/effort` — turn up the reasoning when it matters
Drop "think harder" or "ultrathink" into a and Claude reasons longer before answering. Use `/effort max` for hard debugging, architecture decisions, or anything where speed matters less than getting it right.
-
Tip · Prompting
Prompt in Greek (or any language) — Claude understands
Claude is multilingual. in Greek when it's the language you can think in most clearly. The replies in the language you wrote — and code/identifiers stay in English, which is exactly what you want.
Control keys
The keystrokes and modes that put you back in the driver seat — stop, undo, switch what Claude is allowed to do.
-
Tip · Control keys
`--dangerously-skip-permissions` — what it actually does
The flag the team uses as its default Day-1 launch command. Skips read/ permission but does NOT skip code-edit reviews. Knowing the precise boundary defuses the "wait, isn't this dangerous?" anxiety.
-
Tip · Control keys
Esc to stop Claude mid-action (the control key)
When Claude is going down the wrong path, press Esc to halt it immediately. This single key prevents most "Claude just deleted everything" horror stories.
-
Tip · Control keys
Permission modes — what Shift+Tab toggles
Press Shift+Tab in the to cycle Claude's permission mode between default (confirm everything), auto-accept edits (just watch), and plan mode (read-only). Saves dozens of confirmations once you trust the plan.
Workflow & commands
How to drive Claude Code — plan-first, slash commands, sessions, subagents, hooks. The shortcuts that compound.
-
Tip · Workflow & commands
Don't check Claude's work by hand — make it prove it
The strongest verification habit in the hub — after Claude produces an output, ask it to verify its own work with real commands (grep the quotes, recompute the sums, re-run the logic) and show you the output. Commands either pass or fail; assurances always pass.
-
Tip · Workflow & commands
Two skills worth knowing — `/team` for one sitting, `gsd-*` for the long haul
Once you're past the plain- basics, the next decision is which orchestrator to reach for. /team runs a feature end-to-end in one sitting. -* manages a multi-week project with persistent state. Pick by horizon, not by ambition.
-
Tip · Workflow & commands
`@file` and `!command` — two prompt shortcuts every newcomer misses
Type `@` to reference a file by path (autocompletes), `!` to run a and embed its output. Both go straight into the . They cut the "let me copy this in" loop entirely.
-
Tip · Workflow & commands
When Claude does something wrong, add a line to CLAUDE.md
Boris Cherny's ('s creator) golden rule — every time Claude makes the same mistake twice, add a one-liner to so it doesn't make it a third time. The file grows as your project's tribal knowledge gets written down.
-
Tip · Workflow & commands
Install `gh` (and other CLIs) — Claude knows how to use them
Claude is fluent with tools like ``, `az`, `aws`, `jq`, ``. Install them, log in once, and Claude can read , query Azure resources, inspect — without a single server.
-
Tip · Workflow & commands
Hooks for the non-negotiables — CLAUDE.md only asks nicely
is advisory — Claude follows it about 80% of the time. are deterministic — they run every time, no exceptions. If something must happen 100% of the time (lint, security check, format), make it a hook.
-
Tip · Workflow & commands
One session, one task — don't pile work into a long conversation
Long mixed-topic sessions confuse Claude and burn context. Finish the auth refactor, then `/clear` and start the cart bug fresh. Sessions are cheap; misremembering isn't.
-
Tip · Workflow & commands
Plan first, then execute — the workflow that pays for itself
The single biggest mistake newcomers make is letting Claude jump straight into coding. Use plan mode to align on the approach first; the code you don't have to undo is the cheapest code you'll ever write.
-
Tip · Workflow & commands
Resume yesterday's session instead of starting from scratch
You don't have to lose context overnight. `claude --continue` picks up your last session; `claude --resume` opens a session picker. The codebase knowledge Claude built up is worth more than the 30 seconds of re-grounding.
-
Tip · Workflow & commands
Custom slash commands — turn repeated workflows into one keystroke
If you find yourself typing the same three times, write it as a custom . Drop a file in `.claude/commands/`, invoke with `/yourname`. it and the whole team gets the shortcut.
-
Tip · Workflow & commands
Subagents — delegate the file-reading so your main session stays clean
A subagent runs in its own , does its exploration, and reports a summary. Your main session never loads the 40 files it had to read. Best for research-heavy tasks where the input is large and the answer is small.
Context discipline
Keeping Claude focused — what stays in the conversation, what should be cleared.
-
Tip · Context discipline
What a real CLAUDE.md looks like (worked example)
A worked example of a project-level , distilled from 's official guidance, Karpathy's viral behavioral rules, HumanLayer's "under 60 lines" guide, and the awesome-claude- curated index. Each section is annotated with why it earns its slot.
-
Tip · Context discipline
/compact and /clear — context-window discipline
Don't carry irrelevant history. Use `/compact` to summarise the conversation when staying on-task, `/clear` to wipe and start fresh when switching tasks.
-
Tip · Context discipline
Keep CLAUDE.md clean and your project tidy — why Claude hallucinates without project hygiene
When Claude starts making things up, the bug is almost always in your project, not the . Stale sections, leftover scratch files, orphaned READMEs — Claude reads everything and the noise leaks into its answers.
Compliance & safety
Working with bank data and external services — what is allowed and what is not.
-
Tip · Compliance & safety
Always look at the diff before you accept
Claude is fast and capable — treat it like a brilliant junior. Read what it's about to change before saying yes. Skipping the diff review is the most expensive habit a newcomer can pick up.
-
Tip · Compliance & safety
Real bank data at runtime: Azure OpenAI only
If a tool will process real bank data at runtime, its calls MUST go through Azure OpenAI. The public and Gemini are off-limits for real customer data. This is data-residency, not a preference.