← ClaudeAtlas

never-twicelisted

Load at the start of every task and before every answer that recommends something, states a status, or says "done". It keeps a shared error log (ERRORS.md) so the same mistake never happens twice across sessions: read the log for the task's topic first, verify before claiming, think the whole plan before writing it, show real evidence before saying done, and log every new mistake with the rule that prevents it. Triggers on "no errors", "sin errores", "don't make mistakes", "get it right", "be perfect", or any task where a wrong answer costs the user time or money.
RabbitDesigns22/claude-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill RabbitDesigns22/claude-skills
# Never twice No method makes an agent perfect. This one gets as close as it can with three promises: 1. **The same mistake never happens twice.** 2. **Nothing is claimed without checking it.** 3. **Every answer is the final answer.** No "first this, then actually that". ## The error log Keep one file that every session can read, for example `ERRORS.md` at the root of the workspace. One line per mistake: ``` - YYYY-MM-DD · TOPIC · what happened · root cause · RULE so it never happens again ``` Example lines: ``` - 2026-11-05 · UI LABELS · "Closed sales" also counted booked calls · the label did not say what it counted · RULE: every metric label says exactly what it counts. - 2026-11-05 · STATUS SCREENS · Explained "(UNKNOWN)" as "not registered"; it was the quality rating · guessed from the screen · RULE: before explaining a field, find in the code what renders it. ``` ## Step 1. Before starting: read the mistakes for this topic - Search the log for the task's topic (client, product, platform, tool). Every matching line is a rule for this task. - Also read what was already decided: project notes, client files, memory. ## Step 2. Verify before deciding - Every fact you use (number, ID, price, name, status, what a field means) comes from the source: code, live page, API, file, screenshot. Never from memory. - If a fact cannot be checked and it changes the decision, find a way to check it first. If there is none, say "not verified" once, and say how it will be known. #