Skip to content

Prompt Library

These are session-scoped starting points, not durable truth. Fill the <placeholders>, paste into Claude Code (plan mode first for anything that touches architecture or more than a handful of files), then evaluate the output against the criteria on each entry. If you find yourself re-pasting the same constraints twice, escalate them into a file — see Prompts vs Specs.

How to pick a prompt

You need to…Start here
Start a project, clarify product, plan architecture, decompose workProject & Planning
Design schema, API, UI, ADRs, threat modelDesign
Implement a feature, backend, UI, walking skeletonImplementation
Review, test, attack, fix types/lintQuality
Debug, refactor, migrate, understand legacyMaintenance
Docs sync, deploy, CI/CD, runbooks, observabilityOperations
Multi-agent briefs, handoffs, recover from bad outputAgent Management

Match the job, not the tool. "Write some code" is almost always Implementation or Maintenance; "is this safe to ship?" is Quality or Operations.

How to fill inputs

  1. Replace every <angle bracket> with a concrete value — file paths, branch names, acceptance criteria, out-of-scope lists. Leaving a placeholder is worse than a weak prompt: the agent invents a confident-looking fill.
  2. Prefer paths over adjectives. Follow src/routes/invoices.ts beats "idiomatic Express."
  3. Paste or @-reference the real files Claude Code should read. Don't summarize what the agent can open.
  4. Keep durable decisions out of the prompt body when they already live in CLAUDE.md, a spec, or an ADR — point at those files instead. See Prompt Anatomy.

How to evaluate

Each entry has an Evaluate section. Use it as a gate before you accept the diff or continue the session. Minimum bar for any prompt:

  • [ ] Output matches the Expected output shape (not a surprise artifact type)
  • [ ] Scope stayed inside the stated files / non-goals
  • [ ] Ambiguities were surfaced, not silently resolved
  • [ ] You can name the acceptance criteria that are still unmet

If evaluation fails, don't "nudge" with a vague follow-up — use Recover from bad output or open a fresh session with a tighter prompt.

When to customize

Customize when the stock prompt's assumptions don't match your stack, risk, or team process. Keep the structure (context → behavior → constraints → acceptance → out of scope); swap the domain details. Do not customize by deleting constraints to "let the agent be creative" — that reintroduces the six-silent-decisions problem.

Escalate to a committed spec when: the task spans more than one session, another human will pick it up, or the acceptance criteria are load-bearing for production. Prompts stay as pointers; specs carry truth (Specs over Prompts).

Categories

CategoryWhat it's for
Project & PlanningInit, clarification, research, decomposition, handoff
DesignSchema, API, UI, ADRs, options, threat model
ImplementationFeature/backend/UI build patterns that constrain scope
QualityReview, security, perf, tests, adversarial attack
MaintenanceDebug, debt, refactor-with-frozen-behavior, migration
OperationsDocs, deploy, CI/CD, release, runbook, readiness
Agent ManagementMulti-agent briefs, resets, recovery, reconciliation

A field manual for AI-native software engineering.