~/ai · agents · prompts · verification

AI workflows, for the whole engineering loop.

Prompts, skills, commands, configs, and agent patterns for planning, coding, reviewing, debugging, documenting, and shipping with verification close to the code.

config

The CLAUDE.md that keeps agents grounded

A short project memory file for the stack, invariants, and the lines an agent must not cross.

CLAUDE.mdopen →
CLAUDE.md
// config
name: claude-md
description: earns its keep
steps: [ scope, run, verify ]
32 resources
Skills·Jun 18, 2026

Remove trivial tests before they harden

An agent skill for replacing shallow AI-written coverage with tests that can catch real regressions.

4 min read·SKILL.md·skills/remove-trivial-tests/SKILL.md
Commands·Jun 2, 2026

Verification gate before done

Run typecheck, lint, tests, API flow, and build; keep fixing until the repo agrees.

2 min read·command.md·commands/verify.md
Skills·Jun 1, 2026

Write tests that can actually fail

Behavior checks, negative cases, regression coverage, and cleanup that keeps the next run honest.

2 min read·SKILL.md·skills/writing-tests/SKILL.md
Commands·May 30, 2026

Security review of the actual diff

A read-only pass over dependency bumps, auth changes, and CI edits, with a fixed checklist and findings format.

2 min read·command.md·commands/security-review.md
Skills·May 29, 2026

UI verification with real browser evidence

Run user and guest flows, include hard refreshes, and keep screenshots as proof of what changed.

2 min read·SKILL.md·skills/ui-visual-verification/SKILL.md
Prompts·May 27, 2026

End-of-task reports that are useful later

A short closeout with changed files, commands and results, decisions made, and honest follow-up.

2 min read·prompt.md·commands/report.md
Skills·May 26, 2026

Root-cause investigation before edits

Find the exact source with file:line, name the systemic cause, and avoid masking symptoms with a patch.

2 min read·SKILL.md·skills/root-cause-investigation/SKILL.md
Commands·May 24, 2026

Plan before touching the code

For large or ambiguous work: inspect first, write the steps, ask the blocking questions, then execute.

2 min read·command.md·commands/plan.md
Skills·May 23, 2026

PHP to Python with golden-file parity

Move behavior across languages with fixture proof, uv tooling, and boring first-party libraries where they fit.

2 min read·SKILL.md·skills/php-to-python-migration/SKILL.md
Loops·May 21, 2026

Final cleanup pass before calling it done

Re-scan the whole project for leftovers, stale docs, missed simplifications, and rule violations.

2 min read·loop.md·commands/holistic-pass.md
Skills·May 20, 2026

Parallel agents with clean write scopes

Plan first, split the work into disjoint surfaces, fan out, then reconcile and verify the whole result.

2 min read·SKILL.md·skills/parallel-agent-execution/SKILL.md
Commands·May 18, 2026

Commit, push, and open the PR cleanly

Branch when needed, make one conventional commit, keep the PR scoped, and report the exact SHA.

2 min read·command.md·commands/commit-push-pr.md
Skills·May 17, 2026

Observability that makes failures inspectable

Traceable logs, level control, test ids where they help, and no silent failure paths.

2 min read·SKILL.md·skills/observability-and-logging/SKILL.md
Commands·May 15, 2026

Read-only audit with file:line findings

A strict no-write pass that reports one concrete finding per line, sorted by impact.

2 min read·command.md·commands/audit.md
Skills·May 14, 2026

Prove parity during a refactor

Capture reference behavior, separate public from internal fields, and make the new path match what matters.

2 min read·SKILL.md·skills/migration-parity-check/SKILL.md
Commands·May 12, 2026

Fix the whole pattern, not one instance

Find every occurrence, patch the full surface, and write the rule down so the drift does not come back.

2 min read·command.md·commands/apply-everywhere.md
Skills·May 11, 2026

Docs and diagrams before the work is done

Update the README, comments, Mermaid flows, and AGENTS.md decisions while the context is still fresh.

2 min read·SKILL.md·skills/docs-and-diagrams/SKILL.md
Agents·May 9, 2026

House rules agents can actually follow

The recurring repo rules — cleanup, stack, schemas, IDs, CI — written as constraints an agent can check.

8 min read·AGENTS.md·AGENTS.snippet.md
Skills·May 8, 2026

DaisyUI and Tailwind without visual drift

Use the real components, match the reference theme, and verify every page in light and dark.

2 min read·SKILL.md·skills/daisyui-design-conventions/SKILL.md
Prompts·May 7, 2026

Commit and PR text from the real diff

A conventional commit subject and PR body that say what changed, why it matters, and how it was checked.

2 min read·prompt.md·prompts/commit.md
Skills·May 5, 2026

Compress a worklog without losing signal

Turn messy session notes into a dense developer journal while preserving decisions, commands, and evidence.

2 min read·SKILL.md·skills/compress-worklog/SKILL.md
Commands·May 4, 2026

Add Discord notifications without breaking Slack

Find every Slack notification path, add the Discord twin, and keep the old channel working.

2 min read·command.md·commands/add-discord-notify.md
Workflows·Apr 22, 2026

Domain and TLS expiry watcher

A daily check that ranks domains and certificates by expiry, then keeps one rolling issue current.

2 min read·workflow.md·check-expiry.ts
Workflows·Apr 9, 2026

Dependency updates that only land green

A scheduled job bumps packages, runs the repo checks, and pushes only when the branch earns it.

2 min read·workflow.md·update-deps.ts
Configs·Apr 2, 2026

AGENTS.md as the house-style file

One place for toolchain, code style, and repo invariants, with every other agent note pointing back to it.

2 min read·CLAUDE.md·AGENTS.md
Workflows·Mar 18, 2026

Incident timelines while evidence is fresh

An agent follows logs and metrics during an incident so the timeline is accurate before context fades.

2 min read·workflow.md
Skills·Mar 17, 2026

Teach agents to read EXPLAIN

Give it the plan, get back the slow node, estimate drift, and the index worth testing.

2 min read·SKILL.md
Prompts·Mar 16, 2026

Staff-engineer review with a narrow charter

A terse review prompt for correctness, retry-safety, blast radius, and the smallest useful fix.

2 min read·prompt.md
Prompts·Mar 15, 2026

Postmortems from logs, not memory

Turn the incident channel and system evidence into a timeline that names systems, never people.

2 min read·prompt.md
Workflows·Mar 12, 2026

Spec, scaffold, then tests

Write the design first, let the agent scaffold the shape and failing tests, then fill in the logic.

2 min read·workflow.md
Skills·Mar 11, 2026

Gate production migrations before review

Block locking DDL, unsafe deploy order, and unbatched backfills before a human has to catch them.

2 min read·SKILL.md
Configs·Mar 6, 2026

design.md for keeping generated UI on-system

The short token and component contract that stops agent-built UI from drifting into visual noise.

2 min read·CLAUDE.md