Skill Claude CodeCodex
Part of loopkit
Write safe, reversible database migrations for this repo's conventions. Use for any schema change.
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI).
Skill Claude CodeCodex
Part of loopkit
Write safe, reversible database migrations for this repo's conventions. Use for any schema change.
Skill Claude CodeCodex
Part of loopkit
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
Skill Claude CodeCodex
Part of loopkit
Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.
Skill Claude CodeCodex
Part of loopkit
Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.
Skill Claude CodeCodex
Part of loopkit
Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
Skill Claude CodeCodex
Part of loopkit
Write a PR description a reviewer can approve fast. Use when opening any pull request.
Skill Claude CodeCodex
Part of loopkit
Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under a minute.
Skill Claude CodeCodex
Part of loopkit
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. Use when the system prompt, tool defs, or reference docs are stable across many turns.
Skill Claude CodeCodex
Part of loopkit
Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
Skill Claude CodeCodex
Part of loopkit
Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.
Skill Claude CodeCodex
Part of loopkit
Rebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.
Skill Claude CodeCodex
Part of loopkit
Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.
Skill Claude CodeCodex
Part of loopkit
Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.
Skill Claude CodeCodex
Part of loopkit
Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.
Skill Claude CodeCodex
Part of loopkit
Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.
Skill Claude CodeCodex
Part of loopkit
Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.
Skill Claude CodeCodex
Part of loopkit
Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.
Skill Claude CodeCodex
Part of loopkit
Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.
Skill Claude CodeCodex
Part of loopkit
Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.
Skill Claude CodeCodex
Part of loopkit
Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. Turns fuzzy specs into a testable target the evaluator can hold the generator to.
Skill Claude CodeCodex
Part of loopkit
Review SQL and ORM queries for correctness, safety, and performance before they ship.
Skill Claude CodeCodex
Part of loopkit
Get JSON out of the model reliably. Prefer tooluse with a schema over prompted-JSON, validate on receive, retry on parse fail. Use when downstream code will parse the response.
Skill Claude CodeCodex
Part of loopkit
Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.
Skill Claude CodeCodex
Part of loopkit
Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so featurelist.json stays immutable.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: