Skill Claude CodeCodex
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Skill Claude CodeCodex
Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
Skill Claude CodeCodex
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
Skill Claude CodeCodex
Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
Skill Claude CodeCodex
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'.
Skill Claude CodeCodex
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
Skill Claude CodeCodex
Make a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.
Skill Claude CodeCodex
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping…
Skill Claude CodeCodex
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, and Global English syntax. Use when writing, editing, or reviewing docs, READMEs, AGENTS.md or CLAUDE.md files, skill or agent prompts, RFCs, design docs, runbooks, code comments, PR descriptions, or commit…
Skill Claude CodeCodex
Draft a brief GitHub issue (bug, feature, or task) that a maintainer can read in under a minute. Searches for duplicates, checks claims against the code, runs the repro when one exists, drafts from the repository issue template (or a short default), cuts it to fit, verifies accuracy, then applies the technical-writing…
Skill Claude CodeCodex
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Skill Claude CodeCodex
Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
Skill Claude CodeCodex
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Skill Claude CodeCodex
Review the active session transcript for durable learnings and route each one to a concrete edit on an existing catalog skill, a description fix, or a backlog item. Use when the user says reflect or /reflect.
Skill Claude CodeCodex
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
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: