Skill Claude CodeCodex
Use when work changes or evaluates load-bearing authority, ownership, public or persisted contracts, dependency boundaries, migration/cutover, recovery, guards, or structural deletion.
Installable AI coding workflow for risk-based routing, scoped sub-agents, and evidence-backed completion.
Skill Claude CodeCodex
Use when work changes or evaluates load-bearing authority, ownership, public or persisted contracts, dependency boundaries, migration/cutover, recovery, guards, or structural deletion.
Skill Claude CodeCodex
Use when writing or designing code: name premise and blast radius, deepen modules at seams, TDD at agreed seams, diagnose before patching, and keep producer→consumer contracts honest.
Skill Claude CodeCodex
Use when repo terms or invariants are drifting, or when user/docs/code naming disagrees and a canonical glossary is needed — .do-it/CONTEXT.md is the downstream source of truth for names, relationships, and facts.
Skill Claude CodeCodex
Use when starting non-trivial repo work or making a done/fixed/ready/merge claim: apply the universal evidence, scope, boundary, recovery, verification, and reporting rules.
Skill Claude CodeCodex
Use when premises or options must be pressure-tested, a short plan/handoff is needed, or a large plan must be sliced — grill facts locally, ask decisions one at a time.
Skill Claude CodeCodex
Use when a project needs a lean .do-it/handbook/ for stable project truth plus .do-it/worklog/ for daily or goal notes.
Skill Claude CodeCodex
Use only when the user explicitly asks to enable, disable, inspect, report, or persist opt-in local do-it behavioral feedback.
Skill Claude CodeCodex
Use when a diff needs PR-style review, or findings need atomic repair and same-scope re-review — Standards axis and Spec axis, kept separate.
Skill Claude CodeCodex
Use when starting any non-trivial repo task: pick Light / Standard / Heavy tier, then self-select meaning skills — not a fixed pipeline.
Skill Claude CodeCodex
Use when creating or updating do-it skills: write predictable model-invoked descriptions, progressive disclosure, leading words, and hook-aware escape behavior.
Skill Claude CodeCodex
Use before any done, fixed, passing, ready, install, or merge claim, and when closing a branch — fresh evidence on this worktree; hooks vary by host, this skill is the checklist.