Run meta-overlord in Codex. Trigger: meta-overlord.
原文语言:英语
菜单
这个仓库中的 skills
SkillsMP 已收集 ansonphong/meta-dev 中的 67 个 Skill。打开任一 Skill 可查看来源和详情。
ansonphong/meta-dev已展示 27 / 67 个已收集 Skill。
Run meta-overlord in Codex. Trigger: meta-overlord.
原文语言:英语
Run meta-planner in Codex. Trigger: meta-planner.
原文语言:英语
Run meta-probe in Codex. Trigger: meta-probe.
原文语言:英语
Run meta-repair in Codex. Trigger: meta-repair.
原文语言:英语
Run meta-review-batch in Codex. Trigger: meta-review-batch.
原文语言:英语
Run meta-review-design in Codex. Trigger: meta-review-design.
原文语言:英语
Run meta-security in Codex. Trigger: meta-security.
原文语言:英语
Run meta-sweep in Codex. Trigger: meta-sweep.
原文语言:英语
Run meta-ux in Codex. Trigger: meta-ux.
原文语言:英语
Run meta-version in Codex. Trigger: meta-version.
原文语言:英语
Run meta-visual-critique in Codex. Trigger: meta-visual-critique.
原文语言:英语
Run opus-execute in Codex. Trigger: opus-execute.
原文语言:英语
Write and save a self-contained implementation plan for a fresh agent. Use for plan requests, medium changes, or implementation planning before code.
原文语言:英语
Coordinate related plans through a campaign runbook.
原文语言:英语
Run sonnet-execute in Codex. Trigger: sonnet-execute.
原文语言:英语
Diagnose a focused failure and preserve evidence.
原文语言:英语
Stress-test a plan before execution.
原文语言:英语
Review a scoped change through the shared protocol.
原文语言:英语
Batch engineering changelog. Append entries during work, cut on demand or auto-threshold, draft release post, pair with version bump.
原文语言:英语
Design quality rubric scoring — evaluates implementation against design doc on 4 dimensions
原文语言:英语
Generate definition-of-done contracts from task descriptions. Output structured acceptance criteria, test plan, rollback strategy, and blast radius.
原文语言:英语
Patterns for headless Claude execution via claude -p --output-format json. Tool allowlist tiers, env inheritance, model override for Sonnet routing.
原文语言:英语
Judgment-based plan quality checks — cross-reference integrity, dependency ordering, contract completeness, terminology consistency
原文语言:英语
Attempt auto-fix with 3-attempt cap, smallest-fix-first strategy, failure dossier to inbox. Use when verify step fails.
原文语言:英语
Grug-brain sniff test for plans AND code — detect over-engineering, complexity demons, vague tasks, and bad practices in plans/specs (primary) or code (secondary). Report-only, never edits. Invoked as /sniff-test. By default sniffs the subject under…
原文语言:英语
Multi-repo, context-aware versioning. Declarative config, semver/calver/custom strategies, follows cascades, atomic version_files updates.
原文语言:英语
Stand up and maintain a visible stage-level task list for the /meta-dev 6-stage waterfall. Use in autopilot/walk runs so the user can walk away and watch Brainstorm→Design→Plan→Harden→Execute→Review progress live. Stage granularity only — never mirrors…
原文语言:英语