Claude Skills by sd0xdev

Multi-target refactoring orchestrator. Use when: cleaning up messy code/docs, simplifying code, restructuring documents, batch cleanup. Not for: new features (use feature-dev), bug fixes (use bug-fix), code understanding (use code-explore). Output: refactored code/docs + review gate.

Lightweight model correction with context-aware rule loading. Use when: model forgot a rule, skipped a required step, edited code/docs without running review, needs to re-read CLAUDE.md or rules. Triggers on: 'you forgot', 'remind', 'check rules', 'what did you miss', '你忘了', 'did you skip review', 'why didn't you run precommit', or /remind. Also use PROACTIVELY after editing files if unsure whether auto-loop was followed — running /remind costs nothing and catches drift early. Not for: full c...

Requirements analysis — problem decomposition, stakeholder scan, requirement structuring. Produces 1-requirements.md (Phase 1 lifecycle doc, NOT the per-task request ticket — for those use /create-request). Use when: analyzing needs before tech spec, decomposing requirements, stakeholder analysis, 需求分析. Not for: solution comparison (use feasibility-study), tech design (use tech-spec), per-task tracking tickets (use create-request), issue root cause (use issue-analyze).

Review technical spec documents from completeness, feasibility, risk, and code consistency perspectives.

Uncommitted code risk assessment with breaking change detection, blast radius analysis, and scope metrics. Use when: evaluating PR risk, pre-commit risk check, large refactoring review. Not for: security vulnerabilities (use /codex-security), code correctness (use /codex-review-fast). Output: 3-dimension weighted score + risk level + gate.

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

Safely remove plugin assets (skill/agent/rule/script/hook) with dependency detection and reference cleanup. Use when: user says 'remove skill', 'delete skill', 'deprecate', 'clean up unused', or /safe-remove. Not for: code refactoring (use /simplify), feature removal requiring architecture changes (manual).

Independent second-opinion verification for any finding. Use when: Claude or user wants independent Codex verification of a review finding — dismiss (false positive check), confirm (does this issue exist?), or clarify (what's the impact?). Triggers: dismiss verification, seek verdict, verify dismiss, false positive check, second opinion, confirm finding, clarify impact. Not for: general code review (use codex-code-review), architecture debates (use codex-brainstorm). Output: [DISMISS_VERDICT]...

Replicate knowledge from any source as sd0x-dev-flow skill definition. Use when: copying skills from repos, adapting patterns from articles/papers/code, converting knowledge to skill format. Not for: research without skill output (use deep-research), creating skills from scratch (use skill-creator), project onboarding (use repo-intake). Output: analysis report + generated SKILL.md files with 3-layer validation.

Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior

Validate skill quality against routing, progressive loading, and verification criteria. Use when: auditing skills, checking skill health, reviewing skill design. Not for: code review (use codex-code-review) or doc review (use doc-review). Output: health report with per-skill ratings + Gate.

Smart batch commit. Analyzes uncommitted changes, groups by cohesion, generates commit messages matching project style. Default: output git commands for manual execution. With --execute: directly run git add + git commit (requires user approval). Use when: user says 'commit', 'batch commit', 'prepare commit', 'write commit message', or /smart-commit

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (use git directly), merge conflict resolution (use /merge-prep), branch switching (use git checkout). Output: rebase plan table + copy-pasteable git rebase --onto command.

Customize Claude Code statusline. Use when: user says 'statusline', 'status line', 'customize statusline', 'modify statusline', 'statusline settings', 'statusline theme', 'change theme', 'color scheme', wants to add/remove/change segments (cost, git, model, context), switch color themes (catppuccin, dracula, nord), or asks what can be shown in the statusline.

Technical briefing for developer sharing. Use when: sharing implementation findings with technical colleagues, post-development knowledge transfer, documenting what was built and why. Not for: PM/CTO summary (use project-brief), first-principles reasoning (use fp-brief), design-phase specs (use tech-spec). Output: 6-section technical brief with source provenance.

Context-aware test orchestration. Use when: smart test selection, failure triage, progressive test ladder, test failure analysis. Not for: writing tests (use post-dev-test), reviewing tests (use codex-test-review), generating tests (use codex-test-gen), full manual run (use verify). Output: test results + triage report + fixer actions.

Holistic test coverage measurement. Use when: assessing test health, measuring coverage trends, quantitative + qualitative test audit. Not for: running tests (use verify), reviewing test sufficiency only (use codex-test-review), generating tests (use codex-test-gen). Output: multi-dimensional dashboard with coverage metrics + test inventory + trend.

First-principles UI/IA reasoning: turns a `<scenario>` + API field set into JTBD analysis, principle-anchored field-priority decisions, anti-pattern findings, and a bidirectional UI↔API gap report. Trigger: UI、UX、資訊架構、IA、scenario-driven UI、欄位優先級、information hierarchy. Not for: visual/CSS work (use `/frontend-design`), post-build critique (use `/critique`), or simplifying existing layouts (use `/distill`).

Research current code state then update corresponding docs, ensuring docs stay in sync with code.

Verification loop — lint -> typecheck -> unit -> integration -> e2e

Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run verdict (pass/fail/timeout).

Rewrite the previous reply in Traditional Chinese

Create or refactor a Claude Code skill

Bug/Issue fix workflow. Investigate → Locate → Fix → Test → Review.

Claude Code configuration health check. Scans .claude/ directory structure, naming consistency, junk files, count sync.

Dual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally integrate both conclusions.

Code review using Codex MCP. Supports fast (diff-only), full (lint+build), and branch review variants.

Explain complex code logic using Codex MCP. Supports brief/normal/deep depth levels.

Implement feature code using Codex MCP. Decomposes specs into items, implements one at a time, with review loop.

Create or refactor Claude Code skills. Guides skill design, file structure, and best practices.

Remove AI-generated artifacts from documents, including tool names, boilerplate patterns, over-structuring.

Document review knowledge base. Covers tech spec review, document audit, document refactoring. Codex MCP integration for .md reviews.

Feasibility analysis from first principles. Explore solutions, quantitatively assess, in-depth Codex discussion. Use before /tech-spec.

Feature development workflow. Covers implementation, verification, pre-commit checks, refactoring. Guides through design -> implement -> verify -> review -> commit flow.

Portfolio system knowledge base. Covers position queries, routing strategies, {PRIMARY_PROVIDER} integration, cache design.

Post-development test completion. Analyzes developed features from context, checks integration/e2e test coverage, writes missing tests. Use after feature-dev, before /precommit.

Initialize project configuration. Auto-detect framework, package manager, database, and replace CLAUDE.md placeholders.

Project initialization inventory and cache generation (one-time intake). Use when first onboarding a project or after major structural changes.

Request tracking knowledge base. Covers request structure, status tracking, document references, progress management.

Security review knowledge base. OWASP Top 10 review using Codex MCP, dependency security audit.

Tech spec knowledge base. Full workflow from requirement analysis, code research to spec output.

Test review knowledge base. Covers test coverage review, test generation, coverage analysis. Codex MCP integration.