菜单
Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD. Use when: an expert agent needs to self-review and self-correct code after the Execute phase, before sniper validation.
Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing. Do NOT use for: lint/type/code-quality validation (use code-quality / sniper AFTER functional verification passes).
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use when committing changes, saving work, staging and committing, or choosing a conventional commit message.
Use when committing, branching, opening PRs, or deciding merge strategy. Covers GitHub Flow (default), trunk-based, branch naming conventions, squash vs rebase, branch lifecycle, and protected branch enforcement.
Universal post-commit actions. CHANGELOG update for all repos (git tag is created POST-MERGE, not here — see `commit` command Step 8). Plugin version bumping for marketplace repos. Triggered after any code commit (except wip/amend/undo).
| name | research |
| description | Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations. |
Runs in a forked subagent context (spawn_agent) via the research-expert agent. The research topic is passed as the skill argument.
1. THINK → Sequential Thinking decomposition
2. RESOLVE → Context7 resolve-library-id
3. DOCUMENT → Context7 query-docs (5000-10000 tokens)
4. SUPPLEMENT → Exa code context search
5. SYNTHESIZE → Structured answer with sources
1. DEEP THINK → Multi-hypothesis Sequential Thinking
2. DEEP RESEARCH → Exa deep researcher (45s-2min)
3. MONITOR → Check status until completed
4. VALIDATE → Cross-check Context7 official sources
5. REPORT → Comprehensive solution
1. WEB SCAN → Exa search latest developments
2. CODE PATTERNS → Exa code context for practices
3. ECOSYSTEM → Company research for key players
4. ANALYSIS → Sequential Thinking for implications
5. RECOMMENDATIONS → Actionable insights
Parallelization:
resolve-library-id + web_search_exa simultaneouslySource Priority:
resolve-library-idreferences/tool-usage.md — Load when calling Context7, Exa, or Sequential Thinking (exact call patterns, models, and per-tool error handling)references/response-format.md — Load when writing the final research report