菜单
Investigate local repository, document, and attached-artifact context. Use for local investigation requests like "investigate", "find where", "understand this repo", "trace", and local-context research; do not use for web search.
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
Review any artifact and output results in a Retrospective board format — what is well, what is bad, what should be improved, what to change. Use when the user says "review", "critique", "evaluate", "what's wrong with", "compare", or passes a skill, rule, doc, spec, code, diff, or pull request for assessment. Works on a single artifact, an artifact against a reference, a diff or PR, or two artifacts side by side.
Compare options and recommend a direction. Use for decision requests like "choose", "which option", "tradeoffs", "recommend", "should we", and option selection with criteria, risks, and reversibility.
Organize material into meaningful groups. Use for classification requests like "categorize", "group", "cluster", "sort", "taxonomy", "organize these", and grouping by criteria, priority, dependency, similarity, or abstraction level.
Explain any knowledge topic simply and accurately. Use for explanation requests like "explain X", "why/how/what is X?", concepts, science, definitions, code, design, architecture, and walkthroughs.
Manage active work across people, agents, tasks, dependencies, blockers, and handoffs. Use for coordination requests like "manage this work", "lead this", "assign", "delegate", "track blockers", "status", "handoff", and multi-workstream execution.
Sequence work before execution. Use for planning requests like "break this down", "roadmap", "approach", "milestones", "how should we proceed", migration planning, rollout planning, and scoped next steps.
| name | investigate |
| description | Investigate local repository, document, and attached-artifact context. Use for local investigation requests like "investigate", "find where", "understand this repo", "trace", and local-context research; do not use for web search. |
| license | MIT |
| tags | ["local-investigation","investigation","local-context"] |
| metadata | {"author":"Oleg Shulyakov","version":"1.1.0","source":"github.com/olegshulyakov/agent.md","catalog":"utility","category":"research"} |
Investigate local context and report evidence-backed findings.
Scenario: Investigation stays local Given the user asks for local investigation Then search local files, project docs, attached artifacts, repository history, and available workspace context only
Scenario: Web research would be needed Given the answer requires web search, browsing, or current-information research Then do not perform it as part of this skill And state that external research is outside the local investigation scope
Scenario: Findings are reported Given findings are presented Then ground them in file references, artifact references, command output, or clearly marked inference
Scenario: No matches are found Given local searches return no matches Then say what was searched And suggest the next local search path
Scenario: Sources conflict Given local sources disagree Then prefer runtime wiring and tests over stale docs And state the conflict
Scenario: Generated or external code is missing Given a needed generated or external source is unavailable Then identify the missing source And explain how it affects confidence
Scenario: Output passes quality check Given local findings have been produced Then key searches were run before relying on memory And implementation, tests, configs, or authoritative docs are preferred over secondary mentions And no external or current-information claims are introduced
