菜单
Deep codebase research — five parallel search modalities (names, content, structure, git history, tests), deep-reads of every lead, a cited synthesis, and a completeness critic. Use for "where is X handled", "how does Y work", "what breaks if Z changes". This searches the repo, not the web.
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
| name | fable-research |
| description | Deep codebase research — five parallel search modalities (names, content, structure, git history, tests), deep-reads of every lead, a cited synthesis, and a completeness critic. Use for "where is X handled", "how does Y work", "what breaks if Z changes". This searches the repo, not the web. |
| argument-hint | <question> |
The user invoked /fable-research: that is explicit opt-in to workflow orchestration — call the Workflow tool.
fable-research with args: { question: "<the question>" }.If the Workflow tool is unavailable, run the same structure with Agent-tool subagents: five parallel fable-scout sweeps (one modality each), scouts deep-reading the deduplicated leads, one fable-scribe synthesis, then one fable-critic completeness pass.
Loop-until-dry exhaustive hunt — waves of diverse finders keep sweeping until two consecutive rounds surface nothing new, and every fresh finding faces a three-lens judge panel. Use for "find ALL the bugs", full audits, and edge-case sweeps.
Continuous goal-directed operation across many cycles or sessions — maintains a persistent run file (goal, backlog, journal), executes one backlog item per cycle through the full phase discipline, commits at verified milestones, and keeps cycling. Composable with /loop or scheduled tasks for unattended long runs. Use for "keep working on this", overnight runs, or multi-day builds. Wants a git repository — checkpoint commits are its safety rail; it offers git init once if missing.
Repo-wide mechanical change — four parallel discovery modalities find every site, a two-file pilot proves the instruction before the fan-out, then each file is transformed and independently checked, and the project's own checks run once. Use for "rename X everywhere", "replace API A with B", "apply this fix across the repo". It edits files.
Judge-panel design — three genuinely different approaches (simplicity-first, robustness-first, evolution-first) scored by independent judges and synthesized into one grounded implementation plan. Use for architecture decisions or "how should I build X".
Multi-agent adversarial code review — four parallel finders (correctness, contracts, security, resources), with every finding independently attacked by skeptics before it reaches you. Use for "review this", "check my changes", or as a pre-PR gate.
Release-readiness gate — detects the project's build/test/release mechanics, runs the gates (read-only hygiene first, then checks and docs in parallel), then a skeptic attacks the "ready to ship" claim. Use before releasing, deploying, tagging, or publishing. It verifies readiness; it never deploys.