跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

tree

Universal radial-tree exploration engine. Loads a preset, builds a §2 baseline, then recursively applies 12 framing passes per node until stable convergence (no new high-verdict branches over the last 2 rounds + all 12 framings exercised + all leaves complete). Width × depth × rounds default to ∞; resource caps are opt-in. Hard ban on `defer / future-work / TODO / NEEDS-MORE-INFO` leaves — every leaf must be fully derived before counting. Use when 用户说 "brainstorm" / "attack" / "design exploration" / "code audit" / "explore options" / "find what's wrong" / "what should we build" / "tree of thoughts" / 想做穷尽的发散探索 / 想做多角度审查 / 想对一个工件 adversarial critique / 想做设计空间探索. Prefer the per-preset commands (`/cc-tree:brainstorm`, `/cc-tree:attack`, `/cc-tree:design`, `/cc-tree:code-audit`) when the use-case matches; call this skill directly with `--preset <name|path>` to override or supply a custom preset.

skymanbp · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add skymanbp/cc-tree --skill tree

技能说明


name: tree description: Universal radial-tree exploration engine. Loads a preset, builds a §2 baseline, then recursively applies 12 framing passes per node until stable convergence (no new high-verdict branches over the last 2 rounds + all 12 framings exercised + all leaves complete). Width × depth × rounds default to ∞; resource caps are opt-in. Hard ban on defer / future-work / TODO / NEEDS-MORE-INFO leaves — every leaf must be fully derived before counting. Use when 用户说 "brainstorm" / "attack" / "design exploration" / "code audit" / "explore options" / "find what's wrong" / "what should we build" / "tree of thoughts" / 想做穷尽的发散探索 / 想做多角度审查 / 想对一个工件 adversarial critique / 想做设计空间探索. Prefer the per-preset commands (/cc-tree:brainstorm, /cc-tree:attack, /cc-tree:design, /cc-tree:code-audit) when the use-case matches; call this skill directly with --preset <name|path> to override or supply a custom preset. disable-model-invocation: false argument-hint: " --preset <name|path> [--lang <tag|auto>] [--width N|∞] [--depth N|∞] [--rounds N|conv] [--max-branches N|∞] [--out ] [--glossary ] [--field <name|path>] [--seed-from <primary.md>] [--no-grill] [--no-online] [--min-frameworks N] [--min-novelty-ratio R] — <root> is a topic string, file path, problem statement, or design prompt; --preset is required (use brainstorm / attack / design / code-audit for shipped presets, or a path to your own .md)"

tree — universal radial-tree exploration engine

What this skill is. A single engine implementing recursive radial-tree exploration (root → 12-framing expansion → per-node 12-field derivation → score → recurse on high-verdict leaves → terminate on substantive convergence). What varies between use-cases (brainstorm vs critique vs design vs code-audit) is the baseline recipe, node schema, scoring dimensions, and verdict vocabulary — all parameterized via a preset file.

What this skill is NOT. Not a one-shot LLM call that returns a bulleted list. Not a chat interface — once /cc-tree:tree is invoked, the engine runs to convergence without further prompts. Not bundled with a model — pure prompt-engineering on top of Claude Code's existing model setting.

The full engine specification lives in docs/ENGINE.md. This SKILL.md is a 7-step navigation guide; Read docs/ENGINE.md before producing the first node (the engine spec is what defines "valid" for everything you'll write).


1. Invocation

/cc-tree:tree <root> --preset <name|path> [flags]

<root> is preset-typed:

  • brainstorm preset → topic string, e.g. "ways to detect dark-matter substructure"
  • attack preset → file path (.md / .tex / etc.) or quoted argument-text
  • design preset → design-prompt string or .md file path
  • code-audit preset → file path or directory path

--preset is required:

  • Built-in: brainstorm, attack, design, code-audit (resolve to presets/<name>.md in this plugin)
  • Path: ./my-custom.md (any .md file with the right frontmatter)

Common flags (apply across presets)

FlagDefaultMeaning
--lang <tag|auto>enOutput language for all localized prose (node statements, derivations, report narrative, warnings). Machine tokens — flag/command names, frontmatter & JSON keys, root_kind values, verdict labels, status tokens, filenames — always stay English. <tag> is a BCP-47-like code (en, zh, zh-Hans, zh-Hant, fr-CA); zh = Simplified Chinese, zh-Hant = Traditional. auto detects the dominant language of <root> and falls back to en for mixed / path-only / code-only input. Resolved once before preset load, recorded in run metadata (language_request / output_language / language_source), and never prompted mid-run. Full precedence, resume, and chain semantics: docs/ENGINE.md §1.0.
--width N∞Cap on final leaf count (the outer arc of the tree). ∞ / inf / unspecified all mean unlimited.
--depth N∞Cap on tree depth from root.
--rounds NconvCap on expansion rounds. conv = no cap; terminate by §6 substantive convergence.
--max-branches N∞Cap on new branches per node per round. Floor is 12 because §3 requires all 12 framings to fire; this flag only raises the ceiling.
--out <dir>tree-out/<UTCdate>__<slug>/Output directory. Per-preset commands override (e.g. brainstorm-out/).
--glossary <path>(preset-determined)Path to a glossary / FACTS.md / glossary section in a dossier; used by §2.0 grill prelude.
--field <name|path>(none)Field profile for domain-aware reviewer weighting. <name> → field-profiles/<name>.md in this plugin; <path> → a literal file. Feeds §3.C / §3.D / §3.I / §3.J + the §3.X / §4 evidence bar. Missing profile → warn + continue (non-blocking). See docs/ENGINE.md §2.2.
--seed-from <primary.md>(none)Seed the tree from a prior run's primary deliverable (shortlist.md / options.md / confirmed.md): each listed item enters as a depth-1 seed node and is re-expanded. The substrate for cross-preset chaining (docs/chaining.md). Alias: --from-prior.
--no-grilloffSkip §2.0 glossary grill prelude. Marks root-node terms as unverified; §6 convergence adds a warning.
--no-onlineoffDisable WebSearch / WebFetch. Local + already-Read references only.
--min-frameworks N12Minimum framing passes per node. Floor is 12 (full §3.A–§3.L); flag exists for documentation, not relaxation.
--min-novelty-ratio R0.15§6.1 condition 2 requires "last 2 rounds' high-verdict / total < R".

Presets and their command wrappers may document additional preset-specific

阅读完整来源 ↗