skymanbp
UserClaude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.
Categories
Indexed Skills (8)
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.
erase
Guided cleanup of CodeEraser findings — read the reports, verify every candidate against the actual code, delete safely, and prove convergence with ce check. Invoke when the user asks to clean up duplication, dead code, or act on CodeEraser findings.
ccm-load
Load cc-memory for this project — verify the plugin is globally enabled, ensure the project's .ccm/ directory is initialized, and report end-to-end health. The cc-memory equivalent of "make sure I'm wired up here".
save-memories
Save important memories from this conversation to the cc-memory database via the anti-patch upsert path (merge / supersede / insert based on similarity to existing memories).
repo-refresh
全库更新扫描器。在用户要求"全库更新"、"扫一遍仓库"、"检查文档是否过时"、"repo refresh"、"stale scan"、"audit the repo"、"哪些文档跟代码对不上"、"清理冗余"、"找漂移" 等语境下自动唤起。对整个仓库（md 文档 + 代码一视同仁）做系统式扫描，找出并修复"陈旧、过时、冗余、错误、漂移"五类内容；每条 finding 必须带 file:line 证据。它是 rules/12-repo-wide-sync.md 主动半区的执行入口。
systematic-debug
在 debug / 修 bug / 异常排查 / "为什么不工作" 等语境下自动唤起。强制 agent 先走完根因分析的 7 问与 5 步骤，禁止直接给出反应式修补。当用户描述��bug、错误、stack trace、异常行为、"为什么 X 失败"、"为什么 Y 不工作"、"修一下这个"、"测试不过"、"500 报错"、"突然就坏了" 等情形时使用。
paper
Load the unified SCIPAPER_STANDARD writing guidance, formula derivation conventions, scientific-integrity rules, canonical L0 examples, and field-specific reference anchors for ApJ/MNRAS/PRD-level papers. Use when writing or reviewing scientific content.
proposal-polish
Funding-proposal editing mode (NSF Project Summary/Description, NIH Specific Aims, fellowship proposals). Keeps the vision-and-feasibility register a paper would trim, enforces claim-feasibility matching, edits the score-forming first pages hardest, and applies the shared L0 lexical policy. Never invents preliminary data, partners, funding history, or letters, and is not for evading AI-use disclosure.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.