Claude Skills by skymanbp

github.com/skymanbp

19 skillsA× 190 installs5 views

TreeAUniversal radial-tree exploration engine — loads a preset, grounds a root, expands every node through 12 framing passes, derives each child in 12 evidence-bearing fields, scores it, and recurses on `advances` leaves until substantive convergence (or a user cap). Caps default to ∞; `defer / TODO / NEEDS-MORE-INFO` leaves are hard-banned. Use when the user wants the engine itself — a custom preset via `--preset <path>`, explicit control of a run, or "tree of thoughts" / 穷尽的树状探索 in general; for ...ai-agentspythongoVotes: 0GitHub stars: 101
EraseAGuided 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.developmentgogitVotes: 0GitHub stars: 21
Ccm LoadALoad 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".ai-agentspythongoVotes: 0GitHub stars: 7
Save MemoriesASave 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).ai-agentspythongoVotes: 0GitHub stars: 7
Systematic DebugA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。ai-agentsbashreactVotes: 0GitHub stars: 6
BrainstormAFully automatic radial exploration engine for divergent research ideation, or for exhaustively finding ways to solve one concrete hard problem. The data model is a phylogenetic tree: root = the starting point (topic / problem / current research state), node = one idea, depth = number of divergence layers, width = number of final results. Every node is brainstormed through twelve framing passes (first-principles, inversion, cross-disciplinary transport, adversarial, constraint relaxation, scal...ai-agentspythongoVotes: 0GitHub stars: 6
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
CalibrateAMake the plugin yours. Walks the whole calibration chain for one field — corpus intake, profile extraction, per-axis calibration, optional model training, a held-out provenance measurement, and finding-level labelling against your own standard, style and target journal — then verifies the result. Every axis reports `measured`, `degraded` or `unmeasured` from its own floor; a stratum that cannot support a rate stays `unmeasured` rather than being given one. Produces evidence only: no threshold...ai-agentspythonrustVotes: 0GitHub stars: 6
CondenseAWhole-document condensation. Removes every passage that is unnecessary or already stated elsewhere: claims and numbers repeated across sections, zero-information paragraphs, dead definitions and uncited figures, verbose constructions. Executes SCIPAPER_STANDARD §5.3 (condense, do not accumulate): the default direction of every edit is shorter — delete > compress in place > same-length rewrite, with growth last and only under a recorded justification. Each fact keeps exactly one canonical home...ai-agentspythongoVotes: 0GitHub stars: 6
De AiAThe single de-AI skill. Chains three passes over one target file: (1) in-house de-AI subsystem measurement (L0 lexicon plus L1-L4 structural and learned signals), (2) a vendored humanizer structural-tell audit (AIScientists-Dev/academic-humanizer Layers 1-5 plus blader/humanizer patterns 2.12-2.16 and the Pass-2 self-interrogation), and (3) claim-first faithful rewriting under hard fidelity eligibility and the §5.3 length budget. Every number, formula and citation is preserved; it strips mach...ai-agentspythongoVotes: 0GitHub stars: 6
Figure ReviewAReview every paper figure from the compiled document at print-realistic 150 DPI. Verify figure/caption/data consistency, required labels, units, references, readability, accessibility, float placement, and cross-figure visual coherence. Report SCIPAPER_STANDARD typed findings: objective figure/build contradictions as integrity blockers and aesthetic or borderline readability concerns as advisories, never a universal PASS/WARN paper verdict. Use after figure changes or before submission.ai-agentspythongoVotes: 0GitHub stars: 6
Final ReviewAPre-submission final-review orchestrator. Each round loads /sci-paper:paper and SCIPAPER_STANDARD as the framework, then runs paper-review (all A-R dimensions, including the narrative spine and adversarial escalation), figure-review, de-ai (--audit-only structural-tell audit) and the physics, mainline and logic measurement primitives in isolated worktrees. Merges sci-paper.feedback.v1 typed findings: scientific-integrity blockers must be resolved, L0 targets must reach zero, strong advisories...ai-agentspythongitVotes: 0GitHub stars: 6
LogicA逻辑与统计核查（测量原件，只产 finding，不改稿）：claim graph 的循环论证、断链、偷换条件、充分/必要条件错误、未声明假设；样本与 split、CV/grouping、泄漏防护、metric、uncertainty、多重比较、prior 的可复现性；以及声明-证据纪律的审查端——动词强度不得超过证据强度。findings 走 sci-paper.feedback.v1。可单独运行，也是 /sci-paper:paper-review 维度 C 的唯一来源。Use for: 逻辑检查, 论证是否成立, 统计方法学, 数据泄漏, 多重比较, 声明证据纪律, claim-evidence, over-claim 检查。ai-agentsVotes: 0GitHub stars: 6
MainlineA叙事主线核查（测量原件，只产 finding，不改稿）：建 paper-level purpose record 与 contribution graph，再按 cold reader 回答八问，定位读者需要回溯、补隐藏上下文或在竞争解读间抉择的地方。findings 走 sci-paper.feedback.v1；不假设三幕模板，多贡献论文可有多个明确相关的分支，但都从属于唯一的 thesis line。可单独运行，也是 /sci-paper:paper-review 维度 E 的唯一来源。Use for: 叙事主线, 主线检查, contribution graph, 冷读八问, narrative spine, 文章结构是否讲得通, 读者会不会卡住。ai-agentsnodeVotes: 0GitHub stars: 6
Paper ReviewAStrict, source-traced scientific paper review. Runs all A-R dimensions under the SCIPAPER_STANDARD feedback contract: mathematics, physics, logic and statistics, language and de-AI, document structure and narrative spine (contribution graph plus an eight-question cold read), citation existence and relevance, data and figures, interfaces, redundancy, reproducibility, modern-physics checks, cross-section consistency, adversarial derivation verification (three passes plus twelve-framing escalati...ai-agentspythongoVotes: 0GitHub stars: 6
PaperALoad 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.ai-agentspythonbashVotes: 0GitHub stars: 6
PhysicsA物理第一原则核查（测量原件，只产 finding，不改稿）：量纲一致性、渐近极限、对称性/宇称/守恒律、信息论与统计不等式的前提、代数再推导、数值溯源、基础引用真实性、编译与交叉引用完整性。findings 走 sci-paper.feedback.v1 的后果类别与 measurement state；拿不到证据报 unmeasured 或 not_applicable，绝不记成零 finding。可单独运行，也是 /sci-paper:paper-review 维度 K 的唯一来源。Use for: 物理正确性核查, 量纲检查, 守恒律与宇称, 渐近极限, 数值溯源, physics check, 物理第一原则审查。ai-agentsVotes: 0GitHub stars: 6
Proposal PolishAFunding-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.ai-agentspythonrustVotes: 0GitHub stars: 6
Repo RefreshA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。ai-agentspythonbashVotes: 0GitHub stars: 6
Repo RefreshA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。ai-agentspythonbashVotes: 0GitHub stars: 5