スキル一覧に戻る
Zpankz

lambda

by Zpankz

MCP Skillset - Claude Code skills, references, and knowledge base

0🍴 0📅 2026年1月24日
GitHubで見るManusで実行

SKILL.md


name: Lambda description: Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation. metadata: λ.in: "" λ.out: "Learn" λ.kin: "compound-reference, learn-compound"

λ

λ(ο,K).τ :: (Query, Knowledge) → (Response, Knowledge')

Kernel

λ(ο,K).τ = let τ = emit ∘ validate ∘ compose ∘ execute(K) ∘ route ∘ parse $ ο
               K' = K ∪ compound(assess(τ))
           in (τ, K')

This skill is the transformation it describes. Reading it executes it. Applying it improves it.

Pipeline

StageSymbolFunctionReference
ParseρExtract intent, components, constraintsBuilt-in
RouteΠClassify complexity → select pipeline[reference/pipeline.md]
ExecuteΨApply skills via composition operators[reference/pipeline.md]
ValidateΓ+χEnforce η≥target, KROG[reference/topology.md]
EmitΦFormat per style constraints[reference/style.md]
CompoundΚExtract learnings → update K[reference/compound.md]
SkillRelationshipShared Concepts
LearnExtended form λ(ο,Κ,Σ).τ'compound loop, topology, vertex-sharing
reasonρ* core reasoningcomplexity routing
thinkθ ⊗ models cognitivemulti-step reasoning
grounding-routerExamination modeSAQ, VIVA, citations

Routing

LevelScoreFormConstraints
R0<2id≤50 tokens, no format
R1<4ρ*1-2¶, implicit η
R2<8γ ⊗ ηη≥4, mechanistic
R3≥8ΣKROG, comprehensive

Complexity = domains×2 + depth×3 + stakes×1.5 + novelty×2

Force R0: "define", "what is" | Force R3: "current", "verify", "comprehensive"

Composition

(∘) sequential    (⊗) parallel    fix recursive    (|) conditional

Invariants

η = |edges|/|nodes| ≥ target    -- Density (default: 4.0, SAQ: 2.5)
KROG = K ∧ R ∧ O ∧ G            -- Knowable ∧ Rights ∧ Obligations ∧ Governance

Style (Φ)

  1. PROSE_PRIMACY: Paragraphs over lists
  2. TELEOLOGY_FIRST: Why → How → What
  3. MECHANISTIC: Explicit causation (A → B → C)
  4. MINIMAL: Format only when necessary

Compound (Κ) — The Self-Improvement Loop

After significant interactions, extract learnings:

trigger: "resolution detected"
insight: "what was learned"
vertices: ["shared PKM concepts"]
prevention: "future error avoidance"

K' = K ∪ crystallize(assess(τ))

See [reference/compound.md] for full protocol.

Vertex-Sharing

New knowledge integrates only via shared vertices with PKM:

integrate(new, K) = if shared(new, K) then merge else bridge

Bridge types: [[x]] direct, [[x|y]] synonym, [[x]] > y hierarchical

Examination Mode

ModeTriggerConstraints
SAQ"SAQ", "short answer"~200 words, η∈[2,2.5], R1, prose only
Viva"viva", "oral"Progressive, η∈[3,4], R2, anticipate follow-ups

See [templates/exam.md] for patterns.

Self-Application

This skill validates by demonstrating:

  • Structure has η≥4 (13+ nodes, 50+ edges via cross-references)
  • Process follows KROG (transparent, authorized, meets obligations, governed)
  • Output follows Φ (prose, minimal formatting, mechanistic where applicable)
  • Compound section enables self-update

Reference Documents

DocumentLoad When
reference/pipeline.mdRouting, execution, composition
reference/compound.mdSelf-improvement, learning crystallization
reference/topology.mdη targets, validation, remediation
reference/style.mdΦ constraints, response formatting

Templates

TemplatePurpose
templates/response.mdR0-R3 output patterns
templates/learning.mdKnowledge crystallization schema
templates/exam.mdSAQ/viva constraints

Examples

ExampleDemonstrates
examples/self-apply.mdSkill applying itself
examples/routing.mdClassification decisions

Connected Skills

SymbolSkillComposition
ρreasonρ* core reasoning
θthinkθ ⊗ models cognitive
γgraphγ.extract→compress structure
ηhierarchical-reasoningS→T→O decomposition
κcritiquefix(κ ∘ β) refinement

λ(ο,K).τ    parse→route→execute→validate→emit→compound    η≥target KROG Φ

スコア

総合スコア

40/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

レビュー

💬

レビュー機能は近日公開予定です