CtrlK
BlogDocsLog inGet started
Tessl Logo

stanley-druckenmiller-investment

スタンレー・ドラッケンミラーの投資哲学と戦略に基づいた投資アドバイスを提供。30年間無敗、年率30%近いリターンを達成した伝説的投資家の思考法を活用し、マクロ経済分析、リスク管理、ポジション構築、市場サイクルの読み方などについて実践的な指導を行う。投資判断、市場分析、リスク管理、ポートフォリオ構築などの相談時に使用。

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable meta-skill body with clear sequencing and good reference disclosure. The only weakness is redundancy: the upstream-skill list and trigger phrasings are repeated across sections, adding tokens without new information.

Suggestions

Collapse the 'Relationship to Other Skills' table into the Input Requirements tables (or drop it) so the 8 upstream skills are listed only once; merge the Time Horizon column into the requirement tables.

Remove or shorten the 'When to Use This Skill' bilingual bullet list in the body since the same triggers already appear in the frontmatter description, keeping the body focused on execution.

Trim the Phase 3 'Present Results' bullet list to the distinct items not already implied by the Output Files section to reduce overlap.

DimensionReasoningScore

Conciseness

Mostly efficient and table-driven, but the 8 upstream skills are listed twice (Input Requirements tables and the Relationship to Other Skills table) and the 'When to Use This Skill' section duplicates the frontmatter triggers, so it could be tightened.

2 / 3

Actionability

Provides a fully executable command with all flags ('python3 skills/.../strategy_synthesizer.py --reports-dir reports/ --output-dir reports/ --max-age 72'), a numbered script-behavior list, and concrete output filenames — copy-paste ready.

3 / 3

Workflow Clarity

Four phases are clearly sequenced, and Phase 1 is an explicit validation checkpoint ('Check that the 5 required skill JSON reports exist ... and are recent (< 72 hours). If any are missing, run the corresponding skill first'), giving a validate-and-correct feedback loop.

3 / 3

Progressive Disclosure

Overview points to four real one-level-deep reference files (all present under references/) plus scripts/ and assets/, with an explicit 'When to Load References' subsection signaling each load condition.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete capabilities, explicit when/triggers in both English and Japanese, and a clearly distinct niche. No missing elements against the rubric.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Integrates 8 upstream skill outputs ... into a unified conviction score (0-100), pattern classification, and allocation recommendation' — matching the 'Lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (synthesize 8 outputs into conviction score / pattern / allocation) and when ('Use when user asks about overall market conviction, portfolio positioning, asset allocation ... Triggers on queries like ...'), satisfying the explicit-triggers anchor.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say ('What is my conviction level?', 'How should I position?', 'Run the strategy synthesizer') plus Japanese equivalents, giving broad coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (Druckenmiller-style meta-skill consuming 8 named upstream skills) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tradermonty/claude-trading-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.