portfolio-review

AI Berkshire skill: 组合管理：从"研究公司"到"管理组合". Source: skills/portfolio-review.md.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/portfolio-review/SKILL.md

Quality

Content

77%

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

The body is a strong, highly actionable portfolio-review workflow with clear sequencing and an explicit data-validation step, weakened mainly by philosophical padding and a monolithic structure that references external repo paths rather than in-bundle reference files.

Suggestions

Trim the motivational quotes and the closing "关键原则" section, or move them to a separate references/ file, to reduce philosophy Claude already knows.

Verify that referenced paths (tools/financial_rigor.py, reports/portfolio-latest.md, AGENTS.md) actually exist relative to where the skill runs, and signal them as external repo dependencies rather than implied bundle files.

Consider splitting the analytical sub-sections (4.1–4.4) into a reference file to bring SKILL.md closer to an overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The workflow body is mostly purposeful, but motivational quotes ("巴菲特...", "李录...", "段永平...") and the closing "关键原则" section restate investment philosophy Claude already knows and could be trimmed without losing guidance.	2 / 3
Actionability	Concrete, specific guidance throughout: fillable tables, exact tool invocations (tools/financial_rigor.py verify-valuation, three-scenario), explicit formulas (FCF Yield + 预期增速), specific scenarios with assumptions, and concrete checklists — actionable even though it is instruction-only.	3 / 3
Workflow Clarity	Seven steps are explicitly sequenced (第一步…第七步) with a validation checkpoint in 第二步 (verify-valuation + A/B/C 信息丰富度 grading, C级标注低置信度) and a baseline date check, providing a clear feedback loop for the data-gathering stage.	3 / 3
Progressive Disclosure	The skill is a ~200-line monolithic single file with no in-bundle reference files (references/scripts/assets are absent); the paths it cites (tools/, reports/, AGENTS.md) are external repo files rather than one-level-deep skill references, so it is internally sectioned but not progressively disclosed.	2 / 3
	Total	10 / 12 Passed

Description

50%

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

The description is largely metadata and a slogan rather than a trigger-oriented capability statement: it names the domain but lists no concrete actions and gives no usage triggers. It would be hard for a user or router to confidently select this skill from the description alone.

Suggestions

Replace the meta prefix ("AI Berkshire skill:" and "Source: ...") with concrete actions, e.g. "审视并优化投资组合：解析持仓、单仓位体检、集中度与相关性分析、机会成本排序、压力测试，并给出调仓建议。"

Add an explicit "Use when..." trigger clause naming natural user phrasings such as 持仓审视、组合管理、调仓建议、压力测试我的组合.

Drop the source-file citation from the user-facing description; keep it in the body's adapter note instead.

Dimension	Reasoning	Score
Specificity	The description names the domain ("组合管理") but offers no concrete actions such as reviewing holdings, rebalancing, or stress-testing; the framing "从研究公司到管理组合" is a philosophy statement rather than a capability list.	2 / 3
Completeness	It weakly answers "what" (portfolio management) but provides no "when" — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	It contains one relevant term ("组合管理") but omits the natural phrasings a user would actually say (e.g. 持仓, 审视组合, 调仓, 股票组合), and most of the string is meta noise ("AI Berkshire skill", "Source: skills/portfolio-review.md") rather than trigger terms.	2 / 3
Distinctiveness Conflict Risk	The Berkshire/组合管理 framing gives it a niche, but the description is generic enough that it could overlap with sibling investment skills referenced in the body (e.g. /industry-research, /investment-checklist).	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xbtlin/ai-berkshire
Path: codex-skills/portfolio-review/SKILL.md
Commit: 634a399

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.