CtrlK
BlogDocsLog inGet started
Tessl Logo

portfolio-review

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

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/portfolio-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

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 well-sequenced, actionable portfolio-review workflow with concrete tools and validation, but it is padded with motivational philosophy and keeps all detail inlined rather than splitting reference material into separate files.

Suggestions

Trim motivational padding — the investor quotes, the '设计理念' section, and the closing '关键原则' list restate concepts and add tokens without adding capability.

Add an explicit error-recovery loop around validation, e.g. 'If verify-valuation fails or returns C-grade data, flag the holding, re-search, and re-validate before drawing conclusions.'

Move the example tables and expected-return formulas into a reference file (e.g. references/valuation-methods.md) and link to it one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The workflow is mostly efficient with concrete tables and tool commands, but it carries motivational padding Claude does not need — investor quotes (巴菲特/李录/段永平), the '设计理念' philosophy section, and a closing '关键原则' list that restates concepts — fitting 'Mostly efficient but includes some unnecessary explanation.'

3 / 5

Actionability

It provides executable tool calls (`tools/financial_rigor.py verify-valuation`, `three-scenario`), specific thresholds (<40%, 50-80%, 无风险利率~4%), concrete output formats, and a defined report structure — 'Mostly executable guidance with minor gaps' (some tables are blank-cell templates and the return formulas are simplified guidance).

4 / 5

Workflow Clarity

Seven sequenced steps (第一步–第七步) with substeps and validation checkpoints (verify-valuation, A/B/C info-grading with low-confidence labeling, mandatory conclusion questions) give 'Clear sequence with most checkpoints present'; it stops short of 5 because there is no explicit validation-failure/retry feedback loop.

4 / 5

Progressive Disclosure

The skill is well-sectioned with clear headers and references external tools/skills, but no bundle reference files exist and all detail (example tables, formulas, principles) is inlined in one ~200-line document — matching 'Some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline.'

3 / 5

Total

14

/

20

Passed

Description

40%Weight 40%Scale 1-5

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 functions as a localized title with a source note rather than a capability statement: it names the portfolio-management niche but specifies no concrete actions and omits any 'when to use' trigger guidance.

Suggestions

Replace the title-plus-source framing with concrete actions, e.g. 'Reviews and rebalances an investment portfolio: parses holdings, checks concentration/correlation, ranks opportunity cost, and proposes adjustments.'

Add an explicit 'Use when...' trigger clause such as 'Use when the user asks to review, rebalance, or optimize a portfolio/holdings (组合/持仓).'

Drop the 'Source: skills/portfolio-review.md' attribution from the description — it is metadata that does not help Claude decide when to invoke the skill.

DimensionReasoningScore

Specificity

The description names the domain ("组合管理:从'研究公司'到'管理组合'") but lists no concrete actions — it is a category label plus source attribution ("Source: skills/portfolio-review.md"), matching the anchor 'Names the domain but actions are minimal or generic.'

2 / 5

Completeness

It offers only a vague 'what' (portfolio management) with no 'when' guidance whatsoever — no 'Use when...' clause, so it sits below the cap-of-3 case and matches 'Has a vague what and no when.'

2 / 5

Trigger Term Quality

It includes relevant Chinese keywords a user might say ("组合管理", "研究公司", "管理组合") but lacks explicit 'Use when' trigger phrases, common synonyms, or file extensions, fitting 'Some relevant keywords but missing common variations or synonyms.'

3 / 5

Distinctiveness Conflict Risk

"组合管理" (portfolio management) is a clear niche with distinct triggers and minimal overlap with other skills, though the redundant source attribution prevents a perfect 5.

4 / 5

Total

11

/

20

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
xbtlin/ai-berkshire
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.