income-investment

AI Berkshire skill: Income Investment: Durable and Opportunistic Distribution Analysis. Source: skills/income-investment.md.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/income-investment/SKILL.md

Quality

Content

77%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 content is a tightly written, highly actionable research workflow with an explicit multi-step sequence, blocking gates, and a real audit feedback loop. Its main weakness is progressive disclosure: it is one large inline document with no bundle files or one-level-deep navigable references.

Suggestions

Move the sector-measures table and the qualitative scorecard into a reference file (e.g. references/scorecard.md) and link to it, so SKILL.md stays an overview that pulls detail one level deep.

Add at least one concrete `python3 tools/financial_rigor.py` invocation with example arguments so the arithmetic step is copy-paste ready rather than implied.

Convert sibling-workflow and tool mentions into actual links or relative paths (e.g. [financial-data](../financial-data/SKILL.md)) to make navigation explicit rather than relying on code-span strings.

Dimension	Reasoning	Score
Conciseness	The body is dense but almost entirely task-specific instruction with little padding; it avoids explaining concepts Claude already knows (no 'what is a dividend') and every section earns its place, though a few prose lines (e.g. the ex-dividend aside) could be trimmed, keeping it at 4 rather than 5.	4 / 5
Actionability	It gives concrete, mostly-executable guidance: exact CLI command form, `python3 tools/financial_rigor.py` for arithmetic, a fixed 18-section report format, and audit commands; it stops at 4 because the financial_rigor.py and report_audit.py invocations omit argument details/examples and some steps are instructions rather than copy-paste code.	4 / 5
Workflow Clarity	An explicit 8-step Execution Workflow plus a gated Classification/Verdict section and a Release Audit with a validate->fix->retry feedback loop ('A report that fails audit is a draft, not publishable research'; 'Fix failed items and repeat the audit'), with clear checkpoints including the INSUFFICIENT DATA gate and blocking gates.	5 / 5
Progressive Disclosure	It is a single monolithic SKILL.md with no bundle files in references/scripts/assets and inline references to sibling skills/tools as code spans (e.g. `skills/financial-data.md`, `tools/report_audit.py`) rather than navigable links; structure is clear but content that could be split (the sector-measures table, scorecard) is inline, so it sits at 3.	3 / 5
	Total	16 / 20 Passed

Description

28%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 is a terse domain label padded with provenance metadata ('AI Berkshire skill', 'Source: ...') rather than a capability-and-trigger statement. It lacks concrete actions and any 'Use when...' trigger guidance, which limits both completeness and trigger-term quality.

Suggestions

Replace the provenance-style description with a concrete capability statement, e.g. 'Analyzes a company's dividend/distribution durability, coverage, and portfolio income role, and returns a CORE INCOME / OPPORTUNISTIC / YIELD TRAP verdict with a research report.'

Add an explicit 'Use when...' clause naming natural user triggers: 'Use when the user asks about dividend safety, yield, distribution durability, or whether a stock is an income trap.'

Drop the 'AI Berkshire skill:' prefix and 'Source: skills/income-investment.md.' provenance from the description — that metadata does not help users discover or disambiguate the skill.

Dimension	Reasoning	Score
Specificity	The description only states a domain label ('Durable and Opportunistic Distribution Analysis') with no concrete actions, mirroring the score-2 anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because no concrete actions are enumerated.	2 / 5
Completeness	It gives a vague 'what' (an analysis skill) with no 'Use when...' clause or equivalent trigger, so a missing trigger caps it; per the guideline a missing 'Use when' clause caps completeness at 3, but the 'what' itself is also vague, placing it at 2 rather than 3.	2 / 5
Trigger Term Quality	It supplies a few generic domain keywords ('Income Investment', 'Distribution Analysis') but omits natural user phrases such as 'dividend', 'yield', 'income', or 'ticker', matching the score-2 anchor of one or two generic keywords missing common phrases.	2 / 5
Distinctiveness Conflict Risk	The niche is fairly specific ('Income Investment: Durable and Opportunistic Distribution Analysis') and unlikely to conflict broadly, but without explicit triggers it could still overlap with sibling investment-research/portfolio skills; it sits above 2 and below 4.	3 / 5
	Total	9 / 20 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/income-investment/SKILL.md
Commit: be46832

Reviewed: 3 days 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.