CtrlK
BlogDocsLog inGet started
Tessl Logo

investment-memo-craft

Codex-only writing and layout overlay for AI Berkshire investment research reports. Use whenever Codex creates, rewrites, revises, or critiques company/industry/fund research reports, especially long-form Markdown reports that need financial rigor, readable business mechanics, contrarian analysis, valuation-to-action guidance, investor-specific recommendations, restrained typography, and clear buy/hold/sell signals. Do not use this to modify Claude Code slash-command sources.

72

Quality

88%

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

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 highly actionable with a clear sequenced workflow and useful checklists, but it is held back by redundancy between the Core Workflow and Default Report Shape sections and by a monolithic single-file structure with no progressive disclosure.

Suggestions

Merge or cross-reference 'Core Workflow' and 'Default Report Shape' so the same nine-step flow is not described twice; keep one as the canonical sequence and let the other map steps to report sections without restating the guidance.

Move the detailed per-section 'Default Report Shape' template (step headings, expected contents) into a reference file (e.g. references/report-shape.md) and link to it from a short overview, adding one-level-deep progressive disclosure and navigation.

Tighten 'Style Standards' and 'Layout Standards' by deduplicating overlapping typography rules (e.g. bold-usage guidance appears in both) into a single concise list.

DimensionReasoningScore

Conciseness

The guidance is domain-expert content Claude would not already know, but 'Core Workflow' (9 prose steps) and 'Default Report Shape' (11 sections) restate the same workflow twice from two angles, creating redundancy that could be tightened.

2 / 3

Actionability

Provides concrete, copy-ready specifics — exact title and filename templates ('公司名(ticker)研究报告', '公司名研究报告-YYYYMMDD.md'), enumerated moat sources, and explicit per-step content requirements — rather than vague direction.

3 / 3

Workflow Clarity

A clear numbered sequence (Core Workflow) plus an ordered report shape, with checklists (Quality Bar questions, moat sources, AI bias awareness) and a validation gate via report_audit.py; this is a writing task so the destructive-ops cap does not apply.

3 / 3

Progressive Disclosure

The skill is a single ~150-line monolithic file with no bundle files or one-level-deep references; it is well-sectioned but the detailed Default Report Shape template is inline content that could be split into a reference, and there is no file-level navigation.

2 / 3

Total

10

/

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.

The description is specific, uses natural trigger terms, answers both 'what' and 'when' with an explicit trigger clause, and is clearly distinct from other skills. It uses third-person voice with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'creates, rewrites, revises, or critiques company/industry/fund research reports' — matching the score-3 anchor for listing several specific actions rather than just naming a domain.

3 / 3

Completeness

Explicitly answers both what ('writing and layout overlay for AI Berkshire investment research reports') and when ('Use whenever Codex creates, rewrites, revises, or critiques…'), with an explicit 'Use whenever' trigger so it is not capped at 2.

3 / 3

Trigger Term Quality

Uses natural phrases a user would say — 'investment research reports', 'company/industry/fund research reports', 'rewrites/revises/critiques' — giving good coverage rather than jargon or a single generic term.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (AI Berkshire, Codex-only) and explicitly excludes Claude Code slash-command sources, making overlap with other skills unlikely.

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
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.