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.

68

Quality

81%

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

75%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.

A well-structured, actionable writing overlay: directive, clearly sequenced, and self-contained. The recurring gap is that verification and detailed examples are delegated to external skills rather than shown inline, which keeps every dimension at a solid 4 instead of 5.

Suggestions

Inline one compact worked example (a short fictional company hitting the 8-step shape) so the guidance is demonstrably executable end-to-end and actionability can reach 5.

Add an explicit inline validation/feedback loop (e.g., 'run report_audit.py; if it flags a section, revise that section before publishing') to lift workflow_clarity above 4.

Collapse the overlap between Core Workflow and Default Report Shape — either merge the operating steps into the report-shape section or cross-reference them — to tighten conciseness.

DimensionReasoningScore

Conciseness

Largely lean, directive prose ('Prefer concrete numbers and mechanisms over adjectives', 'Use tables when they reduce cognitive load') with little concept over-explanation, but the Core Workflow and Default Report Shape sections cover overlapping ground and could be tightened, so it is not a clean 5.

4 / 5

Actionability

Concrete, specific per-section guidance ('Score or table the moat by source: brand/pricing power, switching cost, network effect...', 'Show current multiples, reverse DCF intuition, scenario valuation') that an instruction-only skill can act on; no code is present but the rubric exempts that for actionable instruction skills, and a fully worked example memo would close the gap to 5.

4 / 5

Workflow Clarity

Two clear, ordered multi-step sequences (9-step Core Workflow, 11-section Default Report Shape) plus a Quality Bar checklist and an audit gate ('report_audit.py before treating a report as publishable'), but validation checkpoints are delegated to peer skills rather than stated as inline feedback loops, which is a minor gap below 5.

4 / 5

Progressive Disclosure

A single self-contained file with well-organized, clearly headed sections and no nested references; because the document is instruction (not reference material) and exceeds ~50 lines, it sits at 'good structure' rather than the simple-skill 5, though nothing is misplaced or buried.

4 / 5

Total

16

/

20

Passed

Description

87%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.

A strong description: third-person, concrete triggers, clear what/when, and a well-scoped niche with an explicit boundary. The only soft spot is that the named actions are generic writing verbs, which keeps specificity and trigger breadth just shy of perfect.

Suggestions

Add one or two more distinctive action verbs tied to the overlay's unique value (e.g., 'stress-test valuations into buy/hold/sell bands', 'audit report layout against the AI Berkshire shape') to lift specificity from 4 to 5.

Include the natural phrase 'investment memo' earlier and add a common-user phrasing like 'research report' alongside it so trigger coverage captures more synonyms.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete verbs ('creates, rewrites, revises, or critiques company/industry/fund research reports') plus a detailed attribute list, but the actions are somewhat generic writing verbs rather than fully distinct capabilities, keeping it just below a 5.

4 / 5

Completeness

Explicitly answers both 'what' (a writing and layout overlay for investment research reports) and 'when' ('Use whenever Codex creates, rewrites, revises, or critiques... long-form Markdown reports'), with concrete trigger phrases and a negative boundary clause.

5 / 5

Trigger Term Quality

Good natural-keyword coverage ('investment research reports', 'long-form Markdown reports', 'buy/hold/sell signals', 'investment memo') with synonyms, but file extensions and a few common phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

Carves a clear, narrow niche ('Codex-only', 'AI Berkshire investment research reports') with distinct triggers and an explicit non-target ('Do not use this to modify Claude Code slash-command sources'), giving minimal conflict risk.

5 / 5

Total

18

/

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.