deep-company-series

Write a publication-grade 8-part deep-dive series on a single company (~120k words total): cognitive reset / moat / profit engine / hidden assets / era variable (e.g. AI) / financials Buffett-style / management / valuation+redlines. The core IP is NOT writing but REVISING — a strict fact-check checklist catches pseudo-precision (probability-weighted expectations, third-party MAU discrepancies, linear extrapolation), absolute language, and cross-article number inconsistencies that most finance long-forms violate. Each piece stands alone but shares one valuation/management/price framework. Use when the user wants textbook-level depth on one company for public publishing (a single research report or earnings note is NOT this — use investment-research / earnings-review instead).

Quality

88%

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

Quality

Content

92%

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

The body is an efficient, highly actionable, well-sequenced workflow with strong validation feedback loops — its core differentiator (strict revision) is concretely operationalized. The lone gap is progressive disclosure: everything lives in one monolithic file with no reference offloading.

Suggestions

Move the 8-part series template table, the banned-words table, and the 7-check revision list into a reference file (e.g. references/revision-checklist.md) and link to it from the body to reduce inline bulk.

Add a brief 'Quick start' overview near the top that points to the phase that matters most (the cross-article consistency scan), so the core IP is discoverable before the full template.

Dimension	Reasoning	Score
Conciseness	The body is dense with skill-specific IP (revision checklist, pseudo-precision traps, cascade rules) and avoids explaining concepts Claude already knows like DCFs or moats; nearly every token earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	Provides concrete tool calls (get_financial_statements, report_audit command=verdict, financial_rigor command=cross_validate), a 7-item revision checklist, a revision-grade table, and explicit file paths — concrete and copy-ready rather than abstract.	3 / 3
Workflow Clarity	Lays out a clear four-phase sequence (Research, Writing, Cross-Article Scan, Pre-publish) with explicit validation checkpoints (report_audit gate, >1% deviation flag, grep scan) and feedback loops (verify facts, grade revision, cascade check), matching the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	It is a single-file skill with well-organized numbered sections, but the long 8-part template table, banned-words table, and revision checklist are inline rather than offloaded to reference files, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	11 / 12 Passed

Description

85%

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, complete, and well-differentiated, clearly stating both what the skill does and when to use it. Its main weakness is trigger-term naturalness — the phrasing is specialized rather than reflecting terms users would actually say.

Suggestions

Add common user-facing trigger phrases such as 'company writeup', 'stock deep dive', or 'long-form company analysis' so the description matches how users actually ask for this work.

Soften the self-referential 'The core IP is NOT writing but REVISING' framing in the description; lead with the user-visible outcome before the internal methodology.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — the eight named series parts and a fact-check checklist targeting pseudo-precision, absolute language, and cross-article number inconsistencies — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers 'what' (8-part revision-driven series sharing one framework) and 'when' via a 'Use when the user wants...' clause plus negative guidance naming rival skills, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Contains adjacent natural terms ('deep-dive', 'research report', 'earnings note', 'sector study') but the central trigger 'textbook-level depth on one company for public publishing' is specialized phrasing a user would rarely say, and common variations like 'stock writeup' or 'company analysis' are missing.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (publication-grade multi-part company series) and explicitly distinguishes itself from single research reports and earnings notes, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/deep-company-series/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.