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

86%

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

81%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 tightly structured, highly actionable process skill with strong validation gates and feedback loops well-matched to a multi-output batch operation. Minor gains are available in trimming restated lines and rendering tool invocations as full command lines.

Suggestions

Trim the closing 'One-liner' and a few checklist restatements that duplicate earlier sections to reach full token efficiency.

Render tool invocations (e.g. report_audit, financial_rigor) as complete copy-paste command lines rather than descriptions to lift actionability to 5.

Consider moving the banned-words table or the fact-check checklist into a reference file so SKILL.md reads as a leaner overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — tables for the part template and banned words carry a lot of signal per token, and it avoids explaining known concepts (Buffett/Munger, IFRS) — but the closing one-liner and a few checklist restatements could be trimmed; not a fully lean score-5.	4 / 5
Actionability	Gives concrete, executable guidance: named tools with specific commands (`report_audit command=verdict`, `financial_rigor command=cross_validate`), literal grep patterns, per-part word ranges, and a replacement table — minor gap is that tool invocations are described rather than given as full copy-paste command lines.	4 / 5
Workflow Clarity	Clear four-phase sequence (Research → Writing → Cross-Article Consistency Scan → Pre-publish Final Check) with explicit validation gates (PASS/FAIL verdict, >1% deviation flagging) and a revision cascade/grading loop, matching the score-5 anchor with explicit validation steps and error-recovery feedback loops for a batch operation.	5 / 5
Progressive Disclosure	No bundle files exist, so this is a single self-contained file; it is well-sectioned with clear headers and a template table, with content appropriately inline for a process skill — good structure but not the lean overview-pointing-to-references pattern of the score-5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

92%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 specific, well-triggered description that clearly scopes an unusual multi-part company-series skill and actively disambiguates it from neighboring research skills. Its only weakness is a slightly expert register that omits a few common positive synonyms.

Dimension	Reasoning	Score
Specificity	Names many concrete actions and components (cognitive reset, moat, profit engine, hidden assets, Buffett-style financials, valuation+redlines) plus a concrete revision checklist catching pseudo-precision, absolute language, and number inconsistencies — comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly states both what it does (write an 8-part series; revise via fact-check checklist) and when to use it ('Use when the user wants textbook-level depth on one company for public publishing'), matching the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases like 'deep-dive series on a single company', 'publication-grade', 'textbook-level depth on one company for public publishing', plus negative disambiguation triggers, but is missing some common synonyms (e.g. 'company analysis', 'equity research') as positive triggers — good but not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (multi-part long-form company series) and explicitly disambiguates from adjacent skills ('a single research report or earnings note is NOT this — use investment-research / earnings-review instead'), giving minimal conflict risk.	5 / 5
	Total	19 / 20 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: d71ed8d

Reviewed: 5 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.