earnings-review

AI Berkshire skill: 财报精读：一手资料深度解读. Source: skills/earnings-review.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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./codex-skills/earnings-review/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 well-sequenced, information-dense workflow with concrete tool commands and a genuine validation/feedback exit gate, scoring high on actionability and workflow clarity. Its main weakness is progressive disclosure: everything is inlined in one file and the referenced external files are not part of the skill bundle.

Suggestions

Move the tool-command references and the financial-data-source catalog into a bundled reference file (e.g. references/financial-data.md) and link to it with a clearly signaled 'See references/financial-data.md for source details' navigation pointer.

Bundle or stub the referenced tools (tools/financial_rigor.py, tools/report_audit.py) under scripts/ so the skill is self-contained, or clearly mark them as required external dependencies.

Tighten the epigraph quotes and 设计理念 section to leaner prose to reclaim a few tokens without losing the workflow signal.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic accounting explanations), with compact tables and minimal padding; only the epigraph quotes and design-rationale prose could be trimmed, fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Provides concrete executable commands (financial_rigor.py cross-validate, report_audit.py extract/verdict) and concrete input examples, but several steps are qualitative checklists and the verdict command leaves a placeholder JSON, so it is mostly executable with minor gaps.	4 / 5
Workflow Clarity	A clear 8-step sequence with an upfront data-availability grade, cross-validation checkpoints in step 2, and an explicit exit-gate validation step (第八步) with a 准出/打回 feedback loop and re-review, matching 'clear sequence with explicit validation steps and feedback loops'.	5 / 5
Progressive Disclosure	The skill is a single inlined SKILL.md with no bundle files (references/, scripts/, assets/ are absent), and inline references to external paths (skills/financial-data.md, tools/*.py) are not signaled as navigation links and point to files not present in this bundle, fitting 'some structure but references not clearly signaled and content that should be separate is inline'.	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 plus provenance metadata rather than a functional skill description; it names the niche but provides no concrete actions, no trigger phrases, and no usage guidance. It would rarely be selected by a user who needs the skill but does not already know its name.

Suggestions

Add concrete actions in third person, e.g. 'Extracts, cross-validates, and interprets first-hand earnings filings (10-K/10-Q, annual reports, call transcripts) to form an investment judgment.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'when the user asks to read or analyze an earnings report, quarterly results, 10-K, or earnings call'.

Remove the non-functional provenance line ('Source: skills/earnings-review.md') from the user-facing description.

Dimension	Reasoning	Score
Specificity	Names the domain ("AI Berkshire skill", "财报精读：一手资料深度解读") but lists no concrete actions such as extract, validate, or generate, matching the 'names domain but actions are minimal' anchor.	2 / 5
Completeness	Has only a vague 'what' (financial-report deep reading) and no 'when' guidance at all, fitting the 'vague what and no when' anchor; the missing 'Use when...' clause caps this low.	2 / 5
Trigger Term Quality	Contains only the domain label and a non-trigger meta line ("Source: skills/earnings-review.md"), missing the natural trigger phrases a user would say; no 'Use when...' clause or synonyms.	2 / 5
Distinctiveness Conflict Risk	The Berkshire/财报精读 framing gives a specific niche distinguishable from generic skills, but the thin trigger surface means it could still overlap with other finance/investment skills.	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/earnings-review/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.