earnings-revision

Earnings estimate revisions, guidance analysis, and post-earnings drift (PEAD) — track analyst consensus changes, earnings surprise patterns, and management guidance shifts for US/HK equities.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/earnings-revision/SKILL.md

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 content is lean, actionable, and well-sequenced with executable examples and checklists. Its only structural weakness is that everything lives in one file with no progressive disclosure to supporting references.

Suggestions

Split the detailed metric definitions and the output-format template into separate reference files (e.g. references/metrics.md, references/output-template.md) and link them from a concise overview section.

Keep the SKILL.md body as a lean overview pointing to those references so it stays within a reasonable token budget on load.

Dimension	Reasoning	Score
Conciseness	The body is dense with domain-specific tables, metrics, and code and assumes Claude's intelligence without explaining basic concepts like what earnings or PEAD are; every section earns its place.	3 / 3
Actionability	Provides executable code (SUE, revision breadth, dispersion, guidance scoring, earnings-quality dict) and concrete yfinance API calls, giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	Pre- and post-earnings checklists are explicitly sequenced, and the output format is templated; the analysis is non-destructive so validation checkpoints are not strictly required.	3 / 3
Progressive Disclosure	It is a single ~230-line monolithic file with no external references or file splitting; it is well-sectioned but content that could live in separate references (e.g. metric definitions, output template) is inline.	2 / 3
	Total	11 / 12 Passed

Description

60%

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 and domain-rich but stops short of providing explicit usage triggers. Adding a 'Use when...' clause naming how a user would request this would raise completeness and trigger-term quality.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when the user asks about analyst estimate revisions, earnings surprises, guidance changes, or post-earnings drift for US/HK equities.'

Add common natural-language trigger terms a user would actually say, such as 'earnings analysis', 'estimate revisions', or 'beat/miss tracking'.

Tighten the domain scoping in the trigger so it is unambiguous when to select this over a generic equity-analysis skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'track analyst consensus changes, earnings surprise patterns, and management guidance shifts' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	It clearly answers what the skill does but never states when Claude should use it; per the guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords exist ('earnings estimate revisions', 'guidance analysis', 'earnings surprise', 'PEAD', 'consensus') but it lacks common user phrasings and a 'Use when' trigger, so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	The earnings-revision/PEAD niche is fairly specific to US/HK equities, but without an explicit trigger clause it could still overlap with general analysis skills, so it is only somewhat distinguishable.	2 / 3
	Total	9 / 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/earnings-revision/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.