CtrlK
BlogDocsLog inGet started
Tessl Logo

earnings-preview

Build pre-earnings analysis with estimate models, scenario frameworks, and key metrics to watch. Use before a company reports quarterly earnings to prepare positioning notes, set up bull/bear scenarios, and identify what will move the stock. Triggers on "earnings preview", "what to watch for [company] earnings", "pre-earnings", "earnings setup", or "preview Q[X] for [company]".

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is earnings-preview in anthropics/financial-services

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is a lean, well-sequenced five-step workflow with concrete metric checklists, scenario/catalyst templates, and a defined output format, with essentially no wasted tokens. It falls just short of top marks on actionability and workflow clarity for lacking a worked example and any explicit verification step.

Suggestions

Add a worked example — e.g., one filled bull-scenario row or a sample catalyst checklist entry — so the output format is unambiguous and copy-paste ready.

Specify how to source the options-implied move (e.g., a concrete web search string, matching the one already provided for earnings reaction history).

Add an explicit verification checkpoint before writing the output, such as confirming the earnings date and estimate freshness from a second source.

DimensionReasoningScore

Conciseness

Every section is directive rather than explanatory — 'Pull consensus estimates via web search (revenue, EPS, key segment metrics)', sector-specific metric checklists, and template tables with no conceptual padding. No section explains things Claude already knows, so nothing could be trimmed without losing guidance; this matches the 'lean and efficient, every token earns its place' anchor.

5 / 5

Actionability

Guidance is concrete and executable: a five-step workflow, a ready-made search string ('search for "[company] earnings reaction history"'), scenario and catalyst table templates, and a defined one-page output format. It falls short of the top anchor because there is no worked example (e.g., a filled scenario row or sample catalyst entry) and the sourcing of the options-implied move mentioned in the output spec is never specified.

4 / 5

Workflow Clarity

The five steps (Gather Context, Key Metrics Framework, Scenario Analysis, Catalyst Checklist, Output) are clearly sequenced, and partial checkpoints exist ('always note the source and date of estimates', 'compare to your scenarios' for calibration). No explicit validation step is present (e.g., confirming the earnings date or estimate freshness before writing), which keeps it at 'clear sequence with most checkpoints present' rather than the top anchor.

4 / 5

Progressive Disclosure

A single self-contained, well-organized file with clearly labeled step sections; the workflow needs no external references and nothing is inlined that clearly belongs in a separate file. Navigation is trivial, matching the 'well-organized sections' standard for a lean single-file skill.

5 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: concrete capabilities, an explicit 'Use before...' trigger condition, and natural trigger phrases covering synonyms and quarter-specific variants. It closely matches the structure and quality of the strongest reference examples.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'estimate models, scenario frameworks, and key metrics to watch', 'prepare positioning notes, set up bull/bear scenarios, and identify what will move the stock' — with comprehensive coverage of the skill's capabilities. It matches the 'multiple specific concrete actions; comprehensive coverage' anchor rather than the 4 anchor, which requires minor coverage gaps.

5 / 5

Completeness

It explicitly answers both questions: what ('Build pre-earnings analysis with estimate models, scenario frameworks, and key metrics to watch') and when ('Use before a company reports quarterly earnings'), plus concrete trigger phrases ('Triggers on ...'). This exactly matches the top anchor's requirement of an explicit what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Trigger phrases are natural user phrasings with good synonym and variant coverage: 'earnings preview', 'what to watch for [company] earnings', 'pre-earnings', 'earnings setup', and 'preview Q[X] for [company]'. These are the phrases a user would naturally say when needing this skill, matching the comprehensive top anchor.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche — pre-earnings positioning analysis — with distinct, earnings-specific triggers ('earnings preview', 'pre-earnings', 'earnings setup') that are unlikely to fire for general stock-research or post-earnings tasks, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

20

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/financial-services
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.