canslim-screener

Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user requests CANSLIM stock screening, growth stock analysis, momentum stock identification, or wants to find stocks with strong earnings and price momentum following O'Neil's investment system.

Quality

87%

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

Quality

Content

85%

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

The content is highly actionable with a well-sequenced, validation-backed workflow and solid progressive disclosure to real bundle files. Its main weakness is verbosity from redundant repetition of prerequisites, API budget, and phase-status details across sections.

Suggestions

Remove the duplicate prerequisites/API-budget block in Step 1 (it already appears in the Overview/Prerequisites section) to tighten conciseness.

Collapse the 'Important Notes' phase-status checklist — it restates the Overview's component/weight table verbatim; a one-line pointer would suffice.

Trim the full Markdown report template in Step 6, which largely duplicates the 'Report Contents'/'Report Structure' sections earlier in the file.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but ~660 lines carries avoidable redundancy — prerequisites/API budget appear in both the Overview and Step 1, the Phase-3 status is restated in 'Important Notes', and the full report template plus troubleshooting largely restate earlier material.	2 / 3
Actionability	Concrete, copy-paste-ready commands with real flags and paths are given throughout ('python3 screen_canslim.py --api-key $FMP_API_KEY --max-candidates 40 --top 20'), and calculator/scorer responsibilities are enumerated, leaving no ambiguity about what to run.	3 / 3
Workflow Clarity	Six numbered steps are clearly sequenced with explicit validation checkpoints — API-key verification in Step 1, the M=0 bear-market gate, and troubleshooting feedback loops (429 retry, Finviz graceful degradation) for the batch/destructive-adjacent operations.	3 / 3
Progressive Disclosure	The body is an overview pointing to four real, one-level-deep reference files (verified present) and a cleanly split scripts/calculators/ tree, each clearly signaled with size and purpose, with inline guidance on which to consult first.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 well-formed: third person, explicit 'Use when' trigger guidance, and strong natural-language trigger terms. It is slightly short of fully listing multiple distinct concrete actions, but otherwise hits the rubric's top anchors.

Dimension	Reasoning	Score
Specificity	Names the domain ('CANSLIM growth stock methodology') and the core action ('Screen US stocks', 'find stocks with strong earnings and price momentum'), but these are variations of a single screening action rather than the multiple distinct concrete actions the level-3 anchor requires.	2 / 3
Completeness	Explicitly states both what it does ('Screen US stocks using William O'Neil's CANSLIM growth stock methodology') and when to use it via a clear 'Use when user requests...' clause.	3 / 3
Trigger Term Quality	Covers natural user phrasing well — 'CANSLIM stock screening', 'growth stock analysis', 'momentum stock identification', 'stocks with strong earnings and price momentum' — matching several ways a user would actually request this.	3 / 3
Distinctiveness Conflict Risk	The CANSLIM/O'Neil niche is specific and clearly distinct; the body's 'When NOT to Use' section further steers value/dividend cases to sibling screeners, minimizing cross-triggering.	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
skill_md_line_count	SKILL.md is long (672 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: tradermonty/claude-trading-skills
Path: skills/canslim-screener/SKILL.md
Commit: 62a1635

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.