us-undervalued-growth-screener

Autonomously screen NYSE, Nasdaq, and NYSE American operating-company stocks for undervalued-growth/GARP opportunities using forward same-basis valuation, driver-derived EPS/FCF forecasts, primary-source financial verification, SBC and dilution controls, sector and cycle normalization, auditable candidate-pool coverage, and fail-closed final reporting. Use when asked to find, screen, rank, or refresh US undervalued-growth stocks, including minimal requests with no ticker list or parameters.

Quality

85%

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

73%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.

Exceptionally actionable and rigorously sequenced, with validation and repair loops at every stage and a genuine one-level-deep reference bundle. The main weakness is conciseness: budget/lane rules are repeated across four sections and dense diagnostic prose is inlined rather than kept in references, inflating the always-loaded body.

Suggestions

State the deep-dive budget and lane-coverage rules once (e.g., in Default Scope) and reference that section from the Overview, Completion Contract, and Result-Quality Controls instead of restating them in each place.

Move the partial-run diagnostic semantics (exit-2 marker verification, prior_decision/prior_selection archival, retry directory rules) into references/claude-code-execution.md, keeping only the exit-code meaning and one pointer in SKILL.md.

Consolidate inline version/migration warnings (v3.1–v3.5 mixing bans, the dated runtime fingerprint) into a short 'Version compatibility' note that points at the existing migration references.

Dimension	Reasoning	Score
Conciseness	The body runs ~620 lines with noticeable padding: the deep-dive budget/lane rules are restated in at least four sections (Overview, Autonomous Completion Contract item 8, Default Scope, Result-Quality Controls), and the ~400-word partial-run diagnostic paragraph duplicates content deferred to references/claude-code-execution.md. Not 3: the repetition and inline duplication go beyond 'could be tightened'; not 1: it never explains concepts Claude already knows — the detail is domain-specific and operational.	2 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready bash invocations with real flags for every pipeline stage, exact exit-code semantics (exit 2 = continue), numeric thresholds (ROIC >= 8%, Net Debt/EBITDA <= 3.0x, diluted-share CAGR <= 5%), and concrete expected outputs ("contract.valid = true"). Not 4: there are no gaps — commands, thresholds, and expected results are all specified.	5 / 5
Workflow Clarity	A numbered 17-step Autonomous Completion Contract plus Workflow Steps 1–7, each with explicit validation gates (runtime preflight fingerprints, strict evaluation, prepublish audit) and genuine feedback loops ("repair every obtainable blocker and rerun", "If the command exits 2, inspect ... continue enrichment ... and rerun"). Not 4: checkpoints and error-recovery loops are present at every stage, not just most.	5 / 5
Progressive Disclosure	Good structure: the body stays an operational overview and defers detail to a Resources section enumerating real, one-level-deep reference files (all verified to exist). Not 5: substantial contract detail — the forecast-bridge arithmetic, source-field requirements, and partial-run diagnostic semantics — is inlined in SKILL.md rather than split into the existing references, leaving the main file heavier than a clear overview.	4 / 5
	Total	16 / 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 strong description: concrete, comprehensive, third-person, and explicitly gated with a natural 'Use when' trigger clause covering minimal requests. The only weakness is moderate synonym coverage for trigger terms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "screen NYSE, Nasdaq, and NYSE American operating-company stocks", "driver-derived EPS/FCF forecasts", "primary-source financial verification", "SBC and dilution controls", "sector and cycle normalization", "fail-closed final reporting" — with comprehensive coverage of the pipeline. Not 4: no minor gaps in capability coverage exist; every major pipeline stage is named.	5 / 5
Completeness	Both what (detailed multi-clause capability description) and when ("Use when asked to find, screen, rank, or refresh US undervalued-growth stocks, including minimal requests") are explicitly stated with concrete triggers. Not 4: the when-clause is already explicit and specific, not merely present.	5 / 5
Trigger Term Quality	"Use when asked to find, screen, rank, or refresh US undervalued-growth stocks" provides good natural-verb coverage plus the synonym "GARP". Not 5: common user phrasings like "value stocks", "cheap growth stocks", or "stock screener" are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche — US-listed undervalued-growth/GARP screening on named exchanges — with distinct trigger verbs (find/screen/rank/refresh a universe of stocks) that do not collide with single-ticker analysis or other screening styles. Not 4: overlap risk with adjacent skills is minimal, not minor-but-present.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (638 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: tradermonty/claude-trading-skills
Path: skills/us-undervalued-growth-screener/SKILL.md
Commit: eab8d5c

Reviewed: 1 day 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.