CtrlK
BlogDocsLog inGet started
Tessl Logo

kanchi-dividend-sop

Convert Kanchi-style dividend investing into a repeatable US-stock operating procedure. Use when users ask for かんち式配当投資, dividend screening, dividend growth quality checks, PERxPBR adaptation for US sectors, pullback limit-order planning, or one-page stock memo creation. Covers screening, deep dive, entry planning, and post-purchase monitoring cadence.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable SOP body with strong workflow validation and clean one-level-deep progressive disclosure across verified bundle files. Its main weakness is conciseness: the same rules are restated across Prerequisites, Steps, and Guardrails, and internal review-artifact codes add tokens without execution value.

Suggestions

Deduplicate guidance repeated across sections: keep the input-source priority, --yield-floor warning, regular-forward-yield rule, and failed/skipped-event-scan rule in one canonical place and have Guardrails reference rather than restate them.

Remove or relocate internal review-artifact references (defect codes D3/D4/D5, 'CFR D5 fix', 'FITB/Comerica golden case', 'MKC-Unilever miss') that do not help Claude execute the workflow, or move them into a references/CHANGELOG.md.

Trim the two JSON input examples and the surrounding handoff-shape paragraph to the single most common shape, pointing to a reference for the variants.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept over-explanation, but weakened by redundancy (input source priority appears in both 'Input Sources' and Step 2; the --yield-floor warning, the regular-yield rule, and the failed/skipped-event-scan rule are each restated in Guardrails) and internal artifact codes (D3/D4/D5, 'CFR D5 fix', 'FITB/Comerica golden case', 'MKC-Unilever miss') that pad tokens without aiding execution. Not 3 because the redundancy and review-artifact references could be tightened; not 1 because it does not explain concepts Claude already knows.

2 / 3

Actionability

Provides copy-paste-ready commands with real flags, paths, and tickers (e.g. build_entry_signals.py --tickers "JNJ,PG,KO" --alpha-pp 0.5 --yield-floor 3.0 --profile balanced --events-json ...) plus concrete JSON input formats, exact verdict tiers, and precise thresholds (40/30/30 sizing, ±0.20pp freshness, 4.0/3.0/1.5% floors). Matches the fully-executable anchor.

3 / 3

Workflow Clarity

A clearly numbered 1-8 sequence (with 6b) carrying explicit fail-safe validation at nearly every gate — Data Freshness Gate => STEP1-RECHECK, adjusted_eps_source=UNAVAILABLE => HOLD-REVIEW, pessimistic cap => HOLD-REVIEW + T1 BLOCKED, pre-order blocker downsizing — plus a test merge-gate (test_golden_p0.py) and a re-run cadence as feedback. Not 2 because the checkpoints are explicit and pervasive, not implicit.

3 / 3

Progressive Disclosure

References are real, one-level-deep, and signaled inline at each step (Load references/default-thresholds.md; Use references/sector-step2-modules.md) with a consolidated Resources section giving per-file descriptions; deep detail (thresholds, sector modules, valuation rules, memo template) is appropriately pushed into references/scripts rather than nested. Not 2 because the references are clearly signaled and the split is appropriate, though some inline defect-code detail borders on content that could be separated.

3 / 3

Total

11

/

12

Passed

Description

100%

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 that answers both what the skill does and when to use it, with concrete actions and the native-language trigger term 'かんち式配当投資' giving it a distinct, low-conflict niche. It is concise, third-person, and free of vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'dividend screening', 'dividend growth quality checks', 'PERxPBR adaptation for US sectors', 'pullback limit-order planning', 'one-page stock memo creation' — matching the multi-action anchor; not 2 because coverage is comprehensive rather than partial.

3 / 3

Completeness

Explicitly states both what ('Convert ... into a repeatable US-stock operating procedure ... Covers screening, deep dive, entry planning, and post-purchase monitoring cadence') and when ('Use when users ask for ...'); not 2 because the 'when' clause is explicit, not merely implied.

3 / 3

Trigger Term Quality

Includes the exact natural user phrase 'かんち式配当投資' plus natural English variants like 'dividend screening' and 'pullback limit-order planning'; not 2 because common variations are present rather than missing.

3 / 3

Distinctiveness Conflict Risk

Anchored to a clear niche via 'Kanchi-style dividend investing', 'かんち式配当投資', and 'PERxPBR adaptation for US sectors' — distinct triggers unlikely to fire for unrelated skills; not 2 because the niche is highly specific, not merely 'somewhat specific'.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
tradermonty/claude-trading-skills
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.