kanchi-dividend-review-monitor

Monitor dividend portfolios with Kanchi-style forced-review triggers (T1-T5) and convert anomalies into OK/WARN/REVIEW states without auto-selling. Use when users ask for 減配検知, 8-Kガバナンス監視, 配当安全性モニタリング, REVIEWキュー自動化, or periodic dividend risk checks.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/kanchi-dividend-review-monitor/SKILL.md

Quality

Content

68%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.

A well-structured, actionable skill body that makes good use of a real one-level-deep reference bundle. Its main weakness is the absence of any validation/verification checkpoint in a batch workflow, plus a small amount of inline detail that should be split out.

Suggestions

Add a validation step to the workflow (e.g., step 5: run `python3 scripts/tests/test_build_review_queue.py` and verify the output JSON against `references/input-schema.md`), since batch processing without verification caps workflow clarity.

Move the detailed SEC fetch procedure (endpoints, T4 keyword family, scan-window recording rules) out of the 'SEC Filing Guardrail' section into a file under `references/` and link to it from the body.

Fix the run command to use the bundle-relative script path (`scripts/build_review_queue.py`) so it is executable regardless of repo layout.

Dimension	Reasoning	Score
Conciseness	The body is an efficient section/bullet structure with no re-explanation of known concepts; only minor trims are needed (the flat-dividend caveat prose and the dense inline SEC guardrail paragraph).	4 / 5
Actionability	Provides an exact runnable command with arguments, concrete input field lists, a defined OK/WARN/REVIEW state machine, dated output filenames, and specific SEC endpoints — the one gap is that the script path ('skills/kanchi-dividend-review-monitor/scripts/...') assumes a repo layout instead of the bundle-relative path.	4 / 5
Workflow Clarity	The four-step workflow is clearly sequenced with a concrete command, but this is a batch operation (per-ticker processing of a whole portfolio) and no validation or verification step exists — no input-schema check, output verification, or 'run the unit tests' checkpoint — which caps this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	The bundle is well organized (three real references plus script and tests, all one level deep and signaled both inline and in a Resources section), but the ~150-word inline SEC fetch procedure (URLs, keyword family, scan-window rules) is operational detail that belongs in a references/ file.	4 / 5
	Total	15 / 20 Passed

Description

83%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 with a clear what/when structure, third-person voice, and natural (Japanese) trigger phrases. Its only weaknesses are modest: slightly incomplete action coverage and no disambiguation from closely related sibling skills.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'Monitor dividend portfolios', 'forced-review triggers (T1-T5)', 'convert anomalies into OK/WARN/REVIEW states without auto-selling' — with minor coverage gaps (e.g., 8-K/governance keyword scanning is only implied via a trigger term).	4 / 5
Completeness	Explicitly answers both 'what' (monitor with T1-T5 triggers, route to OK/WARN/REVIEW states) and 'when' via a concrete 'Use when users ask for...' clause listing five trigger phrases.	5 / 5
Trigger Term Quality	'減配検知', '8-Kガバナンス監視', '配当安全性モニタリング', 'REVIEWキュー自動化', and 'periodic dividend risk checks' are natural phrases a user would say, though common English variants like 'dividend cut' or 'dividend safety' are missing.	4 / 5
Distinctiveness Conflict Risk	The T1-T5 forced-review routing and no-auto-sell framing occupy a clear niche, but sibling skills like kanchi-dividend-sop cover adjacent dividend-review territory and the description does not disambiguate against them.	4 / 5
	Total	17 / 20 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
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: tradermonty/claude-trading-skills
Path: skills/kanchi-dividend-review-monitor/SKILL.md
Commit: eab8d5c

Reviewed: 8 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.