seasonal

Seasonal/calendar-effect strategy. Generates trading signals from time-based patterns such as month-of-year effects and day-of-week effects. Suitable for any OHLCV data.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/seasonal/SKILL.md

Quality

Content

71%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-organized, token-efficient reference for a simple strategy: concrete parameters, sensible defaults, and genuinely useful pitfalls. The main gap is the absence of any executable signal-generation code, which leaves the implementation to be reconstructed from bullet-level logic.

Suggestions

Add a minimal executable example, e.g. a short pandas function mapping DatetimeIndex month/weekday membership to the 1/-1/0 signal convention.

Deduplicate the spring-rally and sell-in-May examples between the Purpose section and the Common Calendar Effects table.

Add a one-line validation note for conflicting parameters, e.g. that a month/weekday must not appear in both the bullish and bearish lists.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — parameter tables, pitfalls, and a signal convention with no filler — but the spring rally and sell-in-May effects are stated twice (Purpose prose and the reference table), a minor instance of tokens that could be trimmed. Not 5 because of that duplication; not 3 because every other section earns its place.	4 / 5
Actionability	Concrete parameter names with defaults and reference configurations (e.g. bullish_months=[1,2,3]) plus an explicit 1/-1/0 signal convention, but there is no executable code or function signature — the signal logic is described as bullets, essentially pseudocode. It is not 4 because nothing is copy-paste runnable and key details (input/output format) are left implicit.	3 / 5
Workflow Clarity	A single-purpose skill whose one action (map timestamp to long/short/flat) is unambiguous, with a pitfalls section covering the fragile spots (1-based months, 0-based weekdays, neutral months must output 0). Not 5 because there is no validation guidance for misconfiguration, e.g. a month appearing in both bullish_months and bearish_months.	4 / 5
Progressive Disclosure	The skill is a compact (~60 line) single-file body with no bundle files and no need for external references; sections are clearly labeled and every piece of content is appropriately sized and placed inline (purpose, logic, effects table, parameters, pitfalls, dependencies, convention).	5 / 5
	Total	16 / 20 Passed

Description

61%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 states a clear, specific capability in third person with good natural trigger terms, but it lacks any explicit 'when to use' guidance, which caps its completeness. Adding a trigger clause naming common seasonal effects would resolve the main gap.

Suggestions

Add a 'Use when...' clause, e.g. "Use when the user asks for seasonal, calendar-effect, or time-of-year trading strategies, or mentions effects like 'sell in May' or the January effect."

Include a few user-natural synonyms ("seasonality", "month-of-year effect", "time-based patterns") to broaden trigger coverage.

State what the skill outputs (e.g. a long/short/flat signal series) to sharpen the 'what' beyond a single action verb.

Dimension	Reasoning	Score
Specificity	"Generates trading signals from time-based patterns such as month-of-year effects and day-of-week effects" names the domain and one concrete action with two pattern types, matching the '1-2 concrete actions, not comprehensive' anchor. It is not 4 because it lists only a single action verb and omits what the skill produces or how it is configured.	3 / 5
Completeness	The 'what' is clear (generates trading signals from calendar patterns), but there is no 'Use when...' clause or equivalent; "Suitable for any OHLCV data" only weakly implies applicability. Per the rubric guideline, a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like "seasonal", "calendar-effect", "trading signals", "month-of-year", "day-of-week", and "OHLCV" give good keyword coverage, though common variations users might say ("seasonality", "January effect", "sell in May", "backtest") are missing.	4 / 5
Distinctiveness Conflict Risk	"Seasonal/calendar-effect strategy" carves out a distinct niche with minimal conflict risk, but the skill appears to belong to a family of trading-strategy skills that share phrases like "trading signals" and "any OHLCV data", leaving minor overlap risk with closely related strategy skills.	4 / 5
	Total	14 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/seasonal/SKILL.md
Commit: 251b094

Reviewed: 3 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.