trade-hypothesis-ideator

Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.

Quality

75%

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/trade-hypothesis-ideator/SKILL.md

Quality

Content

65%

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

The skill body is concise and well-organized with executable commands, but several referenced artifacts (prompts directory, example input, "Step H" anchor) are missing from the bundle, weakening actionability and navigation.

Suggestions

Add the missing `prompts/` directory and `examples/example_input.json` to the bundle (or remove the references from the body) so the documented commands run as written.

Replace the dangling "Step H strategy exporter" cross-reference with a concrete, anchored step so the workflow is self-contained.

Add an explicit validation/checkpoint step for the batch ranking + export pass (e.g., verify generated cards and strategy.yaml against expected schema before declaring success) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — short sections, executable command blocks, and no padding or explanation of concepts Claude already knows — so every token earns its place.	3 / 3
Actionability	It provides concrete `python3 ...` commands with flags, but those commands reference files that are absent from the bundle ("examples/example_input.json") and the workflow cites "prompts/system_prompt.md" and "Step H strategy exporter" that do not exist, so the guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	The six-step sequence is present and ordered, but it relies on undefined cross-references ("Step H", pass 1/pass 2 framing) and offers no explicit validation checkpoint for the batch card-generation and export operations, capping it below the top anchor.	2 / 3
Progressive Disclosure	The Resources section cleanly signals two real one-level-deep reference files, but the body also points to missing paths ("prompts/", "examples/example_input.json"), so navigation is only partly reliable and structure is undermined.	2 / 3
	Total	9 / 12 Passed

Description

85%

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, concrete description that clearly states capabilities and an explicit use-when trigger. Its only weakness is leaning on internal schema jargon ("edge-finder-candidate/v1") that is unlikely to be a natural user phrase.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Generate falsifiable trade strategy hypotheses", "ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export" — matching the anchor for naming several specific concrete actions.	3 / 3
Completeness	It answers both what the skill does and when to use it with an explicit "Use when you have a structured input bundle and want ranked hypothesis cards..." trigger, matching the anchor for clearly answering both what AND when.	3 / 3
Trigger Term Quality	It includes relevant natural terms ("market data", "trade logs", "journal snippets", "hypotheses") but pairs them with technical jargon ("edge-finder-candidate/v1", "strategy.yaml") that a user would not naturally say, so it stops short of full natural-term coverage.	2 / 3
Distinctiveness Conflict Risk	The trade-strategy hypothesis niche with its specific triggers is clearly distinguishable from other skills and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/trade-hypothesis-ideator/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.