CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/trade-hypothesis-ideator/SKILL.md
SKILL.md
Quality
Evals
Security

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 concise, well-organized overview with executable commands, undermined by references to prompt and example files absent from the bundle, an undefined 'Step H' pointer, and no validation or feedback step for the batch export workflow.

Suggestions

Add the referenced prompts/*.md templates and examples/example_input.json to the bundle (or remove/correct the references) so the documented commands run as written.

Replace the opaque 'Step H strategy exporter' reference with an explicit, self-contained description of the export step within the numbered workflow.

Add a validation checkpoint after pass 2 (e.g., run the scripts/tests suite or verify exported strategy.yaml files parse) to create a feedback loop for the batch export.

DimensionReasoningScore

Conciseness

The ~60-line body is lean and assumes Claude's competence: no concept explanations, no padding, and every section (Prerequisites, Workflow, Scripts, Output, Resources) carries operational weight.

5 / 5

Actionability

Two complete copy-paste bash commands with flags are provided, but they reference 'examples/example_input.json' and three 'prompts/*.md' files that do not exist in the bundle, and 'Step H strategy exporter' is undefined — key execution details are missing.

3 / 5

Workflow Clarity

Steps 1-6 are coherently sequenced and mapped to the two script invocations, but there is no validation or verification step (the existing scripts/tests/ suite is never mentioned) and the batch export lacks a feedback loop, which the rubric caps at 3.

3 / 5

Progressive Disclosure

Good overview structure: both references/ files exist, are one level deep, and are signaled with purpose lines, and scripts are modularly split. Broken pointers to the nonexistent prompts/ and examples/ files and the undefined 'Step H' keep it below the top anchor.

4 / 5

Total

15

/

20

Passed

Description

82%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, specific description with explicit what/when structure and a well-defined niche. Its main deductions are the second-person voice in the trigger clause and incomplete coverage of the pipeline (the critique step is never mentioned).

Suggestions

Rewrite the trigger clause in third person, e.g. 'Use when a structured input bundle needs to be turned into ranked hypothesis cards', to satisfy the third-person voice requirement.

Mention the critique-and-revise pass among the described actions so the stated capabilities cover the full pipeline.

DimensionReasoningScore

Specificity

The description names several concrete actions ('Generate falsifiable trade strategy hypotheses', 'ranked hypothesis cards with experiment designs, kill criteria', 'optional strategy.yaml export') but omits the critique pass, and the second-person trigger clause 'Use when you have a structured input bundle and want...' incurs the rubric's third-person voice penalty (base 4, minus 1).

3 / 5

Completeness

Both what ('Generate falsifiable trade strategy hypotheses... ranked hypothesis cards... strategy.yaml export') and when ('Use when you have a structured input bundle and want ranked hypothesis cards') are explicitly stated with concrete trigger phrases, matching the top anchor's shape.

5 / 5

Trigger Term Quality

Natural terms like 'trade strategy hypotheses', 'market data', 'trade logs', 'journal snippets', 'kill criteria', and 'strategy.yaml' give good coverage, though common synonyms such as 'trading edge', 'backtest idea', or 'quant strategy' are missing.

4 / 5

Distinctiveness Conflict Risk

'Falsifiable trade strategy hypotheses' with 'strategy.yaml export compatible with edge-finder-candidate/v1' carves a clear niche with distinct triggers and minimal overlap risk against generic analysis or document skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

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.