edge-strategy-designer

Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.

Quality

72%

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/edge-strategy-designer/SKILL.md

Quality

Content

87%

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

The body is a lean, actionable overview with executable commands and well-structured one-level-deep references to real bundle files; its main weakness is the absence of any validation or verification step in an otherwise clear batch-generation workflow.

Suggestions

Add an explicit validation step to the workflow, e.g. 'Verify generated drafts against the schema (references/strategy_draft_schema.md) and confirm RR >= RR_FLOOR before exporting tickets,' with a fix-and-retry loop.

Optionally point to the existing scripts/tests/ suite or a verification command so Claude can sanity-check drafts after generation.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no definitions of known concepts, tight Overview/When-to-Use bullets, and high-signal workflow steps referencing real knobs (HYPOTHESIS_EXIT_OVERRIDES, RR_FLOOR=1.5); the only minor redundancy is the short Resources list, which serves navigation rather than padding.	3 / 3
Actionability	Two complete, copy-paste-ready 'python3 ...' invocations with all flags (--concepts, --output-dir, --risk-profile, --exportable-tickets-dir) are provided, and workflow steps cite real, existing config knobs and scripts.	3 / 3
Workflow Clarity	The seven workflow steps are clearly sequenced, but this is a batch YAML-generation operation with no validation or verification checkpoint and no fix-and-retry feedback loop, which caps workflow_clarity at 2 per the rubric's batch-operation guideline.	2 / 3
Progressive Disclosure	The SKILL.md is a concise overview that points one level deep to a real, clearly signaled reference (references/strategy_draft_schema.md) and the real script (scripts/design_strategy_drafts.py), with schema detail appropriately split out of the main file and no nested-reference chains.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 conveys a clear, domain-specific purpose with concrete deliverables and a distinct niche, but it omits any explicit 'when to use' trigger guidance and leans on technical jargon rather than natural user phrasing.

Suggestions

Append an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when you have edge_concepts.yaml and need strategy draft variants or exportable ticket YAMLs.'

Soften proprietary jargon with a few natural terms a user would actually say (e.g. 'strategy drafts', 'trade tickets') alongside the pipeline terminology.

Expand 'Convert ... into ...' into one or two more concrete actions (e.g. 'generate per-concept variants and calibrate exits by hypothesis type') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete deliverables ('strategy draft variants' and 'optional exportable ticket YAMLs'), but the verb 'Convert ... into ...' is abstract and lacks an enumeration of the specific transformations performed, so it is not comprehensive enough for a 3.	2 / 3
Completeness	The 'what' is clearly stated, but there is no 'Use when...' clause or any explicit trigger guidance for when to invoke the skill, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Relevant niche keywords appear ('edge concepts', 'strategy draft', 'ticket YAMLs') but the phrasing is heavily proprietary jargon ('edge-candidate-agent export/validation') rather than natural user language, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The proprietary pipeline vocabulary ('edge concepts', 'strategy draft variants', 'edge-candidate-agent export/validation') carves a clear niche unlikely to trigger unrelated skills, distinguishing it from generic data or document skills.	3 / 3
	Total	9 / 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/edge-strategy-designer/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.