strategy-pivot-designer

Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.

Quality

75%

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 ./skills/strategy-pivot-designer/SKILL.md

Quality

Content

76%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.

The body is well-structured and highly actionable with executable commands and a clear workflow, supported by real reference and script bundles. The main gap is the absence of explicit validation checkpoints in the workflow.

Suggestions

Add explicit validation checkpoints to the workflow, e.g. after stagnation detection verify the diagnosis JSON exists and is non-empty before running generate_pivots, and validate generated pivot YAML against references/pivot_proposal_schema.md before export.

Replace the flat Resources path list with contextually signaled links inline (e.g. in the workflow, 'see references/pivot_techniques.md for the inversion rules') so navigation is discoverable without scanning a separate section.

De-duplicate the Resources section against Quick Commands by listing only the reference and asset files there, since the script paths already appear in the command blocks.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows; minor redundancy comes from the Resources section re-listing script paths already shown in Quick Commands.	4 / 5
Actionability	Three copy-paste-ready command blocks with real flags, file paths, and arguments cover the common cases (append-eval, detect stagnation, generate pivots), plus a concrete numbered workflow.	5 / 5
Workflow Clarity	A clear 7-step sequence with an end feedback loop exists, but validation checkpoints are implicit/missing (e.g., verify the diagnosis JSON before generating pivots, validate generated YAML against the schema), which the batch-generation context calls for.	3 / 5
Progressive Disclosure	Good structure with one-level-deep references to real bundle files (stagnation_triggers, strategy_archetypes, pivot_techniques, pivot_proposal_schema) and a Resources list, but references are a flat path list rather than contextually signaled links inline.	4 / 5
	Total	16 / 20 Passed

Description

73%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 is third-person, concise, and clearly distinguishes the skill with both a 'what' and a 'when' clause. Its main limitation is moderate action coverage and a single trigger phrase rather than multiple.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Detect backtest iteration stagnation' and 'generate structurally different strategy pivot proposals'), but stops at two actions rather than listing several, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Clearly states what it does (detect stagnation, generate pivots) and an explicit when clause ('when parameter tuning reaches a local optimum'), but the trigger is singular rather than multiple concrete trigger phrases.	4 / 5
Trigger Term Quality	Strong natural domain terms ('backtest', 'stagnation', 'parameter tuning', 'local optimum', 'strategy pivot') that a user would plausibly say, but no synonyms or file extensions for full coverage.	4 / 5
Distinctiveness Conflict Risk	A narrow, well-defined niche (backtest stagnation detection + strategy pivot generation) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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/strategy-pivot-designer/SKILL.md
Commit: 51c7907

Reviewed: ~6 hours 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.