strategy-dev-manager

Strategy Development Manager: convert academic papers and research reports into validated factors and strategies with automated backtesting, persistent storage, and decay monitoring.

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 ./agent/src/skills/strategy-dev-manager/SKILL.md

Quality

Content

77%

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

The body is highly actionable with a clear, well-validated multi-phase workflow, but it is somewhat verbose and its progressive-disclosure references are inconsistent with the actual bundle — several referenced files are missing and several real files are orphaned.

Suggestions

Reconcile references with the bundle: either add the missing examples.md, templates/factor_signal_engine.py, templates/strategy_signal_engine.py, and src/factors/base.py, or remove the dangling citations.

Surface the existing but unreferenced bundle files (scheduled_decay_scan.md, strategy_extraction_guide.md, strategy_metrics.md) in the References section so users can find them.

Trim the Tool Reference table or fold it into the phases to remove duplication with the inline tool call descriptions and improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is substantive and avoids explaining concepts Claude already knows, but the ~228 lines include redundancy — the Tool Reference table re-states tool roles already described inline in each phase — and could be tightened, matching 'mostly efficient but could be tightened.'	2 / 3
Actionability	Guidance is concrete and executable throughout: parameterized tool calls (e.g., create_hypothesis(title, thesis, universe, signal_definition)), explicit thresholds (IC mean > 0.03, IR > 0.5, Sharpe > 0.5), an AST validation command, and a complete SignalEngine contract with code.	3 / 3
Workflow Clarity	The five-phase workflow is clearly sequenced with explicit validation checkpoints (AST parse in Phase 3, threshold gates in Phase 4, OCR quality check), a decay state machine, error-recovery handling, and a quality checklist — matching the highest anchor.	3 / 3
Progressive Disclosure	A References section signals one-level-deep navigation, but several referenced paths do not exist (examples.md, templates/*.py, src/factors/base.py) while three real bundle files (scheduled_decay_scan.md, strategy_extraction_guide.md, strategy_metrics.md) are never surfaced, so navigation is partly broken.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and occupies a distinct niche, but it omits an explicit 'Use when...' trigger clause and leans on some technical phrasing, which limits trigger-term quality and completeness.

Suggestions

Add an explicit trigger clause such as 'Use when a user wants to turn a paper or research report into a backtested, monitored factor or strategy.'

Soften jargon like 'decay monitoring' and 'persistent storage' with user-natural variants (e.g., 'track factor decay over time', 'save factors for reuse').

Mirror the body's routing triggers (e.g., 'extract factors', 'run the backtest', 'check decay') so the description surfaces the phrasings users actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'convert academic papers and research reports into validated factors and strategies with automated backtesting, persistent storage, and decay monitoring' — matching the anchor for several specific actions rather than just naming a domain.	3 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relevant domain keywords are present ('academic papers', 'research reports', 'factors', 'strategies', 'backtesting'), but 'decay monitoring' and 'persistent storage' lean technical and the phrasing lacks common user-natural variations, so it sits at 'some relevant keywords' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The paper-to-validated-factor/strategy pipeline with backtesting and decay monitoring is a clear, specialized niche that is unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 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/strategy-dev-manager/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.