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

73%

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%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 well-sequenced, highly actionable multi-phase workflow with strong validation checkpoints and a clean code contract. Its main weakness is progressive disclosure: the reference layer is inconsistent, with orphaned bundle files and missing referenced paths.

Suggestions

Link all four references/ bundle files from the body (add strategy_extraction_guide.md, strategy_metrics.md, and scheduled_decay_scan.md to the References section) so no bundle file is orphaned.

Create the referenced templates/ directory with factor_signal_engine.py and strategy_signal_engine.py, or remove those references and inline the template contract instead.

Either add the missing examples.md bundle file or drop the reference to it from the References section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and operational — concrete tool calls, thresholds, and a code contract without padding concepts Claude already knows — though at ~225 lines a few sections (OCR check placement, Templates/References) could be trimmed.	4 / 5
Actionability	Concrete tool signatures with arguments, numeric thresholds (IC > 0.03, IR > 0.5, Sharpe > 0.5), an executable AST-validation command, and a complete SignalEngine contract; the main gap is that the referenced templates/*.py files do not actually exist in the bundle.	4 / 5
Workflow Clarity	Five clearly sequenced phases with numbered steps, explicit validation checkpoints (AST parse, threshold gates, OCR quality, dedup IC check), a self-check Quality Checklist, and feedback loops (re-run Phase 3 to recover decayed artifacts).	5 / 5
Progressive Disclosure	Structure is present (phases, Tool Reference table, References section), but references are not cleanly signaled: three of four bundle files in references/ (scheduled_decay_scan.md, strategy_extraction_guide.md, strategy_metrics.md) are never linked from the body, while the body references examples.md and templates/*.py that do not exist.	3 / 5
	Total	16 / 20 Passed

Description

70%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 clearly conveys a distinctive, well-scoped capability with strong domain keywords, but it omits an explicit "when to use" trigger clause, capping completeness. Adding a "Use when..." sentence referencing papers, research reports, or backtest requests would raise it.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user provides an academic paper or research report and wants extracted factors or strategies backtested and monitored."

Add a few natural synonyms/variations (e.g. "backtest a factor", "monitor alpha decay") to broaden trigger-term coverage toward a 5.

Consider naming the ingestion/extraction step explicitly ("ingest, extract, backtest, monitor") so the action list is more granular.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "convert academic papers and research reports into validated factors and strategies", "automated backtesting", "persistent storage", "decay monitoring" — but the lead action stays somewhat high-level compared to the granular multi-action anchor at 5.	4 / 5
Completeness	The "what" is clear and comprehensive, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good domain keyword coverage ("academic papers", "research reports", "factors and strategies", "backtesting", "decay monitoring") that users would naturally say, though it omits synonyms and any "Use when..." trigger phrasing.	4 / 5
Distinctiveness Conflict Risk	The niche — turning papers/reports into backtested, monitored quant factors and strategies — is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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: 1907e47

Reviewed: 1 day 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.