CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/strategy-dev-manager/SKILL.md
SKILL.md
Quality
Evals
Security

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-engineered orchestration skill body with an exemplary phased workflow, explicit validation checkpoints, and concrete thresholds. Its weaknesses are a bundle that doesn't match the documentation — broken template/example/src references and three orphaned reference files — plus minor internal repetition.

Suggestions

Ship the referenced `templates/factor_signal_engine.py` and `templates/strategy_signal_engine.py` (or remove the `templates/` references and inline the minimal template structure), since Phase 3 step 4 depends on them.

Add navigation to the three orphaned bundle files (e.g. link `references/strategy_extraction_guide.md`, `references/strategy_metrics.md`, and `references/scheduled_decay_scan.md` from the References section) or remove them from the bundle.

Fix or create the `examples.md` reference and deduplicate the IC deduplication thresholds, which are stated in both Phase 2 and the Common Pitfalls section.

DimensionReasoningScore

Conciseness

The body is dense with operational content — tool calls, thresholds, a code contract, pitfalls — and does not explain concepts Claude already knows. Minor trimming is possible: dedup IC thresholds appear in both Phase 2 ("Pearson IC ... exceeds 0.99") and Common Pitfalls, and the SignalEngine constraints repeat details already in the code block. This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean level-5 anchor.

4 / 5

Actionability

Guidance is highly concrete: parameterized tool calls, numeric thresholds ("IC mean > 0.03", "IR > 0.5"), an AST validation command, and a full SignalEngine contract. However, several executable pointers are broken — `templates/factor_signal_engine.py`, `templates/strategy_signal_engine.py`, `examples.md`, and `src/factors/base.py` do not exist in the bundle — leaving 'mostly executable guidance with minor gaps' rather than fully copy-paste ready.

4 / 5

Workflow Clarity

Five phases are clearly sequenced with a routing decision tree, explicit validation checkpoints (AST syntax validation, dedup IC check, OCR quality flags, evaluation thresholds), a Quality Checklist, and error-recovery guidance (formula hallucination handling, template mismatch recovery). This matches the level-5 anchor: clear sequence, explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

The body has a References section and points to `references/decay_thresholds.md` (which exists), but three referenced paths are missing (`examples.md`, `templates/`, `src/factors/base.py`) and three bundle files in `references/` (scheduled_decay_scan.md, strategy_extraction_guide.md, strategy_metrics.md) are never referenced from SKILL.md, leaving them undiscoverable. This fits 'some structure but could be better organized; references present but not clearly signaled' rather than the level-4 anchor with mostly-clear references.

3 / 5

Total

16

/

20

Passed

Description

75%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, third-person description that clearly communicates the skill's domain and lifecycle actions. Its main defect is the absence of any 'Use when...' trigger guidance, which caps completeness and weakens its value for skill routing.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user provides an academic paper or research report and wants to extract, backtest, validate, or monitor factors or strategies from it."

Add natural trigger phrasings users are likely to say, such as "extract factors from this paper", "backtest this strategy", or "check factor decay".

Consider dropping the redundant "Strategy Development Manager:" prefix (the name field already carries it) to free description budget for trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions spanning the full lifecycle — "convert academic papers and research reports into validated factors and strategies", "automated backtesting", "persistent storage", and "decay monitoring" — giving comprehensive coverage of what the skill does. It clearly matches the anchor for multiple specific concrete actions rather than the level-4 anchor, which anticipates gaps in coverage.

5 / 5

Completeness

The 'what' is clearly stated (paper-to-validated-strategy conversion with backtesting, storage, and decay monitoring), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete and specific, not vague.

3 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: "academic papers", "research reports", "factors", "strategies", "backtesting", "decay monitoring". A few natural phrasings are missing (e.g. "implement a factor", "validate a strategy", "quant research"), so it fits the 'good coverage with a few natural terms missing' anchor rather than the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The paper-to-factor/strategy pipeline with decay monitoring is a clear niche with distinct trigger terms; virtually no other skill would claim converting academic papers into backtested, monitored factors. It matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
HKUDS/Vibe-Trading
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.