strategy-generate

Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.

Quality

80%

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 ./agent/src/skills/strategy-generate/SKILL.md

Quality

Content

92%

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

The content is highly actionable and concise, with a clear validated workflow and concrete code/config examples — its main strength. Its weakness is progressive disclosure: a large single file with inline reference material and a dangling examples.md reference rather than well-split, real bundle files.

Suggestions

Move the full config.json field reference, market detection table, and validation options into a separate reference file (e.g. references/config_reference.md) and link to it from SKILL.md to reduce inline bulk.

Provide the referenced examples.md (or remove the link) so the one-level-deep reference resolves to a real bundle file.

Consider extracting the Review Criteria / Bug Categories detail into a references file, keeping SKILL.md as a lean overview pointing to detailed materials.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious domain specifics (config.json schema, instrument suffix rules, market routing table, OKX hyphen requirement, validation options) and assumes Claude's competence rather than explaining backtesting or what PE/PB are; it is not padded with known concepts (score 1) and only has minor redundancy (score 2), so it earns score 3.	3 / 3
Actionability	It provides a concrete SignalEngine contract with full signature, a complete copy-paste config.json example, an exact bash syntax-check command, and explicit hard gates — fully executable, specific guidance rather than pseudocode or vague direction (score 2).	3 / 3
Workflow Clarity	A clear 7-step numbered workflow includes an explicit syntax-check validation checkpoint, hard-gate review criteria, a quality checklist, and a fix → backtest → re-evaluate feedback loop for error recovery, matching the score-3 anchor; it is not just a listed sequence without checkpoints (score 2).	3 / 3
Progressive Disclosure	It is a ~200-line monolithic SKILL.md with large inline reference blocks (full config schema, market detection table, validation options) that could be split into separate files, and it references examples.md which is not present in the bundle (dangling reference); it is better organized than a wall of text (score 1) but lacks well-signaled, real one-level-deep references (score 3).	2 / 3
	Total	11 / 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 distinct, naming concrete create/backtest/evaluate actions in a clear niche, but it lacks a 'Use when...' trigger clause and offers limited keyword variation, which holds completeness and trigger quality at the mid-level. Adding explicit usage triggers and a few more natural trigger terms would lift both.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to build, backtest, or optimize a quant trading strategy.'

Broaden trigger terms to include common variations such as 'quant strategies', 'trading algorithms', 'algo backtesting', and 'strategy evaluation'.

Keep the current concrete action list but pair it with the when-to-use guidance so completeness can reach 3.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them" — matching the score-3 anchor for enumerating specific actions; it is not vague single-action language (score 2) nor abstract (score 1).	3 / 3
Completeness	It clearly answers 'what does this do' but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	It includes natural terms users would say ("trading strategies", "backtest") but offers limited variation coverage — missing common phrasings like "quant strategies" or "algo" — so it sits at 'some relevant keywords but missing common variations' rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	The niche — generating, backtesting, and evaluating quantitative trading strategies — is specific and distinct, unlikely to trigger for unrelated skills; not score 2 because it is not merely 'somewhat specific' and could not easily overlap with generic skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/strategy-generate/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.