CtrlK
BlogDocsLog inGet started
Tessl Logo

strategy-generate

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

60

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/strategy-generate/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 highly actionable, well-sequenced workflow doc with excellent validation checkpoints and copy-paste-ready contracts, examples, and criteria. Its weaknesses are moderate redundancy (crypto rules and defaults repeated across sections) and a monolithic single-file layout whose only external references are broken.

Suggestions

State the crypto pair format rule once (in Instrument Code Normalization) and reference it from Cryptocurrency Notes and the Market Detection table, and similarly mention defaults (initial_cash, commission) only in the config.json section.

Fix the broken references: either ship examples.md in the bundle (with the example call sequence) and the cross-market-strategy skill, or remove the Supporting Files and cross-skill links.

Move the stable reference material — the config.json field reference, validation options, and market-detection table — into a references/ file (e.g., references/config.md) linked one level deep from SKILL.md, keeping the workflow and SignalEngine contract inline.

DimensionReasoningScore

Conciseness

The body is mostly lean, task-specific guidance with no padding about concepts Claude already knows, but it could be tightened: the crypto "XXX-USDT (uppercase + hyphen)" rule is stated three times (Instrument Code Normalization, Cryptocurrency Notes, and the Market Detection table), and defaults (initial_cash 1,000,000, commission 0.1%) appear in both Strategy Design and the config.json section. Matches "mostly efficient but includes some unnecessary explanation or could be tightened".

3 / 5

Actionability

Fully executable throughout: an exact syntax-check command (`python -c "import ast; ast.parse(...)"`), a complete `SignalEngine` contract with signal semantics, a copy-paste `config.json` example, exact regex patterns per market, and explicit hard-gate thresholds and `action_items` examples. Matches "fully executable; copy-paste ready".

5 / 5

Workflow Clarity

The 7-step numbered workflow sequences parsing → design → coding → syntax check → backtest → evaluation → iteration, with explicit validation checkpoints (step 4 syntax check, Hard Gates, Quality Checklist) and a feedback loop ("modify with `edit_file` → run `backtest` → re-evaluate") for error recovery. Matches the clear-sequence-with-explicit-validation anchor.

5 / 5

Progressive Disclosure

All ~190 lines of detail (config reference, validation options, market-detection table, review criteria) are inlined in SKILL.md with no bundle files, and the only references — "[examples.md](examples.md)" and "../cross-market-strategy/SKILL.md" — point at files that do not exist in the bundle, a broken reference. Matches "some structure; references present but not backed by real files; content that should be separate is inline".

3 / 5

Total

16

/

20

Passed

Description

66%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 concise, third-person description naming a distinct niche with several concrete verbs, but it omits any "Use when..." trigger guidance, which both caps completeness and weakens discoverability. Adding trigger phrases (e.g., "Use when the user wants to backtest, optimize, or evaluate a trading or investment strategy") would lift the two capped dimensions.

Suggestions

Append a trigger clause such as "Use when the user asks to backtest, optimize, or evaluate a trading strategy, mentions quant/algo trading, or wants to test an investment idea on historical data" to fix the completeness cap.

Add natural synonyms users actually say ("algorithmic trading", "algo strategy", "trading bot", "walk-forward test") to broaden trigger-term coverage.

Name one or two concrete outputs (e.g., "...and produce metrics, equity curves, and validation statistics") to push specificity from several-actions to comprehensive.

DimensionReasoningScore

Specificity

"Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them" lists several concrete actions (create, modify, optimize, backtest, evaluate), matching the several-specific-actions-with-minor-gaps anchor. Not 5 because the actions remain high-level (no signals, instruments, config, or artifacts named); not 3 because it covers more than 1-2 actions.

4 / 5

Completeness

The "what" is clear (create/optimize/backtest trading strategies) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"quantitative trading strategies", "backtest", and "optimize" are phrases users naturally say, giving good keyword coverage. Not 5 because common synonyms like "algorithmic trading", "algo", or "trading bot" are missing; clearly above the generic-keyword-only anchors.

4 / 5

Distinctiveness Conflict Risk

"Quantitative trading strategies" + "backtest" carves out a clear niche unlikely to trigger the wrong skill, matching "mostly distinct; minor overlap risk". Not 5 because without trigger phrases the boundary against generic data-analysis or trading-execution skills is slightly softer.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
charliedream1/ai_quant_trade
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.