cross-market-strategy

Write signal_engine.py for portfolios spanning multiple markets (A-shares + crypto, equity + forex, etc.)

Quality

69%

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/cross-market-strategy/SKILL.md

Quality

Content

72%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.

The content is a lean, highly actionable reference for cross-market strategy writing: executable code, concrete parameter tables, and a clear statement of what the engine handles so the strategy author doesn't duplicate it. Its main weaknesses are the absence of any verification step in the workflow and a Supporting Files link that points to a nonexistent file.

Suggestions

Fix or remove the example_signal_engine.py link — either ship the file in the bundle (e.g. under references/) or drop the Supporting Files section until it exists.

Add a short validation step, e.g. 'After writing signal_engine.py, run the config.json backtest and confirm each symbol is routed to the correct market loader before iterating on parameters.'

Define or point to MARKET_PARAMS / _detect_market / _market_signal (or note they live in the example file) so the generate() snippet is self-contained.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: 'Group symbols by market type and apply market-specific indicator parameters', a compact parameter table, and 'Different markets have very different dynamics. Using the same parameters everywhere produces poor results.' — no filler, no explanation of concepts Claude already knows, and every table/code block earns its tokens. This matches 'Lean and efficient; assumes Claude's competence; every token earns its place'.	5 / 5
Actionability	Mostly executable guidance: a concrete generate() implementation, a working _vol_adjust() implementation, a complete config.json example, and concrete parameter/detection tables. Minor gaps keep it below 5: MARKET_PARAMS, _detect_market, and _market_signal are referenced but never defined, and the linked complete example (example_signal_engine.py) does not exist in the bundle.	4 / 5
Workflow Clarity	The Key Concepts sections imply a workable sequence (classify markets → per-market params → vol-adjust → signal patterns → engine handles X), but it is concept-organized rather than an explicit ordered workflow, and there is no validation checkpoint (e.g. 'run the backtest and confirm the engine routes each symbol correctly'). This matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	The body has clear section structure and appropriately inlines the concise tables, and the 'Supporting Files' section clearly signals one reference — but that reference ('[example_signal_engine.py](example_signal_engine.py)') points to a file that is not present in the bundle (no references/, scripts/, or assets/ directories exist). Structure is present, yet the single external reference is broken and inlined content like the market-detection table could arguably live in the referenced example file, matching 'Some structure but could be better organized'.	3 / 5
	Total	15 / 20 Passed

Description

53%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 is specific and appropriately concise about what the skill produces, but it omits any explicit 'Use when' trigger guidance, capping its completeness. It also misses the natural trigger terms ('backtest', 'multi-asset', 'cross-market') that users would most likely say when needing this skill.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a backtest request includes codes from different markets, such as A-shares + crypto or equity + forex.'

Include natural trigger synonyms users would say — 'backtest', 'multi-asset', 'cross-market strategy' — alongside the market names already present.

State the concrete sub-actions the skill covers (market classification, per-market parameters, volatility-adjusted weighting) to broaden capability coverage without padding.

Dimension	Reasoning	Score
Specificity	The description names one concrete action — 'Write signal_engine.py for portfolios spanning multiple markets' — with concrete market instantiations '(A-shares + crypto, equity + forex, etc.)'. It stays at a single action rather than listing several, matching 'Names domain and 1-2 concrete actions, but not comprehensive' rather than the level-4 anchor 'Lists several specific actions'.	3 / 5
Completeness	The 'what' is clear (write signal_engine.py for multi-market portfolios), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is at best weakly implied by the market examples in parentheses.	3 / 5
Trigger Term Quality	Relevant keywords like 'portfolios', 'multiple markets', 'A-shares', 'crypto', 'equity', 'forex' are present, but common natural variations a user would say — 'backtest', 'multi-asset', 'cross-market strategy' — are absent, matching 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The cross-market portfolio framing plus the project-specific 'signal_engine.py' artifact gives it a fairly clear niche with distinct triggers, though it could overlap with a general single-market strategy-writing skill — matching 'Mostly distinct; minor overlap risk with closely related skills'.	4 / 5
	Total	13 / 20 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	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/cross-market-strategy/SKILL.md
Commit: 251b094

Reviewed: 3 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.