CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quant-etf-review

Use when the user asks for multi-agent ETF strategy review, fund exposure, tracking error or liquidity checks on an existing backtest.

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 body is an exemplary lean operational skill: exact CLI invocations, a run-once workflow with pre-flight checks and failure-evidence handling, and clean one-level references. The only nit is that the referenced shared guide and example YAML live in the target platform project, so their contents cannot be verified from this bundle.

DimensionReasoningScore

Conciseness

Every line is an instruction or guardrail ('Run `python egs/skills.py run --config <task.yaml> --format jsonl` once', 'Do not fabricate AR/IC/drawdown') with no concept explanations or padding. It assumes Claude's competence throughout — tracking error, JSONL and providers are never explained — so every token earns its place.

5 / 5

Actionability

Gives exact, copy-paste-ready commands for the whole workflow (`python egs/skills.py preview --config <task.yaml>`, `providers --probe`, `run --config <task.yaml> --format jsonl`) plus named follow-up subcommands (`show`, `events`, `files`, `cancel`) and a concrete example config path (`egs/skills_examples/quant-etf-review.yaml`), covering the common cases. Not 4: nothing on the main path is pseudocode or missing.

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit validation checkpoints — preview and provider probe before the paid run, run once, preserve the run ID, present actual terminal status — and concrete error-recovery guidance ('When evidence is missing, report the missing fields and retain failed-run evidence instead of repeating paid calls').

5 / 5

Progressive Disclosure

A 17-line skill with no bundle files keeps only the workflow inline and clearly signals its one-level-deep references: the example config `egs/skills_examples/quant-etf-review.yaml` and the shared guide linked with its purpose ('for provider limits, data fields and research gates'). Per the rubric's simple-skill note, this organization merits 5.

5 / 5

Total

20

/

20

Passed

Description

78%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 specific, well-triggered description for a narrow quant/ETF backtest-review niche, with an explicit 'Use when' clause and distinct triggers. Its main weakness is that the capability ('what') is only implied inside the trigger clause rather than stated explicitly, and a few natural synonyms are missing.

Suggestions

State the 'what' explicitly before the trigger clause, e.g. 'Runs a multi-agent review of ETF strategy backtests covering fund exposure, tracking error and liquidity, and reports actual run evidence. Use when...' — currently the capability is only embedded in the 'Use when' clause.

Add natural trigger synonyms such as 'ETF portfolio review', 'index fund exposure' or 'backtest audit' to broaden keyword coverage for users who phrase the request differently.

Mention what the skill yields (e.g. review report, cost/risk ledger, HTML output) to make the capability list more concrete and comprehensive.

DimensionReasoningScore

Specificity

Names several concrete review types beyond the domain — 'fund exposure, tracking error or liquidity checks on an existing backtest' — but never states what the skill actually does or produces, leaving minor coverage gaps. It exceeds the 3 anchor (more than 1-2 generic actions) but is not the comprehensive action list of the 5 anchor.

4 / 5

Completeness

The 'when' is explicit ('Use when the user asks for...') and a 'what' is present via the enumerated review types, but the what is only embedded inside the trigger clause rather than stated as its own capability sentence. Not 3 (the what is specific, not weakly implied); not 5 (what and when are not both clearly and separately stated).

4 / 5

Trigger Term Quality

'ETF strategy review', 'fund exposure', 'tracking error', 'liquidity' and 'backtest' are natural phrases a quant user would actually say, giving good keyword coverage. Common synonyms like 'ETF portfolio', 'index fund' or 'backtest audit' are missing, so it falls short of the 5 anchor's comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

'multi-agent ETF strategy review... tracking error or liquidity checks on an existing backtest' occupies a clear quant/ETF niche with distinct, domain-specific triggers and minimal overlap risk with generic review or document skills.

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

charliedream1/ai_quant_trade

Path

.agents/skills/quant-etf-review/SKILL.md

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.