CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quant-backtest-review

Use when the user asks analyst, risk, reviewer and chair agents to review an existing backtest with cited evidence.

Quality

77%

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 ./.agents/skills/quant-backtest-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 lean, imperative, project-grounded workflow: every line assumes Claude's competence and the commands are nearly copy-paste ready, with explicit anti-fabrication and cost-safety guardrails. The remaining gaps are minor — incomplete subcommand invocations, no explicit failure-recovery loop, and all referenced material living outside the skill bundle.

DimensionReasoningScore

Conciseness

Every sentence carries project-specific, non-obvious constraints ('do not silently switch provider or relax permissions', 'Do not fabricate AR/IC/drawdown', 'Do not launch recursive Skills from a model-provider subprocess') with zero padding and no explanation of concepts Claude already knows. The ~16-line body is lean and every token earns its place, matching anchor 5 exactly.

5 / 5

Actionability

The body gives copy-paste-ready commands ('python egs/skills.py preview --config <task.yaml>', 'python egs/skills.py run --config <task.yaml> --format jsonl') and a concrete template pointer ('Read `egs/skills_examples/quant-backtest-review.yaml`'), so most guidance is executable. Minor gaps remain: 'providers --probe' and the 'show', 'events', 'files', 'cancel' operations are not spelled out as full invocations, which keeps it below the fully-executable anchor 5.

4 / 5

Workflow Clarity

Five clearly sequenced numbered steps include an explicit pre-run checkpoint (preview, with '--probe' when 'backend availability is uncertain') and an error path for missing evidence ('report the missing fields and retain failed-run evidence instead of repeating paid calls'). However, there is no explicit fix-and-retry feedback loop if preview or the run fails (only 'cancel' is mentioned), so it fits 'clear sequence with most checkpoints present; minor validation gaps' rather than anchor 5.

4 / 5

Progressive Disclosure

The short body is a clear overview that defers detail to a well-signaled, one-level-deep reference ('See [the shared execution guide](../../../docs/usage/agent_cli_skills.md) for provider limits, data fields and research gates') plus the example YAML, so navigation is easy. It falls short of anchor 5 because no bundle files ship with the skill (no references/, scripts/, or assets/) and the referenced guide lives outside the skill directory, making navigation entirely dependent on the host project.

4 / 5

Total

17

/

20

Passed

Description

62%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 has an explicit 'Use when' trigger and a clearly distinct niche, but the 'what' is a single thin action and the trigger leans on internal role jargon ('analyst, risk, reviewer and chair agents') rather than natural user phrases. It reads more as a platform-workflow invocation than a user-facing capability statement, leaving keyword coverage and capability coverage incomplete.

Suggestions

Lead with the concrete capability in third person before the trigger clause (e.g., 'Reviews an existing quant backtest and verifies reported AR/IC/drawdown and PIT evidence against cited sources.') to strengthen the 'what'.

Add natural trigger synonyms users would actually say — 'backtest', 'quant strategy', 'validate backtest results' — rather than relying on internal role names ('analyst, risk, reviewer and chair agents') as the trigger.

Name one or two more concrete actions (e.g., checking PIT evidence, maintaining a shared cost/risk ledger) so the capability coverage is more comprehensive rather than a single 'review' action.

DimensionReasoningScore

Specificity

The description names the domain and one concrete action — 'review an existing backtest with cited evidence' — but lists no further capabilities (e.g., verifying AR/IC/drawdown claims or PIT evidence), matching 'names domain and 1-2 concrete actions, but not comprehensive'. It lists several actions only in the sense of naming four agent roles, which are actors rather than actions, so it does not reach the 'several specific actions' anchor.

3 / 5

Completeness

Both elements are explicitly present: the 'what' ('review an existing backtest with cited evidence') and an explicit 'Use when' trigger clause, so it clears the anchor-3 cap for missing triggers. However, the 'when' is framed around the user asking internal agent roles ('when the user asks analyst, risk, reviewer and chair agents to review...'), a convoluted trigger that could be more explicit and user-facing, keeping it below anchor 5.

4 / 5

Trigger Term Quality

'backtest' and 'review' are natural domain keywords a quant user would say, but coverage is thin — missing common variations such as 'quant', 'strategy', or 'validate' — and 'analyst, risk, reviewer and chair agents' is platform-internal jargon rather than phrases a user would naturally utter. It has some relevant keywords but is missing common variations and synonyms, fitting anchor 3 rather than the 'good keyword coverage' of anchor 4.

3 / 5

Distinctiveness Conflict Risk

'review an existing backtest with cited evidence' combined with the four named agent roles carves out a distinct niche with clear 'review vs. run' separation, giving minimal conflict risk with unrelated skills. There is minor overlap risk with closely related skills in the same platform (e.g., running or creating backtests), which fits 'mostly distinct; minor overlap risk' rather than the fully distinct anchor 5.

4 / 5

Total

14

/

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-backtest-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.