CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

edge-candidate-agent

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.

Quality

89%

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

86%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 highly actionable with complete executable commands, concrete export rules, and a clearly sequenced workflow that includes validation and dry-run checkpoints. Structure follows good progressive disclosure with verified one-level-deep references; the only improvements are removing the path redundancy in Resources and adding an explicit validation-failure feedback loop.

DimensionReasoningScore

Conciseness

The body is efficient and task-specific throughout, with no explanations of concepts Claude already knows. The only trimmable redundancy is the Resources section, which re-lists script and reference paths already given with roles in the Workflow section. This is 'efficient with minor instances of over-explanation' rather than the fully lean top anchor.

4 / 5

Actionability

The skill provides three complete, copy-paste-ready bash invocations with real flags and arguments, plus concrete export rules ("Keep `validation.method: full_sample`", named entry families `pivot_breakout`/`gap_up_continuation`) and explicit output artifacts. Specific commands cover the common cases, matching the fully executable top anchor.

5 / 5

Workflow Clarity

The 6-step workflow is clearly sequenced with an explicit validation checkpoint (step 5: validate interface and Phase I constraints) and a dry-run-before-full-execution guardrail. It lacks an explicit error-recovery feedback loop (what to do when validation fails, e.g., fix the ticket and re-export), which keeps it below the top anchor but above 'checkpoints missing or implicit'.

4 / 5

Progressive Disclosure

The body is a clear overview that delegates details to real, verified one-level-deep bundle files (references/pipeline_if_v1.md, signal_mapping.md, research_ticket_schema.md, ideation_loop.md, and three scripts), each with a stated purpose in the Resources section and invoked with context in the Workflow. Content is appropriately split with easy navigation, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

88%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 strong description that is specific, concrete, and explicitly provides 'Use when' trigger guidance with named artifacts and interface versions. Trigger term coverage is good but lacks synonym breadth, and there is minor overlap risk with sibling skills in the same split workflow.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with named artifacts and versions: "Generate and prioritize US equity long-side edge research tickets from EOD observations", "export pipeline-ready candidate specs for trade-strategy-pipeline Phase I", and "preflight-check interface compatibility (`edge-finder-candidate/v1`)". Coverage is comprehensive with no noticeable gaps, matching the top anchor rather than the 'minor gaps' level below.

5 / 5

Completeness

It explicitly answers both questions: the 'what' (generate/prioritize research tickets, export candidate specs) and the 'when' via a concrete "Use when users ask to..." clause listing three distinct trigger scenarios. This matches the anchor for clearly and explicitly answering both with concrete trigger phrases.

5 / 5

Trigger Term Quality

Trigger phrases like "turn hypotheses/anomalies into reproducible research tickets", "convert validated ideas into strategy.yaml + metadata.json", and "before running pipeline backtests" are natural for this domain and phrased as things a user would actually say. However, synonym coverage is incomplete (e.g., no 'trade ideas', 'signals', or 'screening' variants), so it falls short of the comprehensive top anchor.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to a niche (US equity long-side edge candidates, `edge-finder-candidate/v1`, trade-strategy-pipeline Phase I), giving it clear distinct triggers. Minor overlap risk remains with the closely related sibling skills in the split workflow (e.g., edge-strategy-designer also produces strategy YAML), keeping it at 'mostly distinct' rather than the minimal-conflict top anchor.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

tradermonty/claude-trading-skills

Path

skills/edge-candidate-agent/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.