CtrlK
BlogDocsLog inGet started
Tessl Logo

edge-concept-synthesizer

Abstract detector tickets and hints into reusable edge concepts with thesis, invalidation signals, and strategy playbooks before strategy design/export.

61

Quality

71%

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 ./skills/edge-concept-synthesizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

83%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 lean, efficient, and highly actionable with executable commands covering the common invocation variants, and it appropriately offloads schema detail to a one-level-deep reference. The main gap is the absence of an explicit validation/verification checkpoint in a batch workflow that deduplicates and promotes concepts, which caps workflow clarity.

Suggestions

Add an explicit validation step to the workflow (e.g., after dedup, verify that high-support concepts meet a support threshold before promoting them, and re-check export readiness) to introduce a feedback loop and lift workflow clarity above 3.

Make the reference navigation more explicit in the body, e.g., 'See references/concept_schema.md for the full edge_concepts.yaml schema and design rules', to strengthen progressive disclosure signaling.

Include a brief note on how to verify the generated edge_concepts.yaml (e.g., a sanity check command or fields to inspect) given the batch/export nature of the operation.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — sections like Overview, Prerequisites, Output, and Workflow state only what is needed, with no padding or explanation of basic concepts. Re-reading the 4 anchor (minor over-explanation that could be trimmed) does not fit; every token earns its place.

5 / 5

Actionability

Quick Commands provides copy-paste-ready, fully executable invocations covering the common cases (basic run, hint promotion with synthetic cap, custom dedup threshold, disabling dedup) with concrete flags and paths. This matches the 5 anchor of fully executable, copy-paste-ready examples covering common cases.

5 / 5

Workflow Clarity

A 5-step sequence is listed (collect, optionally provide hints, run script, deduplicate, review/promote), but this is a batch operation with no explicit validation or verification checkpoint before promotion/export, which per the rubric caps workflow clarity at 3. Not a 4 because validation checkpoints are absent rather than merely minor-gapped; not a 2 because the sequence itself is coherent and well-ordered.

3 / 5

Progressive Disclosure

Good structure with a concise overview, a Resources section pointing to the real one-level-deep reference (references/concept_schema.md) and the script, and the schema detail correctly offloaded to the reference file. Not a 5 because the reference is signaled via a plain bullet rather than an explicit 'See [concept_schema.md] for the full schema' navigation cue, leaving a minor organization gap.

4 / 5

Total

17

/

20

Passed

Description

58%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 clearly conveys what the skill does with concrete structural outputs, but omits any explicit 'when to use' trigger guidance, which caps completeness and limits trigger-term quality. It is specific and reasonably distinct but would benefit from a natural-language Use-when clause.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when you have many raw detector tickets and need mechanism-level structure before designing strategies').

Include synonyms and natural user-language terms (e.g., 'trading edge ideas', 'strategy hypotheses') alongside the current domain jargon to improve trigger-term quality.

Clarify the boundary versus general strategy-design skills to lift distinctiveness toward a clear niche.

DimensionReasoningScore

Specificity

Lists several specific actions — 'Abstract detector tickets and hints into reusable edge concepts with thesis, invalidation signals, and strategy playbooks' — naming the inputs, outputs, and structural elements, with only minor coverage gaps. Not a 5 because it does not enumerate a fuller range of concrete actions like clustering or deduplication.

4 / 5

Completeness

The 'what' is clear (abstract tickets/hints into edge concepts with thesis, invalidation signals, and playbooks), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3. Not a 4 because the 'when' is entirely absent rather than merely weakly implied.

3 / 5

Trigger Term Quality

Relevant niche keywords ('detector tickets', 'hints', 'edge concepts', 'strategy playbooks') are present but these are domain jargon rather than the natural phrases a user would say, and no synonyms or variants are offered. Not a 4 because it lacks the broader natural-term coverage users would actually utter.

3 / 5

Distinctiveness Conflict Risk

The niche is fairly clear ('edge concepts', 'detector tickets', 'invalidation signals', 'strategy playbooks') making it mostly distinct with only minor overlap risk against adjacent strategy-design skills. Not a 5 because the description does not sharply delineate the boundary from a general 'strategy design' skill.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tradermonty/claude-trading-skills
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.