edge-concept-synthesizer

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

Quality

78%

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 ./skills/edge-concept-synthesizer/SKILL.md

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.

The content is a strong, token-efficient overview: executable commands cover the common cases, the workflow is sequenced with review/promotion checkpoints, and heavy detail is correctly deferred to a real reference file and script. Minor gaps are the repetitive command examples, an implicit rather than explicit output-validation step, and an unlabeled reference entry.

Dimension	Reasoning	Score
Conciseness	The body is lean — short Overview, When to Use, Prerequisites, Output, and Workflow sections with no explanation of concepts Claude already knows. It stops short of a 5 because the Quick Commands section repeats the same script invocation four times with only flag differences, which could be condensed into one command plus a flag annotation.	4 / 5
Actionability	The Quick Commands section provides fully executable, copy-paste-ready invocations with real paths and flags (--tickets-dir, --hints, --promote-hints, --max-synthetic-ratio, --overlap-threshold, --no-dedup) covering the common cases, and the workflow names the exact script to run. This matches the 5 anchor's "fully executable; copy-paste ready code or commands; specific examples cover the common cases".	5 / 5
Workflow Clarity	The five-step workflow is clearly sequenced, names the script, and includes review checkpoints (dedup with a containment threshold in step 4, "Review concepts and promote only high-support concepts" in step 5). It does not reach 5 because there is no explicit validation of the generated edge_concepts.yaml against the documented schema (references/concept_schema.md) before promotion — the checkpoint is implicit in "review".	4 / 5
Progressive Disclosure	The body is well organized into focused sections and pushes detail out appropriately: the 854-line script and the YAML schema live in scripts/ and references/concept_schema.md respectively, both real files referenced one level deep. It falls short of 5 because the Resources entry for references/concept_schema.md is a bare path with no label describing when to consult it, a minor navigation gap.	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 is specific and clearly distinguishable, naming concrete inputs and outputs in third person. Its main weakness is the absence of explicit trigger guidance — no 'Use when...' clause or natural user-facing phrases — leaving the "when to use" question only weakly implied.

Suggestions

Add an explicit trigger clause, e.g., "Use when you have raw detector tickets and need mechanism-level concepts before drafting strategies."

Include natural trigger phrases or synonyms users would actually say (e.g., "cluster tickets", "ticket patterns", "concept review") alongside the domain jargon.

Clarify the "when" beyond the temporal hint "before strategy design/export" by stating the situations that call for this skill.

Dimension	Reasoning	Score
Specificity	The description names concrete actions and outputs — "Abstract detector tickets and hints into reusable edge concepts with thesis, invalidation signals, and strategy playbooks" — specifying the input (detector tickets, hints), transformation (abstraction), and artifacts produced. It falls just short of the 5 anchor because it describes essentially one composite action rather than multiple distinct concrete actions.	4 / 5
Completeness	The "what" is clear (abstract tickets/hints into edge concepts with thesis, invalidation signals, and playbooks), but the "when" is only weakly implied by "before strategy design/export" — there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Domain terms like "detector tickets", "hints", "edge concepts", and "strategy playbooks" are relevant within this niche, but the description offers no natural trigger phrasing a user would say and no synonyms or variations (e.g., "Use when clustering tickets" or "before building strategies"). Not lower because the keywords it does include are specific and on-domain, not generic.	3 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche — synthesizing detector tickets into edge concepts with invalidation logic — with highly specialized vocabulary ("ticket support", "invalidation signals", "export readiness") that is unlikely to overlap with other skills. It matches the 5 anchor's "clear niche with distinct triggers; minimal conflict risk".	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/edge-concept-synthesizer/SKILL.md
Commit: eab8d5c

Reviewed: 8 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.