edge-signal-aggregator

Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.

Quality

74%

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-signal-aggregator/SKILL.md

Quality

Content

61%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 well-structured, highly actionable skill body with verified executable commands and genuine bundle references. Weaknesses are the missing validation checkpoint in the batch aggregation workflow, noticeably duplicated full output examples, and a small config-value inconsistency between the example output and the actual defaults file.

Suggestions

Add an explicit validation step to the workflow, e.g., "Verify the summary counts (total_input_signals) match the number of input files collected; if inputs are missing, check glob patterns before proceeding."

Trim the Output Format section to one condensed example (or move the full JSON schema to references/) to remove the JSON/markdown duplication.

Fix the dedup similarity threshold inconsistency: the example output shows 0.8 but assets/default_weights.yaml defaults to 0.60.

Dimension	Reasoning	Score
Conciseness	Prose sections are efficient, but the Output Format section inlines two full-length example reports (~105 lines: a complete JSON object and a complete markdown dashboard showing the same data), which is noticeable duplication that could be trimmed to a single condensed example.	3 / 5
Actionability	The three CLI invocations are copy-paste ready with verified flags (--edge-candidates, --weights-config, --min-conviction) and concrete paths, but the example output shows "dedup_similarity_threshold": 0.8 while the actual assets/default_weights.yaml default is 0.60, a minor accuracy gap.	4 / 5
Workflow Clarity	The four workflow steps are clearly sequenced with executable commands, but there is no explicit validation/verification checkpoint (e.g., confirming all expected input files were found or checking summary counts against inputs) for what is a batch aggregation over many files, which the rubric caps at 3.	3 / 5
Progressive Disclosure	Good structure with a Resources section pointing to real, clearly-signaled, one-level-deep bundle files (scripts/aggregate_signals.py, references/signal-weighting-framework.md, assets/default_weights.yaml); the main gap is that the long inline output-format examples could be split into a reference file.	4 / 5
	Total	14 / 20 Passed

Description

75%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, distinctive description that clearly states what the skill does with concrete named capabilities. Its main weakness is the complete absence of an explicit "Use when…" trigger clause, which caps completeness and limits natural trigger-term coverage.

Suggestions

Append an explicit trigger clause, e.g., "Use when consolidating outputs from multiple edge-finding skills or when ranking edge ideas by conviction before allocation decisions."

Add one or two natural user phrasings (e.g., "combine edge signals", "merge overlapping edge ideas") alongside the technical terms to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Aggregate and rank signals… into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection" lists multiple specific concrete actions (aggregate, rank, weight, dedup, detect contradictions) with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The description clearly answers "what" but contains no "Use when…" clause or equivalent explicit trigger guidance; per the rubric guideline, a missing trigger clause caps completeness at 3 even though the "what" is strong.	3 / 5
Trigger Term Quality	Terms like "aggregate", "rank", "signals", "conviction dashboard", "deduplication", and "contradiction detection" give good keyword coverage, but a few natural variations users might say (e.g., "combine edge ideas", "consolidate findings", "merge signals") are missing.	4 / 5
Distinctiveness Conflict Risk	Naming the specific upstream skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) carves out a clear aggregation niche with distinct triggers and minimal conflict risk against the upstream skills themselves.	5 / 5
	Total	17 / 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-signal-aggregator/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.