CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

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-signal-aggregator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable body with executable commands, a clear step sequence, and well-signaled bundle references. Its main cost is token weight: the giant inline JSON example and duplicated rule exposition could be tightened or moved to a reference file.

Suggestions

Move the full JSON output schema (or at least the deduplication_log/invalid_signals detail) into a reference file and keep a minimal example inline.

Trim the producer-contract prose so each rule is stated once instead of being restated by the JSON example and Key Principles.

Add a short feedback loop to Step 3, e.g. "If invalid_signals_dropped > 0, re-run the failing upstream skill before trusting its contribution to the dashboard."

DimensionReasoningScore

Conciseness

Roughly half of the ~305-line body is a 130-line JSON output sample, and the producer-contract prose restates dedup/tie-breaking rules already demonstrated in that example; there is no padding of known concepts, but the duplication is a clear trim target, matching anchor 3 rather than 4.

3 / 5

Actionability

Three copy-paste-ready invocations of scripts/aggregate_signals.py with real flags (--weights-config, --min-conviction), real input globs, and a fully documented output format cover the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The four-step sequence (gather, aggregate, review, act) is clear, with Step 3 as an explicit review checkpoint over contradictions and the dedup log plus built-in input validation (invalid_signals_dropped); it falls short of 5 only because there is no explicit error-recovery feedback loop (e.g. what to do when invalid signals are dropped).

4 / 5

Progressive Disclosure

The Resources section clearly signals three real one-level-deep bundle files (verified to exist), and most content is appropriately placed; the 130-line JSON schema sample and producer-contract detail would fit better in a reference file, keeping it below anchor 5.

4 / 5

Total

16

/

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 capability keywords. Its main weakness is the missing "Use when..." trigger clause, which both caps completeness and limits natural trigger-phrase coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when consolidating or comparing outputs from multiple edge-finding skills, or when prioritizing which edge ideas deserve deeper research."

Include natural synonyms users might say, such as "combine", "consolidate", or "merge" signal outputs, alongside "aggregate".

Consider mentioning the contradiction-resolution use case as a trigger ("when different analyses disagree") since it is a distinctive capability.

DimensionReasoningScore

Specificity

"Aggregate and rank signals... into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection" names the domain and five concrete capabilities, matching the comprehensive-coverage anchor; not 4 because action coverage is complete rather than gappy.

5 / 5

Completeness

The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines; not 4 because nothing states when to invoke the skill.

3 / 5

Trigger Term Quality

Natural phrases like "aggregate", "rank signals", "conviction dashboard", "contradiction", and the four named upstream skills give good keyword coverage, but common synonyms ("combine", "consolidate", "merge outputs") are missing, placing it between anchors 3 and 4, above the midpoint.

4 / 5

Distinctiveness Conflict Risk

Naming the exact 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 with those upstream skills.

5 / 5

Total

17

/

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-signal-aggregator/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.