entry-signals

Entry signal patterns with historical success rates. Use when deciding whether to open a position.

1.05x

Quality

—

Does it follow best practices?

Impact

100%

1.05x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

37%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is an auto-generated reference table of learned signals with confidence guidance, but it lacks any executable procedure or sequenced, validated workflow for actually using those signals to open a position. It is also weighed down by time-sensitive inline metadata and a duplicated header.

Suggestions

Add a short, numbered entry workflow with explicit validation checkpoints (e.g., confirm trend across timeframes, run risk checks, only then open position) to address the missing workflow clarity.

Move the verbose per-signal details and dated metadata into a separate reference file and keep SKILL.md as a concise overview with a signaled link, improving both conciseness and progressive disclosure.

Provide concrete, copy-paste-ready guidance or code for how to evaluate and act on a signal rather than only descriptive success-rate data.

Dimension	Reasoning	Score
Conciseness	The body is mostly a data dump with a redundant "## Entry Signals" header and time-sensitive metadata ("Last updated: 2026-01-17", "First seen: 2026-01-14") inline, which the guideline says should penalize conciseness, though it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	Concrete thresholds and a confidence-interpretation table give some guidance, but there is no executable command, code, or concrete procedure for actually applying a signal to open a position.	2 / 3
Workflow Clarity	There is no sequenced workflow and no validation checkpoint for the risky act of opening a position; the body is reference data rather than a multi-step process with error-recovery feedback.	1 / 3
Progressive Disclosure	Section headers provide some organization, but all signal detail is inlined in a single file with no bundle references, so content that could be split into a reference file is kept inline.	2 / 3
	Total	7 / 12 Passed

Description

75%

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 cleanly answers both what the skill does and when to use it with a clear, third-person trigger clause, and it occupies a distinct niche. It is let down only by moderate trigger-term coverage and a single named action rather than a list of concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain and an action ("Entry signal patterns" with "historical success rates") but does not enumerate multiple concrete actions, so it sits between the single-vague anchor 1 and the comprehensive anchor 3.	2 / 3
Completeness	It states what ("Entry signal patterns with historical success rates") and an explicit when ("Use when deciding whether to open a position"), matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Natural trader terms like "entry signal" and "open a position" are present, but coverage is moderate and misses common variations such as trade entry or long/short setup language.	2 / 3
Distinctiveness Conflict Risk	The description targets a bounded niche (trade entry decisions) with distinct triggers unlikely to conflict with unrelated skills.	3 / 3
	Total	10 / 12 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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.