CtrlK
BlogDocsLog inGet started
Tessl Logo

edge-hint-extractor

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/edge-hint-extractor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The body is actionable and well-structured with real, correctly signaled references, but the three near-duplicate command examples add redundancy and the workflow lacks a validation step for its batch output. Collapsing the command examples and adding an output-verification step would push it higher.

Suggestions

Collapse the three Quick Command blocks into one base command plus the two flag variations (--llm-ideas-cmd vs --llm-ideas-file) to remove repeated argument lists.

Add an explicit validation/verification step to the workflow, e.g. 'Verify reports/edge_hint_extractor/hints.yaml exists and parses as valid YAML before passing it downstream'.

Note the prerequisites and default output path once rather than restating the full argument set in each example.

DimensionReasoningScore

Conciseness

The body is lean and does not over-explain concepts Claude already knows, but the three Quick Command blocks repeat nearly identical argument lists, which could be tightened into one base command plus the flag variations.

2 / 3

Actionability

Provides three full, copy-paste-ready bash invocations with concrete flags and example paths, plus a clear note that --llm-ideas-cmd and --llm-ideas-file are mutually exclusive — fully executable guidance.

3 / 3

Workflow Clarity

The numbered 1–4 workflow gives a clear sequence, but generating hints.yaml is a batch output operation with no validation/verification checkpoint (e.g. confirm the file exists or is valid YAML), which per the guidelines caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Well-organized overview sections with one-level-deep, clearly signaled references — references/hints_schema.md and scripts/build_hints.py are both real bundle files listed in the Resources section — matching the clear-overview-with-one-level-references anchor.

3 / 3

Total

10

/

12

Passed

Description

67%

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 and occupies a distinct niche, but omits an explicit "Use when..." trigger and leans on domain jargon rather than natural user phrasing. Adding trigger guidance and plainer keywords would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when ...' clause naming the natural situations a user would describe (e.g. 'Use when turning daily market observations into reusable edge hints, or when preparing hints.yaml for concept synthesis or auto detection').

Soften jargon ('canonical', 'concept synthesis') with more natural trigger phrasings users are likely to say.

Keep the concrete actions and named artifacts — they are the strongest part of the description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Extract edge hints", "optional LLM ideation", "output canonical hints.yaml" — with named inputs (market observations, news reactions) and a named output artifact, matching the multi-action anchor.

3 / 3

Completeness

The "what" is clearly stated but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Relevant domain terms ("edge hints", "market observations", "news reactions", "hints.yaml") are present but lean technical/jargony ("canonical", "concept synthesis", "auto detection") and lack the common natural variations a user would say, fitting the "some relevant keywords but missing common variations" anchor.

2 / 3

Distinctiveness Conflict Risk

Targets a clear niche — first-stage edge-hint extraction feeding a specific observe->abstract->design->pipeline workflow — with distinct triggers and a named output artifact, making conflict with other skills unlikely.

3 / 3

Total

10

/

12

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.