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.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

76%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 highly actionable with verified, copy-paste-ready commands and lean, well-organized sections, but the workflow lacks explicit validation checkpoints for a batch data-processing skill, and the schema reference is not contextually linked where it is most useful.

Suggestions

Add an explicit validation checkpoint to the workflow, e.g. after running build_hints.py verify the output with `python3 scripts/build_hints.py ... && python3 -c "import yaml; yaml.safe_load(open('reports/edge_hint_extractor/hints.yaml'))"` or check that meta.total_hints > 0, to lift workflow_clarity above 3.

Link references/hints_schema.md inline from the Output section ("see references/hints_schema.md for the full field schema") so the reference is signaled where it is relevant, not only in Resources.

Consolidate the shared base arguments of the three Quick Command examples into a short preamble to reduce token repetition while keeping each mode copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is efficient with brief bullet sections (When to Use, Prerequisites, Output, Workflow) and no over-explanation of concepts Claude already knows. It is not a 5 because the three Quick Command blocks repeat the same base arguments (--market-summary, --anomalies, --output-dir) where a shared preamble could trim tokens.	4 / 5
Actionability	Provides three fully executable, copy-paste-ready bash commands whose flags (--market-summary, --anomalies, --news-reactions, --as-of, --output-dir, --llm-ideas-cmd, --llm-ideas-file) all match the actual build_hints.py argparse definitions, covering the common rule-only, external-CLI, and pre-written-file cases. No gaps prevent execution.	5 / 5
Workflow Clarity	The four-step Workflow is clearly sequenced (gather -> run script -> optionally augment -> pass downstream), but there are no explicit validation checkpoints (e.g., verify hints.yaml validity or check hint counts), and this batch data-processing operation is capped at 3 per the rubric. It is not a 4 because checkpoints are missing rather than merely minor.	3 / 5
Progressive Disclosure	The body is a clear overview with one-level-deep references (scripts/build_hints.py, references/hints_schema.md) listed in a Resources section, and the detailed schema is appropriately split into hints_schema.md. It is not a 5 because hints_schema.md is only referenced in Resources rather than contextually linked from the Output section where the schema is most relevant.	4 / 5
	Total	16 / 20 Passed

Description

61%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 distinct, clearly conveying what the skill does and for which niche pipeline, but it omits any explicit "Use when..." trigger guidance, which caps completeness at 3. Trigger-term coverage is good but lacks synonyms and file extensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when turning daily market observations or news reactions into reusable edge hints for concept synthesis or auto detection." to raise completeness above 3.

Include natural synonyms and the output extension in the description (e.g., "signals", "trading ideas", "hints.yaml") to improve trigger-term coverage toward 5.

Mention the downstream handoff context (concept synthesis / auto detection) as an explicit trigger so the skill is distinguishable from sibling pipeline stages.

Dimension	Reasoning	Score
Specificity	Names the domain ("edge hints from daily market observations and news reactions") and 1-2 concrete actions ("Extract edge hints", "output canonical hints.yaml"), but does not comprehensively enumerate actions. It is not a 4 because the action list is limited to extract/output plus an optional LLM augmentation rather than several specific actions.	3 / 5
Completeness	Clearly states the "what" (extract edge hints and output canonical hints.yaml for concept synthesis and auto detection) but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guidelines. It is not a 4 because the "when" is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Contains natural niche keywords a quant user would say — "edge hints", "market observations", "news reactions", "hints.yaml" — giving good coverage. It is not a 5 because synonyms and file extensions (e.g., "signals", "trading ideas", ".yaml") are missing, and not a 3 because the terms present go beyond generic language.	4 / 5
Distinctiveness Conflict Risk	The description carves out a distinct quant-pipeline niche (edge hints, market observations, hints.yaml, concept synthesis, auto detection) with low conflict risk against unrelated skills. It is not a 5 because sibling skills in the same observe->abstract->design->pipeline workflow could create minor overlap, and not a 3 because the niche is specific rather than broadly generic.	4 / 5
	Total	14 / 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-hint-extractor/SKILL.md
Commit: 51c7907

Reviewed: 3 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.