CtrlK
BlogDocsLog inGet started
Tessl Logo

harmonic

Harmonic Patterns signal engine. Identifies XABCD five-point structures such as Gartley/Bat/Butterfly/Crab based on Fibonacci geometry, and generates trading signals in the PRZ (Potential Reversal Zone).

57

Quality

66%

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 ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/harmonic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body is concise and well-structured for a simple signal skill, but it lacks an executable usage example and fails to point to the detailed reference files that already exist. Linking the references and adding a minimal code snippet would materially raise the score.

Suggestions

Add a short executable example showing how to run the engine and read the 1/-1/0 signal output.

Link the existing bundle files in the body, e.g. 'See [XABCD形态.md](references/XABCD形态.md) for full pattern geometry and [PRZ交易.md](references/PRZ交易.md) for entry/stop/target rules.'

Move the duplicated PRZ definition out of Core Concepts or reduce it to a one-line pointer to the reference file.

DimensionReasoningScore

Conciseness

Lean, dense tables and bullet concepts with no padding or explanation of concepts Claude already knows; only minor restatement of PRZ in Core Concepts keeps it from a 5.

4 / 5

Actionability

Provides a pip install command and parameter/signal tables, but no executable code or concrete steps showing how to actually invoke the engine and produce a signal; the 'how to use it' is missing from the body.

3 / 5

Workflow Clarity

Single-purpose skill with an implicit but clear sequence (install → set is_stock → read 1/-1/0 signals); no destructive/batch step requiring validation, so the simple-skill exception applies, with only minor sequencing gaps.

4 / 5

Progressive Disclosure

Bundle files exist with substantial detail (PRZ trading rules, full XABCD geometry) but the body never references or links to them; references are present in the bundle yet not signaled, leaving navigation unclear.

3 / 5

Total

14

/

20

Passed

Description

70%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 distinctive with strong domain trigger terms, but it omits any explicit 'Use when...' guidance, capping its completeness. Adding a trigger clause would lift it to the top band.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks about harmonic patterns, Fibonacci retracements, or XABCD/Gartley/Bat/Butterfly/Crab setups.'

Include common synonyms or phrasings users might say (e.g. 'Fib retracements', 'reversal patterns') to broaden trigger coverage.

Clarify the output trigger (signal generation) with a natural phrase like 'when the user wants buy/sell signals from harmonic geometry.'

DimensionReasoningScore

Specificity

Names the domain and concrete actions ("Identifies XABCD five-point structures such as Gartley/Bat/Butterfly/Crab", "generates trading signals in the PRZ") with named pattern coverage; not quite the comprehensive multi-action list of a 5.

4 / 5

Completeness

Clear "what" but no "Use when..." trigger clause; per the judging guideline a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Strong natural domain terms ("Harmonic Patterns", "Gartley/Bat/Butterfly/Crab", "Fibonacci", "trading signals", "PRZ") a trader would say, but lacks synonyms or file-extension-style variants for a 5.

4 / 5

Distinctiveness Conflict Risk

Highly specific niche (harmonic Fibonacci patterns with named structures) with distinct triggers and minimal overlap with other skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
charliedream1/ai_quant_trade
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.