CtrlK
BlogDocsLog inGet started
Tessl Logo

candlestick

Candlestick pattern recognition engine, pure pandas vectorized implementation of 15 classic candlestick patterns (5 single-candle + 5 double-candle + 4 triple-candle + 1 trend confirmation), generating a composite signal from bullish/bearish pattern scores.

64

Quality

76%

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 ./agent/src/skills/candlestick/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 concise, clearly organized, and presents an unambiguous single-action workflow, but it lacks any executable code or usage example despite claiming a vectorized pandas implementation, which is the main gap.

Suggestions

Add a minimal copy-paste-ready code example showing the vectorized pattern scoring and composite signal generation in pandas.

Include a short worked example of calling the engine on a price DataFrame and interpreting the returned signal convention.

Document how the two parameters (body_pct, shadow_ratio) are applied in the implementation so users can tune them.

DimensionReasoningScore

Conciseness

The body is lean: compact pattern tables and a one-sentence Signal Logic rule with no padding explaining what candlesticks are, assuming Claude's competence so every token earns its place.

3 / 3

Actionability

It gives the scoring rule and a parameters table, but provides no executable code despite the description promising a 'pure pandas vectorized implementation,' leaving it at 'some concrete guidance but incomplete / missing key details.'

2 / 3

Workflow Clarity

The signal decision rule (score > 0 long, < 0 short, = 0 aside) plus the explicit signal convention table make the single action unambiguous, satisfying the simple-skill allowance for a clear single-purpose workflow.

3 / 3

Progressive Disclosure

No bundle files exist and the body is under 50 lines with well-organized sections (Purpose, Signal Logic, Parameters, Dependencies), meeting the simple-skill allowance that progressive disclosure can score 3 from clean organization alone.

3 / 3

Total

11

/

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 is specific and occupies a distinct niche, but it is incomplete because it never states when Claude should invoke the skill, and its trigger-term coverage is partial and slightly technical rather than natural.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks about candlestick chart patterns, bullish/bearish reversal signals, or Japanese candlestick analysis.'

Broaden trigger terms with natural user phrasings like 'chart patterns,' 'price action,' and 'reversal patterns' alongside the technical terminology.

Trim implementation detail ('pure pandas vectorized implementation') from the description to keep it trigger-focused.

DimensionReasoningScore

Specificity

Names multiple concrete actions such as 'pattern recognition engine,' 'pure pandas vectorized implementation,' and 'generating a composite signal from bullish/bearish pattern scores,' matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

It clearly answers 'what' the skill does but offers no 'Use when...' clause or equivalent trigger for 'when' Claude should use it, which caps completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Relevant domain keywords like 'candlestick patterns' and 'bullish/bearish' appear, but common natural variations a trader might say (e.g. 'chart patterns,' 'price action,' 'reversal patterns') are missing and the phrasing leans technical ('pure pandas vectorized implementation').

2 / 3

Distinctiveness Conflict Risk

'Candlestick pattern recognition engine' occupies a clear, narrow niche unlikely to trigger for or conflict with unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

10

/

12

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
HKUDS/Vibe-Trading
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.