technical-basic

Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting. Pure pandas implementation for any OHLCV data.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/technical-basic/SKILL.md

Quality

Content

57%

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

The body is well-organized and assumption-respecting but stops short of fully executable guidance: indicator formulas and parameters are given, yet no complete code computes and emits the composite signal, and the bullish/bearish mapping is left implicit.

Suggestions

Add one complete, executable pandas snippet that computes all indicators and emits the 1/-1/0 composite signal, so the guidance is copy-paste ready rather than partial formulas.

Make the signal mapping explicit in code: define 'trend is bullish' as `ema_fast > ema_slow and adx > adx_threshold`, and encode the RSI/OBV conditions concretely to remove ambiguity.

Justify or remove the `requests` dependency (no data-fetch step is described) and trim the 'Purpose' table, which restates the frontmatter description.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the 'Purpose' table largely restates the frontmatter description and the 'requests' dependency is listed without any data-fetch step being described, so it could be tightened.	2 / 3
Actionability	It provides partial concrete formulas (OBV = `(volume * sign(close.diff())).cumsum()`, `ewm(alpha=1/period)`) and a full parameter table, but offers no complete executable implementation — the Long/Short/Stand-aside logic is stated as conditions rather than copy-paste-ready code.	2 / 3
Workflow Clarity	The three-dimensional voting logic is laid out, but 'trend is bullish' is never explicitly mapped to EMA-crossover and ADX-threshold conditions, and the indicator-to-signal computation sequence is implied rather than sequenced, leaving ambiguity.	2 / 3
Progressive Disclosure	This is a compact (~50-line) single-file skill with no need for external references, organized into clearly labeled sections (Purpose, Signal Logic, Implementation Details, Parameters, Dependencies, Signal Convention), which earns a 3 under the simple-skill note.	3 / 3
	Total	9 / 12 Passed

Description

60%

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 well-targeted to a quant audience but lacks an explicit 'Use when…' trigger, capping completeness and trigger-term quality at 2. It conveys concrete capabilities but not when Claude should reach for the skill.

Suggestions

Add an explicit 'Use when…' clause, e.g. 'Use when building technical-analysis signals, backtesting momentum or mean-reversion strategies, or generating trade signals from OHLCV bars.'

Include natural user-facing trigger terms alongside the abbreviations — 'trading signal', 'backtest indicators', 'momentum', 'stock/crypto indicators' — so the description reads like what a user would actually say.

Clarify distinctiveness by framing the niche ('composite three-dimensional voting signal engine') as the trigger phrase to reduce overlap with generic indicator skills.

Dimension	Reasoning	Score
Specificity	Enumerates concrete specifics — 'Core technical indicator collection (trend EMA/ADX + mean-reversion BB/RSI + volume-price OBV/volume ratio), generates a composite signal via three-dimensional voting' — naming both the actions (collection, signal generation) and the specific indicators, matching the multi-action anchor.	3 / 3
Completeness	It clearly answers 'what' (collects indicators and generates a composite voting signal) but provides no 'when' — there is no explicit 'Use when…' trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Indicator abbreviations (EMA, ADX, BB, RSI, OBV, OHLCV) are relevant for a quant audience, but the phrasing reads as a dense spec with no natural 'Use when…' trigger sentence and is missing common variations a user would say ('momentum', 'backtest', 'trading signal').	2 / 3
Distinctiveness Conflict Risk	The specific indicator combination is a clear niche, but as a 'strategy'-category skill it could overlap with other quant/indicator skills, and the distinct triggers needed to disambiguate are absent.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/technical-basic/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.