CtrlK
BlogDocsLog inGet started
Tessl Logo

onchain-analysis

On-chain data analysis — active addresses / whale tracking / TVL / DEX liquidity, interpretation and signal generation using on-chain valuation metrics such as MVRV / NVT / SOPR.

49

Quality

54%

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/onchain-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 skill is information-rich and largely actionable with concrete thresholds, formulas, and a worked report template, but it over-explains concepts Claude already knows and lacks validation checkpoints and external reference files for progressive disclosure.

Suggestions

Trim definitional filler Claude already knows (e.g. 'TVL = total value of assets locked', the PE-ratio analogy for NVT) to tighten conciseness toward 5.

Add explicit validation/sanity-check steps to the analysis workflow (e.g. confirm data freshness, cross-check exchange-balance against two sources) to lift workflow clarity above 3.

Move the historical reference tables and the detailed metric reference into separate reference files (e.g. references/metrics.md, references/historical-benchmarks.md) and link to them from SKILL.md for better progressive disclosure.

DimensionReasoningScore

Conciseness

Most content is efficient tables and compact signal lists, but it explains concepts Claude already knows (e.g. 'TVL = total value of assets locked', 'NVT similar to a PE ratio', 'Stablecoin inflows = dry powder') and repeats definitions across sections, which could be tightened.

3 / 5

Actionability

Concrete signal thresholds, metric formulas (MVRV, NVT_Signal, SOPR), and a worked output report make the guidance mostly executable; minor gaps are the lack of specific API calls to retrieve the raw data.

4 / 5

Workflow Clarity

A composite scoring framework and output template provide sequence, but there are no explicit validation checkpoints or feedback loops, and data-source acquisition (Glassnode/Nansen) is only mentioned in notes rather than integrated as a step.

3 / 5

Progressive Disclosure

The body is well sectioned with headers, but it is a monolithic single-file reference with no bundle files and no one-level-deep pointers; much of the metric reference and historical tables could live in separate reference files.

3 / 5

Total

13

/

20

Passed

Description

51%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 names a specific, well-scoped niche with concrete metrics, but it omits any explicit 'Use when...' trigger guidance, leaving Claude without clear activation cues. Trigger-term phrasing also leans technical rather than matching natural user language.

Suggestions

Add an explicit 'Use when ...' clause naming natural user triggers, e.g. 'Use when analyzing on-chain data, tracking whale movements, or evaluating crypto valuation via MVRV/NVT/SOPR.'

Surface common user phrasings and synonyms in the description so it matches how users actually ask (e.g. 'on-chain analysis', 'whale tracking', 'blockchain data').

Reframe the slash-separated list as concrete verbs (e.g. 'Tracks whale activity, computes TVL/DEX liquidity, and evaluates valuation via MVRV/NVT/SOPR') to lift specificity toward 5.

DimensionReasoningScore

Specificity

Lists several concrete analytical capabilities — 'active addresses / whale tracking / TVL / DEX liquidity' plus 'MVRV / NVT / SOPR' — giving good coverage, though framed as topic areas rather than fully enumerated actions.

4 / 5

Completeness

The 'what' is reasonably clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the guidelines; it sits at 2 because the when is entirely absent rather than weakly implied.

2 / 5

Trigger Term Quality

Domain keywords like 'on-chain', 'TVL', 'whale tracking', and 'MVRV / NVT / SOPR' are present, but the natural phrases a user would actually say ('analyze on-chain data', 'whale movements') are not surfaced and synonyms are thin.

3 / 5

Distinctiveness Conflict Risk

The on-chain valuation niche (MVRV/NVT/SOPR, whale tracking) is fairly distinct from generic crypto skills, with only minor overlap risk against a broader market-analysis skill.

4 / 5

Total

13

/

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
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.