CtrlK
BlogDocsLog inGet started
Tessl Logo

portfolio

Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Triggered by a pasted wallet address or questions about yield, positions or rebalancing. Aggregates positions across the user's addresses in one project.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 a tightly written, highly actionable procedural skill with an explicit sequenced workflow and strong validation feedback loops. Its only weaknesses are mild redundancy between the procedure and the Hard Rules section, and an inline-heavy structure with one referenced bundle path missing.

Suggestions

Consolidate the 'Hard rules' section into the relevant procedure steps (or trim rules already covered in-step) to reduce redundancy and improve conciseness.

Either ship the referenced widget/ files (manifest.json, index.js, style.css) in the bundle or note they are generated at install time, so the progressive-disclosure references resolve to real files.

Consider moving the inline strategy-doc frontmatter example and the config.json block into a short references/ doc to keep the core workflow lean.

DimensionReasoningScore

Conciseness

The body is dense and procedural, assuming Claude's intelligence about DeFi concepts without padding, but the closing 'Hard rules' section restates several procedure constraints (fabrication, floor_apy units, source=auto), adding mild redundancy; mostly efficient with minor trim potential, so 4 rather than 5.

4 / 5

Actionability

Guidance is fully executable: exact tool-call parameters (action='scan', source='auto'), a concrete config.json block, verbatim strategy-doc frontmatter, and precise file paths cover the common cases copy-paste ready, matching the 5 anchor.

5 / 5

Workflow Clarity

An 11-step procedure is clearly sequenced with explicit validation checkpoints (skip propose on zero positions, NoRoute downgrade + retry, never overwrite history) and feedback loops for error recovery, matching the 5 anchor.

5 / 5

Progressive Disclosure

The four bundled scripts/ files are clearly listed and signaled in step 11, and the widget files are referenced one level deep; however the bulk of the procedural content is inlined in a single SKILL.md and the referenced widget/ files are not present in the bundle, leaving minor organization gaps that fall just below the 5 anchor.

4 / 5

Total

18

/

20

Passed

Description

87%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, well-triggered, and complete, clearly stating both what the skill does and when to invoke it with natural user phrases. Its only mild weakness is slightly less exhaustive action/keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('Cross-chain DeFi portfolio') and several concrete actions ('discovery, rebalancing suggestions, and NEAR Intent construction', 'Aggregates positions'), giving good but not exhaustive coverage; not a 5 because it stops short of listing the full breadth of operations the skill performs.

4 / 5

Completeness

Explicitly answers both what ('Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction') and when ('Triggered by a pasted wallet address or questions about yield, positions or rebalancing') with concrete trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural trigger terms are present ('pasted wallet address', 'yield', 'positions', 'rebalancing') that users would actually say; missing some common synonyms/variations, so it falls just below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The cross-chain DeFi / NEAR Intent niche with address-pattern triggers is highly distinct and unlikely to fire for unrelated skills, matching the clear-niche 5 anchor.

5 / 5

Total

18

/

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
nearai/ironclaw
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.