CtrlK
BlogDocsLog inGet started
Tessl Logo

tool-evaluator

Expert technology assessment specialist focused on evaluating, testing, and recommending tools, software, and platforms for business use and productivity optimization

30

Quality

13%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./testing-tool-evaluator/skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

0%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads like a generic job title or LinkedIn headline rather than a functional skill description. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and any distinguishing specificity that would help Claude select it appropriately from a pool of skills.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'compare tools', 'which software should I use', 'tool recommendation', 'best app for', 'software comparison'.

Replace vague language with specific concrete actions such as 'Creates comparison matrices for software tools, writes pros/cons analyses, evaluates pricing tiers, and produces recommendation reports'.

Narrow the scope to a distinct niche (e.g., specific tool categories like project management, CRM, or developer tools) to reduce conflict risk with other general-purpose skills.

DimensionReasoningScore

Specificity

The description uses vague, abstract language like 'evaluating, testing, and recommending' and 'productivity optimization' without listing any concrete actions. There are no specific deliverables or operations mentioned—it reads like a job title rather than a capability description.

1 / 3

Completeness

The description weakly addresses 'what' with vague terms and completely lacks a 'when' clause or any explicit trigger guidance. There is no 'Use when...' or equivalent statement to help Claude know when to select this skill.

1 / 3

Trigger Term Quality

The terms used ('technology assessment specialist', 'productivity optimization', 'platforms for business use') are generic buzzwords rather than natural keywords a user would say. A user would more likely say 'compare tools', 'which software should I use', 'tool recommendation', or name specific categories like 'project management tools' or 'CRM software'.

1 / 3

Distinctiveness Conflict Risk

The description is extremely generic—'evaluating tools, software, and platforms' could overlap with virtually any skill that involves technology decisions. There is nothing to distinguish this from general consulting, software development, or IT advisory skills.

1 / 3

Total

4

/

12

Passed

Implementation

27%

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

This skill reads more like a persona/role-play prompt than an actionable skill file. It is extremely verbose, spending significant tokens on identity descriptions, personality traits, success metrics, and communication style coaching that Claude doesn't need. The Python framework, while structurally interesting, is incomplete with multiple undefined methods, and the overall document lacks the concise, actionable, well-structured format that makes skills effective.

Suggestions

Remove all persona/identity/memory/communication style sections—these waste tokens on things Claude already knows how to do and aren't actionable skill content.

Complete the Python evaluation framework by implementing the stub methods (_test_usability, _assess_security, etc.) or remove them and focus on the actually executable portions.

Extract the Python framework into a separate reference file (e.g., EVALUATION_FRAMEWORK.md) and the report template into REPORT_TEMPLATE.md, keeping SKILL.md as a concise overview with clear links.

Add explicit validation checkpoints and decision gates to the workflow (e.g., 'If weighted scores differ by <5%, conduct additional differentiation testing before recommending').

DimensionReasoningScore

Conciseness

Extremely verbose with extensive sections explaining concepts Claude already knows (what TCO is, what usability testing is, communication style coaching, success metrics, personality descriptions). The 'identity & memory' and 'learning & memory' sections are pure padding. The massive Python class includes stub methods that aren't executable. Most content describes rather than instructs.

1 / 3

Actionability

The Python evaluation framework provides some concrete structure but is incomplete—several methods (_test_feature, _test_usability, _assess_security, _test_integration, _evaluate_support, _analyze_cost, _generate_recommendations) are referenced but never defined. The deliverable template is a useful skeleton but is a markdown template rather than executable guidance. Much of the content is aspirational description rather than concrete instruction.

2 / 3

Workflow Clarity

The 4-step workflow process is listed with clear sequencing, but lacks validation checkpoints or feedback loops. There's no guidance on what to do when evaluations produce ambiguous results, when tools fail testing, or how to handle conflicting stakeholder requirements. For a process involving significant business decisions, the absence of explicit decision gates and verification steps is a gap.

2 / 3

Progressive Disclosure

This is a monolithic wall of text at ~300+ lines with no references to external files. The massive Python code block, detailed report template, advanced capabilities section, success metrics, and communication style guidance are all inlined. The final line references 'core training' vaguely rather than pointing to specific files. Content that should be in separate reference files (evaluation framework code, report templates, advanced methodologies) is all crammed into one document.

1 / 3

Total

6

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
OpenRoster-ai/awesome-openroster
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.