CtrlK
BlogDocsLog inGet started
Tessl Logo

research

Deep research into technical solutions by searching the web, examining GitHub repos, and gathering evidence. Use when the user explicitly says "use the research skill", "use a research agent", or asks for deep/thorough research into implementation options or technologies.

75

2.00x
Quality

73%

Does it follow best practices?

Impact

62%

2.00x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/toolkit/skills/research/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

This is a reasonably well-structured research skill that provides a clear workflow and useful output template. Its main weaknesses are the lack of explicit validation/feedback loops in the research process and some sections that describe strategies Claude would naturally employ (like asking users for blocked content). The actionability could be improved with more specific tool usage patterns rather than abstract procedural descriptions.

Suggestions

Add an explicit validation checkpoint after evidence gathering, e.g., 'Before presenting findings, verify: Do you have ≥2 independent sources per option? Are sources from the last 2 years? If not, iterate.'

Make web search steps more actionable by specifying tool usage patterns (e.g., specific search query formulation strategies or how to use the web search tool with targeted queries)

Remove or condense the 'Handle Blocked Content' section—Claude already knows to ask users for inaccessible content; a single line would suffice

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary explanation. The 'Handle Blocked Content' section explains obvious fallback strategies Claude would know. The example prompts are helpful but slightly verbose. The overall structure is reasonable but could be tightened.

2 / 3

Actionability

Provides concrete bash commands for cloning repos and creating directories, and a clear output format template. However, the core research steps are more procedural guidance than executable instructions—web search steps are described abstractly rather than with specific tool invocations or concrete examples of search queries.

2 / 3

Workflow Clarity

Steps are clearly numbered and sequenced (search → examine → handle blocks → store → verify evidence). However, there are no explicit validation checkpoints or feedback loops—no step says 'verify your findings before proceeding' or provides criteria for when research is sufficient vs. needs more iteration. The evidence requirements section partially addresses this but lacks a clear decision gate.

2 / 3

Progressive Disclosure

For a skill of this size (~80 lines) with no bundle files, the content is well-organized into logical sections with clear headers. The structure flows naturally from process steps to output format to example usage. No external references are needed for this scope, and the sections are appropriately sized.

3 / 3

Total

9

/

12

Passed

Description

89%

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 is a well-structured skill description that clearly defines when it should be triggered, with explicit invocation phrases that reduce conflict risk. The 'what' portion could be slightly more specific about concrete deliverables (e.g., comparison tables, recommendation reports), but overall it provides sufficient detail for skill selection. The explicit trigger requirements make it particularly distinctive.

DimensionReasoningScore

Specificity

Names the domain (technical research) and some actions (searching the web, examining GitHub repos, gathering evidence), but the actions are somewhat general and could be more concrete about specific outputs or deliverables.

2 / 3

Completeness

Clearly answers both 'what' (deep research by searching web, examining GitHub repos, gathering evidence) and 'when' (explicit 'Use when...' clause with specific trigger phrases and scenarios).

3 / 3

Trigger Term Quality

Includes strong natural trigger terms: 'research skill', 'research agent', 'deep research', 'thorough research', 'implementation options', 'technologies'. These cover the phrases users would naturally say when requesting this capability.

3 / 3

Distinctiveness Conflict Risk

The requirement for explicit invocation ('use the research skill', 'use a research agent') and the focus on deep/thorough technical research with GitHub repos creates a clear niche that is unlikely to conflict with general web search or coding skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
dwmkerr/claude-toolkit
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.