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.

82

2.00x
Quality

Does it follow best practices?

Impact

62%

2.00x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is well-structured and actionable with executable commands and a clear numbered process, but it is somewhat padded by a full output template and example prompts, and its workflow lacks explicit validation checkpoints. Tightening the template and adding a validate-and-retry step around evidence gathering would lift the weaker dimensions.

Suggestions

Trim or condense the full Output Format markdown template and the example-prompt blockquotes; reference the structure briefly rather than reproducing an entire copy-paste block.

Add an explicit validation/feedback checkpoint to the workflow — e.g., after gathering evidence, verify the 2-3 datapoint threshold is met before recommending, and loop back to search if not.

Consider moving the worked terminal-recording example into a separate reference file to keep the main body as a lean overview.

DimensionReasoningScore

Conciseness

The body is mostly lean and action-oriented with no concept-explanation fluff, but the full copy-paste Output Format template and example-prompt blockquotes are padding Claude could generate itself; could be tightened. Not level 3 because not every token earns its place, and not level 1 because there is no generic background explanation.

2 / 3

Actionability

Provides fully executable commands (git clone, cat README, mkdir -p ./scratch/research) and a concrete worked search-query example, matching the copy-paste-ready anchor. Not level 2 because the code is real and complete rather than pseudocode.

3 / 3

Workflow Clarity

Steps 1-5 are clearly sequenced, but validation checkpoints are implicit (the "Minimum 2-3 datapoints" gate is stated but has no validate-fix-retry loop). Not level 3 because explicit validation/feedback steps are missing; not level 1 because the sequence is clear and present.

2 / 3

Progressive Disclosure

No bundle files exist and the body references none; the skill is a single well-organized file with clean section headers and easy navigation, which satisfies the simple-skill carve-out for a top score. Not level 2 because nothing that should be split is inlined and organization is clean.

3 / 3

Total

10

/

12

Passed

Description

100%

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 strong: it states concrete capabilities, gives natural user-facing trigger phrases, and clearly distinguishes both what the skill does and when to invoke it. It does not over-claim or pad with vague language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "searching the web", "examining GitHub repos", "gathering evidence" — matching the anchor for multiple specific concrete actions; not level 2 because it goes beyond naming a domain and a few actions.

3 / 3

Completeness

Explicitly answers both what ("Deep research into technical solutions...") and when ("Use when the user explicitly says...") with explicit triggers; not level 2 because the when is stated explicitly rather than implied.

3 / 3

Trigger Term Quality

Includes natural phrasings a user would actually say — "use the research skill", "use a research agent", "deep/thorough research" — giving good coverage rather than only some relevant keywords.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche (deep technical research) with distinct explicit triggers tied to the research-skill/agent phrasing, making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

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.