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.

2.00x

Quality

79%

Does it follow best practices?

Impact

62%

2.00x

Average score across 3 eval scenarios

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/toolkit/skills/research/SKILL.md

Quality

Content

75%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 body is well-structured and actionable with concrete commands and a clear numbered research workflow. It could improve by adding validation checkpoints, moving the verbose output template to a reference file, and tightening example prompt prose.

Suggestions

Add an explicit validation step in the evidence workflow (e.g., confirm 2-3 datapoints are independent before recommending) to create a feedback checkpoint.

Move the full markdown output template into a references file and keep only a short inline example in SKILL.md to improve progressive disclosure.

Tighten the "Handle Blocked Content" example prompt and "Look for" bullet lists to remove padding Claude does not need.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with short sections and code blocks, but the example prompt templates and "Look for" lists add minor over-explanation that could be trimmed, matching the 4 anchor.	4 / 5
Actionability	Provides concrete executable commands (git clone, mkdir -p) and a copy-ready output template, but uses placeholder repo URLs and leaves some evidence-gathering steps advisory, matching the 4 anchor.	4 / 5
Workflow Clarity	Clear numbered sequence from web search through evidence and output, but lacks explicit validation checkpoints or feedback loops, matching the 4 anchor.	4 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, but the body is moderately long with an inlined output template that could live in a reference file, matching the 4 anchor.	4 / 5
	Total	16 / 20 Passed

Description

83%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 strong: it states concrete actions, provides explicit trigger phrases, and clearly distinguishes what the skill does from when to invoke it. Minor gaps in synonym coverage and the broad research niche keep trigger quality and distinctiveness at 4 rather than 5.

Suggestions

Add common synonyms such as "investigate", "evaluate", or "compare options" to broaden natural trigger coverage.

Tie the trigger more tightly to a niche (e.g., "pre-implementation technology evaluation") to reduce overlap with general web-search skills.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions — "searching the web, examining GitHub repos, and gathering evidence" — with only minor coverage gaps, matching the 4 anchor.	4 / 5
Completeness	Explicitly answers what (research technical solutions via web/GitHub/evidence) and when ("Use when the user explicitly says..."), with concrete trigger phrases matching the 5 anchor.	5 / 5
Trigger Term Quality	Good coverage of natural phrases ("use the research skill", "use a research agent", "deep/thorough research") users would actually say, though a few synonyms are missing, matching the 4 anchor.	4 / 5
Distinctiveness Conflict Risk	Explicit invocation triggers make it mostly distinct from other skills, though the broad "research" scope leaves minor overlap risk with general web-search skills, matching the 4 anchor.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: dwmkerr/claude-toolkit
Path: plugins/toolkit/skills/research/SKILL.md
Commit: 4316684

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.