research

Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems.

2.05x

Quality

71%

Does it follow best practices?

Impact

80%

2.05x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/data/0-research/SKILL.md

Quality

Content

63%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.

A well-sequenced research methodology with concrete commands and a usable report scaffold. It loses points for token efficiency (a large inlined report template) and progressive disclosure (no external reference files despite content that would benefit from splitting).

Suggestions

Move the full report scaffold into a `references/report-template.md` and keep only a short structural summary inline, linking out with 'See [report-template.md](references/report-template.md)'.

Merge the redundant 'Quality Standards', 'Special Considerations', and 'Output Requirements' sections into a single concise checklist to cut padding.

Add an explicit feedback loop in Phase 2/3 (e.g. 'If sources conflict, note the disagreement and run one targeted follow-up search to resolve it') to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and does not over-explain concepts Claude knows, but the ~65-line inlined report scaffold plus overlapping 'Quality Standards', 'Special Considerations', and 'Output Requirements' sections add padding that could be trimmed.	3 / 5
Actionability	Provides concrete executable guidance (the `gemini -m gemini-3-preview-p "..."` command with timeout, the `./plans/<plan-name>/reports/YYMMDD-<topic>.md` path, and a copy-paste report scaffold), with minor gaps around the WebSearch fallback query construction.	4 / 5
Workflow Clarity	Phases 1-4 are clearly sequenced and Phase 2 step 4 plus Quality Standards give validation checkpoints (cross-reference sources, check dates); short of 5 because there is no explicit validate->fix->retry feedback loop when sources conflict.	4 / 5
Progressive Disclosure	Section structure is clear, but the skill is a single ~160-line monolith with no bundle files: the large report template is inlined and nothing is split into one-level-deep references, so organization could be improved.	3 / 5
	Total	14 / 20 Passed

Description

80%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.

A thorough, well-structured description that clearly states capabilities and explicit 'Use when' triggers. Its main weakness is distinctiveness: the generic 'research' framing and broad verbs risk overlapping with other research-flavored skills.

Suggestions

Tighten the niche by leading with the distinguishing framing (e.g. 'Technical research and trade-off assessment for architecture/solution decisions') so it is less likely to trigger for general research tasks.

Drop low-signal jargon triggers (YAGNI/KISS/DRY, feasibility study) that users rarely say verbatim in favor of more natural phrases like 'compare options', 'evaluate a library', or 'pick between architectures'.

Add a concrete artifact cue (e.g. 'produces a structured markdown research report') to sharpen what distinguishes this skill from generic web search.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design' and verbs 'research, analyze, evaluate, compare, recommend'), but they remain somewhat abstract with no concrete artifacts, so just short of comprehensive.	4 / 5
Completeness	Explicitly answers both what (methodology, capabilities, actions) and when via a concrete 'Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems.' clause.	5 / 5
Trigger Term Quality	Good natural-term coverage ('research', 'best practices', 'trade-offs', 'compare solutions', 'evaluate architecture') a user would actually say, with minor gaps and some jargon-heavy terms (YAGNI/KISS/DRY, feasibility study) diluting naturalness.	4 / 5
Distinctiveness Conflict Risk	The 'research'/'analyze'/'evaluate' verbs are broad and overlap with many general-purpose or research-oriented skills; the technical-research niche helps but conflict risk with sibling skills remains moderate.	3 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: majiayu000/claude-skill-registry
Path: skills/data/0-research/SKILL.md
Commit: 04324c6

Reviewed: about 21 hours 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.