CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-research

Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.

100

1.13x
Quality

100%

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Evaluation results

100%

16%

EV Charging Infrastructure: Competitive Landscape Research

Research intake and evidence table

Criteria
Without context
With context

Report spec file

100%

100%

Subquestions count

100%

100%

Scope and exclusions

75%

100%

Query set present

100%

100%

Raw research files

100%

100%

Evidence table exists

100%

100%

Evidence table: Source ID column

100%

100%

Evidence table: Publisher and Date

100%

100%

Evidence table: Quality tier

0%

100%

Evidence table: Notes column

100%

100%

Source exclusion applied

100%

100%

Disqualifiers defined

60%

100%

100%

14%

Renewable Energy Subsidies Policy Brief

Multi-pass parallel drafting workflow

Criteria
Without context
With context

Multiple draft files

100%

100%

Each draft is full report

66%

100%

No section-only files

100%

100%

Drafts written to files

100%

100%

Intermediate files preserved

100%

100%

UNION merge evidence

30%

100%

Final report H2 structure

100%

100%

Final report H3 subsections

100%

100%

Evidence table present

70%

100%

Report spec file

100%

100%

References section

100%

100%

100%

4%

Supply Chain Resilience Report: Verification and Compliance Pass

Format compliance and citation verification

Criteria
Without context
With context

Completeness review file

100%

100%

Structure check documented

100%

100%

Citation check documented

100%

100%

Numeric claims cited

100%

100%

Conflicting sources flagged

100%

100%

Executive Summary section

100%

100%

Methodology section

100%

100%

Risks and Limitations section

100%

100%

Evidence table present

50%

100%

References/bibliography

100%

100%

H2 top-level sections

100%

100%

No inline URLs in prose

100%

100%

Repository
fernandezbaptiste/claude-code-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.