CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-researcher

Agent skill for researcher - invoke with $agent-researcher

58

1.88x
Quality

36%

Does it follow best practices?

Impact

98%

1.88x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-researcher/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

28%

Codebase Investigation: Data Pipeline Library

Broad-to-narrow search and documentation mining

Criteria
Baseline
With context

Multiple search strategies

100%

100%

Broad-to-narrow evidence

100%

100%

Docstring extraction

100%

100%

README mining

100%

100%

Cross-reference analysis

100%

100%

Data flow tracking

100%

100%

Patterns with locations

0%

100%

Gaps with impact levels

0%

100%

YAML research format

20%

100%

Process log produced

100%

100%

100%

75%

Codebase Research Report: Express Authentication Service

Research output YAML format

Criteria
Baseline
With context

Top-level key

0%

100%

Summary field

20%

100%

Codebase structure

10%

100%

Patterns with locations

33%

100%

External deps format

33%

100%

Internal deps format

30%

100%

Recommendations list

10%

100%

Gaps with impact

26%

100%

Impact values

0%

100%

YAML format

100%

100%

94%

33%

Dependency Audit: Plugin-Based Notification Service

Dependency mapping and cross-reference analysis

Criteria
Baseline
With context

Import statement tracking

100%

80%

External deps documented

100%

100%

External dep version field

100%

100%

External dep usage field

70%

100%

Internal module mapping

60%

100%

Dependents field

0%

100%

API contracts documented

40%

60%

Integration points identified

90%

100%

Gaps with suggestions

40%

100%

YAML research format

10%

100%

Repository
ruvnet/claude-flow
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.