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

Quality

Content

50%

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

The content provides a reasonably structured research methodology with some concrete examples, but it is padded with generic best-practice advice, lacks validation checkpoints in its workflow, and keeps all detail inline rather than using progressive disclosure.

Suggestions

Remove the generic "Best Practices" list and the closing "Remember:" line — they restate obvious guidance Claude already applies.

Add an explicit validation step to the methodology (e.g. cross-check findings against the actual code before writing recommendations) so the workflow has a checkpoint.

Move the MCP tool integration details and the full YAML output schema into reference files (e.g. references/output-format.md) and link to them from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly organized with useful code blocks, but generic sections like "Best Practices" ("Be Thorough", "Think Critically", "Stay Organized") and the closing "Remember: Good research is the foundation..." restate concepts Claude already knows and could be trimmed.

2 / 3

Actionability

There are concrete executable examples (e.g. `grep -r "class.*Controller" --include="*.ts"` and MCP calls), but they sit alongside abstract guidance ("Use multiple search strategies", "Read relevant files completely") and the YAML output block is a template rather than runnable code.

2 / 3

Workflow Clarity

The Research Methodology is numbered (Information Gathering → Pattern Analysis → Dependency Analysis → Documentation Mining), giving a clear sequence, but there are no validation/verification checkpoints or feedback loops to confirm findings before synthesis.

2 / 3

Progressive Disclosure

The ~190-line body is well-sectioned but monolithic with no external reference files; content like the detailed MCP integration and the YAML output schema is inline and could be split into separate reference files.

2 / 3

Total

8

/

12

Passed

Description

22%

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 meta-instructional rather than capability-focused: it tells how to invoke the skill but not what it concretely does or when to use it. It fails to provide explicit trigger guidance or specific actions.

Suggestions

Rewrite to lead with concrete actions, e.g. "Analyzes codebases to map structure, identify patterns, track dependencies, and synthesize research findings into recommendations."

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g. "Use when investigating an unfamiliar codebase, mapping dependencies, or summarizing research findings").

Drop the invocation hint ("invoke with $agent-researcher") from the description; it is not a capability and wastes the trigger-term budget.

DimensionReasoningScore

Specificity

The description names no concrete actions — "Agent skill for researcher - invoke with $agent-researcher" only labels the skill's role and invocation, never saying what it does, matching the vague/no-actions anchor.

1 / 3

Completeness

The "what" is very weak ("agent skill for researcher" says nothing concrete) and the "when" is entirely absent with no "Use when..." trigger guidance, so both halves are missing or very weak.

1 / 3

Trigger Term Quality

"researcher" is one relevant domain keyword, but the phrasing is meta/instructional ("invoke with $agent-researcher") rather than task-based, and common natural variations like "research this codebase" or "analyze" are missing.

2 / 3

Distinctiveness Conflict Risk

"researcher" gives a slight niche but the description is otherwise generic with no distinct triggers, so it could still overlap with other research/analysis skills.

2 / 3

Total

6

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.