comprehensive-research-agent

Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/interleaved-thinking/generated_skills/comprehensive-research-agent/SKILL.md

Quality

Content

42%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 delivers concrete, actionable research-quality protocols with explicit validation checkpoints, but is hurt by significant cross-section redundancy, non-execution metadata padding, and a lack of any external reference structure or reusable templates.

Suggestions

Collapse 'Patterns to Avoid', 'Recommended Practices', and 'Guidelines' into a single non-redundant section, and remove the 'Score Expectations' and 'Skill Metadata' optimization-process blocks that do not aid execution.

Convert the narrative before/after Examples into reusable templates (e.g., a fill-in source-tracking table and a thinking-block skeleton) that Claude can copy directly.

Present the protocols as one explicit ordered research workflow (search -> rank sources -> read -> synthesize/validate -> cross-check -> report with gaps) so the sequence and checkpoints are coherent rather than distributed.

Dimension	Reasoning	Score
Conciseness	The 'Patterns to Avoid', 'Recommended Practices', and 'Guidelines' sections restate the same four to five ideas, and the 'Score Expectations' and 'Skill Metadata' sections are process padding that does not help Claude execute the skill.	2 / 5
Actionability	Concrete directives exist (thinking blocks of 3-5+ sentences with four enumerated parts, a pre-completion checklist, a source-tracking table), but examples are narrative before/after paragraphs rather than reusable templates or executable artifacts.	3 / 5
Workflow Clarity	Validation checkpoints are explicit (pre-read source evaluation, post-read synthesis, pre-completion checklist), but there is no single coherent numbered workflow; practices are scattered across multiple sections.	3 / 5
Progressive Disclosure	Section structure is reasonable, but the skill is monolithic with all content inline; the provided references/ files are optimization metadata never referenced from the body, and the long narrative Examples could live in separate files.	3 / 5
	Total	11 / 20 Passed

Description

46%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 clearly states the domain and several process-level actions but lacks an explicit activation trigger and uses generic language that overlaps heavily with other agent skills.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when conducting web research, gathering information from multiple sources, or running multi-step lookups').

Replace abstract process terms with concrete actions the user will see in output (e.g., 'cross-validate claims across sources', 'document unretrieved sources as gaps').

Narrow the scope so it is distinguishable from generic agent skills — specify the research quality niche (e.g., 'multi-source research reliability') rather than 'multiple tool calls'.

Dimension	Reasoning	Score
Specificity	Names the domain ('research tasks with multiple tool calls') and several actions (validation, error recovery, transparent reasoning), but the actions are abstract processes rather than concrete deliverable actions like 'extract' or 'fill'.	3 / 5
Completeness	Provides a clear 'what' but no explicit 'Use when...' trigger clause; per rubric guideline, a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	'research' is a natural user term, but 'multiple tool calls' is technical jargon and common user phrasings like 'look up', 'find information', or 'search the web' are missing.	3 / 5
Distinctiveness Conflict Risk	'multiple tool calls' describes virtually any agent task, giving the description broad overlap risk with many general research and agent skills rather than a distinct niche.	2 / 5
	Total	11 / 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: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: examples/interleaved-thinking/generated_skills/comprehensive-research-agent/SKILL.md
Commit: 6dbe1a1

Reviewed: 3 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.