CtrlK
BlogDocsLog inGet started
Tessl Logo

comprehensive-research-agent

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

40

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/comprehensive-research-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

The skill offers genuinely useful, well-illustrated research-quality practices, but it duplicates the same guidance across five sections, stays largely instructional rather than executable, lacks a single crisp sequenced workflow, and is a monolithic body that ignores its own reference bundle. Restructuring and de-duplicating would lift all four dimensions.

Suggestions

Collapse the duplicated guidance across Core Concepts / Patterns / Recommended Practices / Guidelines into one section, keeping only the before/after Examples as illustration, to remove redundant tokens.

Turn the Guidelines list into a single explicit sequenced workflow with numbered validation checkpoints (e.g., rank sources -> read -> validate -> cross-check -> pre-completion checklist) and error-recovery feedback loops.

Move detailed material into the existing references/ bundle files and link them from the body (e.g., 'See patterns_found.json for the full anti-pattern catalog') so SKILL.md becomes a concise overview with one-level-deep navigation.

DimensionReasoningScore

Conciseness

Concept definitions in Core Concepts are reasonably tight, but the same guidance is restated across Core Concepts, Patterns to Avoid, Recommended Practices, Guidelines, and Examples (e.g., source tracking and read_file-vs-list_directory appear multiple times), adding redundant tokens that a level-3 lean body would not carry.

2 / 3

Actionability

The before/after Examples are concrete and useful, but most guidance is instructional prose lists ("implement a tracker", "maintain a table") rather than executable code or commands, and several items stay abstract, fitting the level-2 "some concrete guidance but incomplete" anchor.

2 / 3

Workflow Clarity

Guidelines 1-10 enumerate validation practices and checkpoints conceptually, but there is no single clearly sequenced multi-step workflow with explicit validation gates and recovery loops; it is a practice checklist rather than the level-3 sequenced-process-with-feedback anchor.

2 / 3

Progressive Disclosure

The body is a monolithic wall of text spanning concepts, patterns, practices, guidelines, and examples all inline, and the existing bundle files in references/ are never signaled or linked from the body, matching the level-1 monolithic/poor-organization anchor.

1 / 3

Total

7

/

12

Passed

Description

35%

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 conveys the skill's intent and domain but relies on abstract quality statements rather than concrete actions, omits an explicit "Use when" trigger, and uses technical phrasing instead of natural user keywords. It is distinguishable but not sharply niche.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural terms users would say (e.g., 'Use when doing multi-source web research, gathering and verifying information, or running multi-step searches').

Replace abstract quality language ('thorough validation, error recovery, transparent reasoning') with concrete capability verbs (e.g., 'Validates sources, recovers from tool errors, traces citations, and cross-checks claims across sources').

Add common trigger variations (research, search, sources, verify, multi-step) to reduce overlap with generic browsing/research skills.

DimensionReasoningScore

Specificity

Quotes "thorough validation, error recovery, and transparent reasoning" name the research-task domain and several actions, but the actions are abstract process qualities rather than the concrete, comprehensive capability list a level-3 anchor requires.

2 / 3

Completeness

It states what the skill does ("Ensure thorough validation...") but provides no explicit "Use when..." trigger clause, so per guideline it caps at 2 rather than reaching the level-3 both-what-and-when anchor.

2 / 3

Trigger Term Quality

The phrase "research tasks with multiple tool calls" uses technical jargon; it lacks the natural terms a user would say (e.g., "research", "search", "sources", "verify") and offers no common variations, matching the level-1 jargon anchor.

1 / 3

Distinctiveness Conflict Risk

The "research tasks with multiple tool calls" framing carves out a niche but is broad enough to overlap with general research or web-browsing skills, fitting the level-2 "somewhat specific but could overlap" anchor rather than a clearly distinct trigger set.

2 / 3

Total

7

/

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
foryourhealth111-pixel/Vibe-Skills
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.