research-workflow

Systematic research workflow orchestrating multi-source research operations for comprehensive domain investigation. Sequential workflow from web search through GitHub exploration and documentation analysis to research synthesis. Use when researching new domains, gathering patterns, investigating technologies, or conducting comprehensive multi-source research for skill development.

Quality

65%

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 ./skills/research-workflow/SKILL.md

Quality

Content

46%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 content provides a clear, well-sectioned overview of a five-step research workflow but is held back by vague, non-executable step descriptions, absent validation checkpoints before synthesis, and triple repetition of the step list. It reads as a roadmap rather than actionable operating instructions.

Suggestions

Make each step actionable: include example search queries, concrete tool/CLI invocations, or a one-line code snippet instead of one-line descriptions like 'Search for best practices'.

Add an explicit validation checkpoint before Step 5 (e.g. 'Confirm at least 3-5 credible sources across categories before synthesizing') to add a feedback loop to the batch research process.

Remove the redundant triplication: keep the Quick Reference table and per-step detail, but drop the full step enumeration from the Overview so the five steps appear once as a table and once as detailed sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explanation padding, but the five steps are repeated three times (Overview list, per-step sections, Quick Reference table) plus a redundant closing summary line, so it 'could be tightened' and does not reach the lean 4-5 range.	3 / 5
Actionability	Each step is a high-level one-line hint ('Search for best practices, recent blog posts, community knowledge') with time budgets but no concrete queries, commands, code, or tool invocations, matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute' rather than the incomplete-but-present guidance of a 3.	2 / 5
Workflow Clarity	The five steps are clearly numbered and sequenced with time estimates, but there are no validation checkpoints between research and synthesis (e.g. verify sufficient credible sources before aggregating), so it matches 'steps listed but validation gaps; checkpoints missing' and is capped below 4.	3 / 5
Progressive Disclosure	The self-contained body is well sectioned (Overview, When to Use, Research Workflow, Quick Reference) with no external references needed for this orchestration skill, but the triplicated step listing is a minor organization gap keeping it at 4 rather than the cleanly split 5.	4 / 5
	Total	12 / 20 Passed

Description

83%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 is well-formed: it pairs a concrete enumeration of research operations with an explicit multi-trigger 'Use when' clause, satisfying both the what and when requirements with good specificity. Its only weakness is slightly broad trigger phrasing that risks minor overlap with adjacent research skills.

Dimension	Reasoning	Score
Specificity	Enumerates several concrete operations ('web search', 'GitHub exploration', 'documentation analysis', 'research synthesis') with only minor gaps (MCP research appears in the body but not the description), fitting 'lists several specific actions; minor gaps in coverage' rather than the 1-2 actions of a 3.	4 / 5
Completeness	It explicitly answers both what (a sequential multi-source research workflow through named operations to synthesis) and when (a concrete 'Use when...' clause with multiple triggers), matching the 5 anchor and exceeding the 4 where 'when' could be more explicit.	5 / 5
Trigger Term Quality	The 'Use when...' clause surfaces natural phrases ('researching new domains', 'gathering patterns', 'investigating technologies') that users would say, but lacks synonyms/file extensions and leans slightly formal, so it is good but not the comprehensive coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	The multi-source skill-development research niche is mostly distinct from generic single-source research skills, though broad triggers like 'investigating technologies' create minor overlap risk with related research skills, so it sits at 4 rather than the clearly-bounded 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/research-workflow/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.