deep-research

Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis. Use for comprehensive research, deep analysis, or evidence-backed answers. Produces executive summary + markdown report. Supports search tools, playwright-cli, and MCP.

Quality

88%

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

Quality

Content

88%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.

A well-structured orchestration skill with executable prompts, concrete scoring formulas, and rigorous validation/feedback checkpoints across a clear phase sequence. The only soft spots are the length of the Phase 0 method-detection block and slightly heavier inlining of operational detail.

Suggestions

Trim the Phase 0 search-instruction example block (e.g. consolidate the four near-identical method examples into a single parameterized template) to lift conciseness toward anchor 5.

Consider moving the worker output format and scoring rubric details into the existing `assets/report_template.md` or a sibling reference so SKILL.md stays a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no concept explanations or padding, but the multi-method search-instruction block in Phase 0 is fairly extensive, keeping it just below the lean anchor-5 example.	4 / 5
Actionability	Provides fully executable guidance throughout — the `mktemp -d` command, the exact subagent prompt template, numeric scoring tables with formulas, and citation format are copy-paste ready and cover the common cases.	5 / 5
Workflow Clarity	Phases 0–5 are clearly sequenced with explicit validation checkpoints (Phase 2 post-worker check table, Phase 3 escalation threshold < 6.0 with retry loop, Phase 5 integrity verification that stops on failure), including feedback loops for this batch operation.	5 / 5
Progressive Disclosure	SKILL.md is an overview that signals one real one-level-deep reference (`assets/report_template.md`) inline and in a References section, with content appropriately split; minor gap is that most operational detail lives inline rather than being further externalized.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

A strong description that clearly states both capability and trigger conditions with concrete, distinguishable language. It could push higher on specificity and trigger-term coverage by adding crisper action verbs and a few more natural synonyms.

Suggestions

Lead with concrete action verbs (e.g. 'Conduct multi-directional deep research ... score and verify sources ... synthesize a cited report') to lift specificity to anchor 5.

Add common trigger synonyms such as 'literature review', 'investigate a topic', or 'cite sources' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('sub-agents, scoring, source verification, and cited synthesis', 'Produces executive summary + markdown report') but the verbs are somewhat abstract rather than the crisp action verbs of the anchor-5 example.	4 / 5
Completeness	Explicitly answers both what ('Multi-directional deep research with sub-agents, scoring, source verification, and cited synthesis ... Produces executive summary + markdown report') and when ('Use for comprehensive research, deep analysis, or evidence-backed answers') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('comprehensive research, deep analysis, or evidence-backed answers') with good coverage, but misses common synonyms like 'literature review', 'investigate', or 'cite sources'.	4 / 5
Distinctiveness Conflict Risk	'Multi-directional deep research with sub-agents, scoring, source verification' carves a clear niche distinct from generic search or single-query skills, with minimal overlap risk.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/deep-research/SKILL.md
Commit: b4ba256

Reviewed: ~20 hours 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.