deep-dive

Claude-native deep research using DAG-based query planning, parallel subagent execution, and gap-driven iteration. No external API needed.

Quality

62%

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/deep-dive/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete templates and a clear end-to-end process, but it is a monolithic single file and lacks per-wave validation for its batch subagent execution. Splitting reference material and adding subagent-quality checks would lift the weaker dimensions.

Suggestions

Add a per-wave validation step: check each subagent's Findings/Gaps/Sources are non-empty and on-topic before marking its task completed, with a retry path for failed or thin responses.

Extract the reusable subagent prompt and report-markdown templates into a reference file (e.g. references/templates.md) and link to it, reducing inline bulk.

Trim the redundant intro framing that repeats the frontmatter's 'no external API' claim.

Dimension	Reasoning	Score
Conciseness	Mostly lean and free of basic-concept padding, but the intro line 'running entirely on Claude Code with no external dependencies' repeats the frontmatter's 'No external API needed' and a few passages could be tightened.	2 / 3
Actionability	Provides copy-paste-ready subagent prompts, exact file paths, an exact JSON source shape, an exact report markdown structure, and an exact filename format — fully executable guidance.	3 / 3
Workflow Clarity	Sequence, task-state checkpoints, and a gap-analysis feedback loop are clear, but this batch operation (parallel subagents) lacks per-wave verification of output quality or failed-subagent recovery, which the rubric caps at 2.	2 / 3
Progressive Disclosure	No bundle files exist and all content is inline in a ~130-line file over the 50-line simple-skill threshold; the large prompt and report templates could be split into one-level-deep references but are not.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 specific and non-vague, naming concrete techniques, but leans on implementation jargon and entirely omits a 'Use when…' trigger clause. Adding natural-language triggers would raise both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when…' clause with natural triggers (e.g., 'Use when the user asks to deep-dive a topic, investigate something thoroughly, or do deep research').

Soften jargon by pairing technical terms with plain phrasing users would actually say.

Reinforce distinctiveness by contrasting with a quick single-search (e.g., 'for multi-step research, not a quick lookup').

Dimension	Reasoning	Score
Specificity	Names three concrete techniques — 'DAG-based query planning, parallel subagent execution, and gap-driven iteration' — matching the multiple-specific-actions anchor rather than the domain-only score 2.	3 / 3
Completeness	States what the skill does but has no 'Use when…' trigger clause; the rubric caps completeness at 2 when explicit trigger guidance is missing.	2 / 3
Trigger Term Quality	'deep research' is a natural term, but 'DAG-based query planning', 'parallel subagent execution', and 'gap-driven iteration' are jargon and common variations like 'investigate' or 'deep dive' are absent.	2 / 3
Distinctiveness Conflict Risk	The 'deep research' niche is fairly distinct, but the broad term 'research' could overlap general web-search skills and no explicit triggers sharpen the boundary.	2 / 3
	Total	9 / 12 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: rohitg00/awesome-claude-code-toolkit
Path: skills/deep-dive/SKILL.md
Commit: ebdf1d5

Reviewed: 2 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.