inno-deep-research

Comprehensive research assistant that synthesizes information from multiple sources with citations. Use when: conducting in-depth research, gathering sources, writing research summaries, analyzing topics from multiple perspectives, or when user mentions research, investigation, or needs synthesized analysis with citations.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/inno-deep-research/SKILL.md

Quality

Content

50%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 offers a clear, actionable research process and output template, but is notably verbose: it re-explains concepts Claude already knows and inlines an oversized worked example. Workflow sequencing is good but lacks explicit validation checkpoints, and everything lives in one file.

Suggestions

Trim or remove the generic process explanations ('Consider multiple perspectives', 'Identify patterns and themes') that Claude already knows, keeping only the structural guidance.

Move the full intermittent-fasting worked example into a separate EXAMPLES.md reference file and link to it from the body, reducing inline token load.

Add explicit validation checkpoints to the research process, e.g. 'Before synthesizing, confirm at least 3 independent sources cover each key finding'.

Dimension	Reasoning	Score
Conciseness	The body restates general knowledge Claude already has ('Consider multiple perspectives', 'Identify patterns and themes', 'Note areas of consensus and disagreement') and inlines a very long fully-written worked example that is demonstration rather than guidance, adding substantial padding.	2 / 5
Actionability	Provides concrete, specific structural guidance — numbered citation format, a fixed output section template, and a tiered source-credibility rubric — giving Claude an executable structure to follow, with only minor gaps.	4 / 5
Workflow Clarity	A clear five-step research process is sequenced (Clarify, Identify, Gather, Synthesize, Document), but it lacks explicit validation checkpoints such as confirming sufficient source coverage before synthesizing.	3 / 5
Progressive Disclosure	No bundle files exist and the SKILL.md is a single monolithic document; section headers are clear, but the lengthy full worked example is inlined content that could live in a separate examples file.	3 / 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-constructed: it clearly states the skill's purpose and gives an explicit, multi-condition 'Use when' trigger clause with natural keywords. Specificity and distinctiveness are strong but not maximal due to somewhat generic verbs and broad trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain plus several concrete actions ('synthesizes information from multiple sources', 'gathering sources', 'writing research summaries', 'analyzing topics from multiple perspectives'), but the verbs are somewhat generic rather than sharply distinct.	4 / 5
Completeness	Explicitly states what the skill does ('synthesizes information from multiple sources with citations') and provides a concrete 'Use when:' clause with multiple trigger phrases, answering both what and when.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('in-depth research', 'investigation', 'research summaries', 'synthesized analysis with citations'); coverage is good though some common phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The multi-source synthesis-with-citations niche is mostly distinct, but 'research' and 'investigation' are broad triggers that could overlap with other research-oriented skills.	4 / 5
	Total	17 / 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: OpenLAIR/dr-claw
Path: skills/inno-deep-research/SKILL.md
Commit: 4b35756

Reviewed: 5 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.