deep-research

Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation. Produces a cited research brief with provenance tracking.

Quality

72%

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/deep-research/SKILL.md

Quality

Content

66%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 body is extremely concise and well-structured for a delegating skill, but its actual workflow detail and validation checkpoints are hidden behind an unshown slash command, leaving actionability and workflow clarity incomplete on their own.

Suggestions

Add a brief numbered outline of the researcher->verifier->reviewer steps and how their outputs flow into the final brief so the workflow is legible without invoking the slash command.

Include an explicit validation/verification checkpoint (e.g., the verifier confirms citations resolve and provenance is recorded before writing the brief) to strengthen workflow_clarity for a citation-sensitive task.

Specify the brief's expected structure or required sections (e.g., summary, sources, provenance table) so the output contract is fully actionable.

Dimension	Reasoning	Score
Conciseness	Three lean statements assume Claude's competence and avoid re-explaining research concepts; the one explanatory clause about the slash command is justified anti-drift operational guidance, so every token earns its place per anchor 5.	5 / 5
Actionability	It gives a concrete delegating action ('Run the /deepresearch workflow'), names agents, and specifies the output contract, but the actual executable steps live behind a slash command not shown here, leaving key execution detail implicit per anchor 3.	3 / 5
Workflow Clarity	No sequenced steps are written in the body — only 'run the workflow' with an implicit researcher->verifier->reviewer->output roster; steps are poorly defined and validation checkpoints are absent, fitting anchor 2 better than anchor 3.	2 / 5
Progressive Disclosure	Under 50 lines with no external references needed, the body is well-organized into a single delegating instruction plus agent roster and output location, and the one-level-deep delegation to the slash command is clearly signaled, satisfying the simple-skill anchor 5.	5 / 5
	Total	15 / 20 Passed

Description

78%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 concise, third-person, and cleanly answers both what the skill does and when to use it with multiple natural trigger phrases. It is slightly limited in enumerating specific actions and has minor overlap risk with general research skills.

Dimension	Reasoning	Score
Specificity	Names the research domain and two concrete actions ('Run a thorough, source-heavy investigation', 'Produces a cited research brief with provenance tracking') but does not enumerate several specific actions, matching anchor 3 rather than the multi-action anchor 4.	3 / 5
Completeness	Explicitly answers both what ('Run a thorough... investigation', 'Produces a cited research brief with provenance tracking') and when ('Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes several natural phrases a user would say ('deep research', 'comprehensive analysis', 'in-depth report', 'multi-source investigation') with synonyms, but is missing a few common variations (e.g., 'literature review', specific output formats), so it lands at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (source-heavy multi-source investigation with provenance tracking) but carries minor overlap risk with a generic research/web-search skill, fitting anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	16 / 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: companion-inc/feynman
Path: skills/deep-research/SKILL.md
Commit: 95c51d9

Reviewed: about 10 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.