scout

Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.

Quality

77%

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 ./src/skills/scout/SKILL.md

Quality

Content

70%

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

A well-structured scouting skill with a clear sequenced workflow, validation/exit checkpoints, and clean one-level-deep progressive disclosure. It is held back by redundant sections and guidance that mixes concrete tool calls with abstract directives.

Suggestions

Merge the "Validation" and "Exit criteria" sections and deduplicate the repeated over-searching/memory-reuse pitfalls to tighten the body.

Convert the abstract workflow directives (e.g., "Search only the unresolved neighborhood") into concrete first-actions tied to the named tools so guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural prose without concept explanations, but sections overlap ("Validation" vs "Exit criteria", repeated pitfalls about not over-searching and reusing memory) and could be tightened; not a 3 due to this redundancy, not a 1 because it avoids padding with things Claude already knows.	2 / 3
Actionability	Concrete tool calls are named ("memory.list_recent(...)", "artifact.arxiv(paper_id=..., full_text=False)", "bash_exec(...)") alongside a numbered workflow, but much of the guidance stays abstract ("Search only the unresolved neighborhood", "Make the evaluation contract... explicit"); incomplete enough to land at 2 rather than the copy-paste-ready 3.	2 / 3
Workflow Clarity	A clear 5-step "Control workflow" is paired with a "Preconditions and gate", a checklist-style "Validation"/"Exit criteria", and a "Blocked-state handling" feedback loop, matching the explicit-validation-and-recovery anchor; not a 2 because checkpoints are explicit, not implicit.	3 / 3
Progressive Disclosure	The body keeps the control surface inline and offloads longer notes to five one-level-deep references (paper-triage-playbook.md, literature-scout-template.md, eval-contract-template.md, baseline-shortlist-template.md, operational-guidance.md), all verified present in ./references/, with clear usage triggers; matches the well-signaled one-level-deep anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%

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, trigger-led description that covers what and when with a distinct pre-deeper-work niche. The main weakness is trigger-term naturalness: the keywords are domain jargon rather than phrases a user would commonly say.

Suggestions

Add more colloquial trigger phrases (e.g., "find related papers", "pick a baseline", "decide on a metric") alongside the jargon so the description matches natural user wording.

Separate the what and the when more clearly (e.g., lead with a short action clause, then "Use when...") so the capability and the trigger are not the same list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "problem framing, literature scouting, dataset or metric clarification, or baseline discovery" — matching the multiple-specific-actions anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	An explicit "Use when..." trigger states when to invoke it, and the enumerated actions state what it does, satisfying both halves; not a 2 because the when-clause is explicit rather than implied.	3 / 3
Trigger Term Quality	Keywords like "literature scouting", "baseline discovery", and "metric clarification" are relevant but specialized jargon tied to the "quest" framing, missing common user variations; not the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The "before deeper work" scoping carves a clear pre-execution framing niche with distinct triggers, unlikely to fire for the wrong skill; not a 2 since the niche is explicit rather than merely "somewhat specific".	3 / 3
	Total	11 / 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: ResearAI/DeepScientist
Path: src/skills/scout/SKILL.md
Commit: b366244

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.