scout

Evaluate URLs and tools — check vault coverage, assess relevance, recommend save or skip

Quality

63%

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 ./.claude/skills/scout/SKILL.md

Quality

Content

61%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 skill body is a well-structured, actionable instruction-only skill with strong templates and a clear 7-step flow, but its batch-capable workflow lacks explicit validation checkpoints (capping workflow_clarity at 3) and some content is repeated or could be tightened. Progressive disclosure is good for a single file but would benefit from splitting out reusable templates.

Suggestions

Add explicit validation/verification checkpoints for batch mode (e.g., 'verify each fetched page title matches the URL domain before scoring relevance' and a retry loop when fetch fails) to lift workflow_clarity above the batch cap.

De-duplicate the save→/url-dump handoff — keep it once in the Process Flow and trim the repetition in 'Boundary with /url-dump' and 'Integration with Other Skills'.

Move the reusable prompt templates (coverage/save/skip outputs) and the fallback table into a referenced file (e.g. references/TEMPLATES.md) to push progressive_disclosure toward 5 and tighten the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient instructional content with no padding about concepts Claude already knows, but the 'Boundary with /url-dump' and 'Integration with Other Skills' sections restate the same save→url-dump handoff and the 'Philosophy' section restates principles already implied, which could be tightened; this keeps it below 4 rather than the verbose anchor of 2.	3 / 5
Actionability	Provides concrete, copy-paste-ready output templates ('✅ SAVE — [Title/Name]' with fields), a specific search strategy ('grep for domain, repo name, tool name'), and a fallback table mapping scenarios to behavior; not 5 because steps like relevance scoring lack a fully specified method and some 'extract: title, description...' guidance is given without execution detail.	4 / 5
Workflow Clarity	The 7-step Process Flow is clearly numbered with user-confirmation gates and a fallback table, but as a batch-capable skill (Batch mode, Batch Summary) it lacks explicit validation/verification checkpoints or validate→fix→retry loops, which the rubric caps at 3 for batch operations; not 2 because the sequence is well-defined rather than gappy.	3 / 5
Progressive Disclosure	The single-file body is well-organized with clear headers and no nested references, but at ~195 lines with no external bundle files or signaled one-level-deep references it does not meet the content-splitting bar of 5; not 3 because structure is good rather than 'content that should be separate is inline' in a problematic way.	4 / 5
	Total	14 / 20 Passed

Description

66%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 specific, actionable, and reasonably natural, but lacks an explicit 'when to use' clause, which caps its completeness at 3. It is otherwise a solid, well-scoped triage description with minor trigger-synonym gaps.

Suggestions

Add an explicit 'Use when...' trigger clause with concrete user phrases (e.g., 'Use when the user asks should I save this?, is this worth keeping?, or wants to evaluate a URL before saving') to raise completeness.

Include a few natural synonyms and variations users actually say ('worth bookmarking?', 'scout this link') to broaden trigger-term coverage toward 5.

Sharpen 'assess relevance' into a more concrete action (e.g., 'score relevance against the user's active projects and interests') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain (URLs and tools) and several concrete actions — 'check vault coverage, assess relevance, recommend save or skip' — with only minor coverage gaps, matching the 'lists several specific actions' anchor; not 5 because 'assess relevance' is somewhat generic and the action set is not comprehensive.	4 / 5
Completeness	The 'what' is clear (evaluate URLs/tools for vault triage) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; it is above 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('evaluate', 'save', 'skip', 'relevance') with good coverage, but misses common variations like 'should I save this?' or 'is this worth keeping?', so it sits below the comprehensive-synonym anchor of 5.	4 / 5
Distinctiveness Conflict Risk	The vault-triage-with-save/skip niche is mostly distinct and uses third-person voice, with only minor overlap risk against the closely related /url-dump skill that the body itself acknowledges, keeping it below the minimal-conflict anchor of 5.	4 / 5
	Total	15 / 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: huytieu/COG-second-brain
Path: .claude/skills/scout/SKILL.md
Commit: cb4644d

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.