CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scout

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/scout/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 an extremely lean environment-adapter shim that delegates cleanly to an authoritative playbook, and it is perfectly concise. However, the skill's actual content is entirely absent from the bundle, its referenced paths cannot be resolved within the skill, and nothing in SKILL.md itself explains the evaluation workflow.

Suggestions

Inline a brief overview of the scout workflow (coverage check → relevance assessment → save/skip recommendation) in SKILL.md so the skill is not wholly dependent on unresolvable external paths.

Bundle the playbook content into the skill's own references/ directory (e.g., references/playbook.md) and update the paths, keeping references one level deep.

State the precedence between the playbook and `.agents/rules/cog.md` explicitly, and add a fallback for when a referenced file is missing.

DimensionReasoningScore

Conciseness

The ~7-line body is pure instruction with zero padding and no explanation of concepts Claude already knows — every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

It gives concrete file paths and a concrete mechanism ("invoke `.agents/agents/<name>.md` via `invoke_subagent`"), but the actual evaluation steps live entirely in `.claude/skills/scout/SKILL.md`, which is not part of this bundle, so the guidance is incomplete rather than fully executable.

3 / 5

Workflow Clarity

The delegation sequence is clear (read the playbook → execute it → follow cog.md) with an explicit conditional substitution rule; minor gaps remain, such as no handling if referenced files are missing and the precedence between the playbook and cog.md being implicit.

4 / 5

Progressive Disclosure

All substantive content is externalized to references that do not exist in the skill's bundle (no references/ or scripts/ files), and the chain runs two levels deep (this file → playbook → agent workers), matching the minimal-structure "actual instructions are elsewhere" pattern.

2 / 5

Total

14

/

20

Passed

Description

55%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 states concrete capabilities in third person with a clear "what", but omits any "when to use" trigger guidance and lacks natural synonym terms users would say. It is serviceable but sits mid-scale on completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user shares a link/URL or tool to evaluate, or asks whether to save it to the vault."

Include natural synonyms users would actually say — "links", "bookmarks", "resources" — to improve trigger term coverage.

Clarify the tool-evaluation scope (e.g., "check if a tool is already covered in the vault") so the fourth capability is as concrete as the other three.

DimensionReasoningScore

Specificity

Names the domain ("URLs and tools") and lists three concrete actions — "check vault coverage, assess relevance, recommend save or skip" — fitting the several-specific-actions anchor; not a 5 because coverage is not comprehensive and what evaluating tools concretely involves is left open.

4 / 5

Completeness

The "what" is clear (evaluate, check coverage, assess relevance, recommend), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Keywords like "URLs", "tools", "vault", and "save or skip" are relevant, but common user variations such as "links", "bookmarks", or "resources" are missing, matching the some-relevant-keywords anchor rather than good coverage.

3 / 5

Distinctiveness Conflict Risk

"Vault coverage" and "save or skip" signal a niche PKM/curation context, but "Evaluate URLs and tools" is broad enough to overlap with research, bookmarking, or web-search skills, matching the somewhat-specific anchor.

3 / 5

Total

13

/

20

Passed

Validation

100%

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

huytieu/COG-second-brain

Path

.agents/skills/scout/SKILL.md

Revision

144c7a3

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill