CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paseo-advisor

Spin up a single agent as an advisor — second opinion on the current task. Use when the user says "advisor", "second opinion", "what does X think", or wants an outside take without delegating the work itself.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-crafted instruction-orchestration skill: concrete, correctly sequenced, and genuinely lean, with verbatim prompt blocks and explicit gates and fallbacks. The residual gaps are minor — a couple of redundant forwarded-skill examples, directive-only briefing bullets, and no recovery path when an advisor's response falls short.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence ("Single agent. Reads the situation you're in. Gives a judgment."), but the forwarded-skills section lists five near-duplicate examples where three would do, and "The advisor — not you — runs the skill; you're still just the orchestrator" restates the section opener. These are minor trimmable instances, matching the efficient-with-minor-over-explanation anchor.

4 / 5

Actionability

Guidance is concrete for an instruction-only skill: named calls (`list_profiles`, `create_agent` via paseo), a title convention (`[Advisor] <topic>`), and two verbatim copy-paste blocks (no-edits suffix, forwarding instruction). It falls short of fully executable because the briefing bullets are directives ("The question, sharply.") and agent-creation mechanics are deferred to the external paseo skill.

4 / 5

Workflow Clarity

Sections run in true execution order (prerequisites → pick → materialize → brief → launch → synthesize) with an explicit gate ("Do not create the advisor until you have read the configured profiles") and a fallback ("If no profile fits, use Paseo's provider discovery fallback"). It misses the top anchor because there is no error-recovery loop for a poor advisor response and no explicit checklist.

4 / 5

Progressive Disclosure

No bundle files exist, and none are needed: this single-purpose skill keeps everything appropriately inline behind clear section headers, with the profile/agent details cleanly delegated one level deep to the clearly-signaled paseo skill ("Read the **paseo** skill", "as described by the **paseo** skill"). Navigation is easy and nothing that belongs in a separate file is inlined.

5 / 5

Total

17

/

20

Passed

Description

90%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.

A strong description that pairs a clear single-action statement of what the skill does with an explicit 'Use when' clause quoting the exact phrases a user would say. The only relative weakness is specificity, which is capped by the skill's inherently single-action nature rather than by vague wording.

DimensionReasoningScore

Specificity

"Spin up a single agent as an advisor" names the domain plus one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is above a 2 because the action is specific rather than generic, and below a 4 because no several-action list is present.

3 / 5

Completeness

It explicitly answers both parts: "Spin up a single agent as an advisor — second opinion on the current task" (what) and "Use when the user says 'advisor', 'second opinion', 'what does X think'..." (when) with concrete trigger phrases. This is a direct match to the top anchor's example pattern.

5 / 5

Trigger Term Quality

The description quotes exact natural user phrases — "advisor", "second opinion", "what does X think", "outside take" — covering the synonyms users would naturally say for this need. Nothing relevant to the domain is missing, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

The advisor/second-opinion niche is distinct, and "without delegating the work itself" explicitly disambiguates from general delegation or agent-spawning skills. Trigger terms are unlikely to fire the wrong skill, matching the minimal-conflict anchor.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

getpaseo/paseo

Path

skills/paseo-advisor/SKILL.md

Reviewed

Table of Contents

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.