CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oracle-advisor

Request a second-model consultation with explicit API, browser, or render transport and per-run provenance. Use when transport choice or model/effort evidence is part of the request; the existing oracle skill remains the browser-first workflow.

Quality

82%

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

81%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 well-structured, actionable, and sequences a multi-step consultation workflow with explicit validation and feedback loops. It is concise for its scope, with only minor tightening opportunities and no bundle files to organize.

DimensionReasoningScore

Conciseness

The body is directive and free of basic-concept padding (no 'what an API is' explanations), but the evidence/provenance caveat section contains justificatory prose ('A configured API model is a requested/effective route, not independent proof...') that could be trimmed, fitting 'efficient; minor instances of over-explanation' rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Copy-paste-ready oracle commands cover the API, browser, and render cases with concrete flags (--engine, --dry-run full, --files-report, --followup), but the MCP path is only described ('consult with explicit engine, model...') rather than shown as an example, fitting 'mostly executable guidance; concrete commands with minor gaps'.

4 / 5

Workflow Clarity

A clear select-transport -> run-consultation -> return-evidence sequence carries explicit validation checkpoints and feedback loops: 'preview the exact bundle with --dry-run full', 'inspect its existing session before retrying; do not create a duplicate consultation', and 'Verify the advice against the repository and tests before acting on it', matching the anchor for clear sequence with explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

A single self-contained file is organized into well-signaled sections with no nested or buried references, and no bundle files exist to split further; the dense evidence/provenance block in the final section is slightly long for inline placement, fitting 'good structure; most content appropriately placed; minor organization gaps' rather than a 5.

4 / 5

Total

17

/

20

Passed

Description

76%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 clearly states what the skill does and when to use it, with concrete transport modes and an explicit trigger clause. Its main weakness is trigger-term naturalness: the language is technical and misses common user phrasings.

Suggestions

Add natural-language trigger synonyms a user would actually say, e.g. 'second opinion', 'ask another model', or 'cross-check with a different model', alongside the technical terms.

Soften jargon like 'per-run provenance' and 'model/effort evidence' with a plainer phrasing (e.g. 'records which model and effort level were actually used') without losing precision.

Tighten the transport list so the distinctiveness from the browser-first oracle skill is even clearer, e.g. name when API or render is preferred over the default browser route.

DimensionReasoningScore

Specificity

Names the domain ('second-model consultation') plus several concrete transport actions ('API, browser, or render transport') and per-run provenance, matching 'lists several specific actions; minor gaps' rather than the comprehensive multi-action coverage of a 5.

4 / 5

Completeness

Explicit 'what' ('Request a second-model consultation with explicit API, browser, or render transport and per-run provenance') and an explicit 'Use when...' clause with concrete triggers ('transport choice or model/effort evidence is part of the request') match the anchor for clearly answering both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Relevant keywords appear ('consultation', 'model', 'API', 'browser', 'transport choice') but the phrasing is jargon-leaning ('provenance', 'model/effort evidence') and misses natural synonyms a user would say such as 'second opinion' or 'ask another model', fitting 'some relevant keywords but missing common variations' rather than the fuller coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

It carves a distinct niche and explicitly separates from the sibling ('the existing oracle skill remains the browser-first workflow'), but the consultation domain inherently overlaps that closely related oracle skill, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5.

4 / 5

Total

16

/

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

steipete/oracle

Path

skills/oracle-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.