CtrlK
BlogDocsLog inGet started
Tessl Logo

x-research

Use when the user asks to research, investigate, look up, or understand something — orchestrates MCP servers (perplexity/exa/deepwiki/context7), agy-agent, and OMO agents (explore/librarian/oracle/multimodal-looker) with optional Max Mode for parallel multi-lane synthesis

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

The body is a well-structured, workflow-clear router skill with strong sequencing and validation gates, but it leans verbose and offers prose-heavy rather than copy-paste actionable guidance. The missing gotchas.md reference slightly weakens progressive disclosure.

Suggestions

Add the missing gotchas.md bundle file (referenced in the Bootstrap step 4 and the Gotchas section) or drop the dead references so navigation is intact.

Consolidate the dense parenthetical constraint blocks (C3 graceful degradation, hard-gate exemptions, default-agy-fan-out) — the repeated rationale across these sections is the main verbosity source.

Inline at least one concrete executable invocation example (e.g. a real `agy-agent`/`omo-agent` command) so the routing rows move from prose to copy-paste-ready guidance.

DimensionReasoningScore

Conciseness

Mostly efficient routing tables, but dense parenthetical asides (e.g. the C3/graceful-degradation, hard-gate, and default-agy-fan-out blocks) restate surrounding constraints repeatedly and could be tightened; some redundancy with linked x-shared files.

2 / 3

Actionability

Concrete tool/agent names and invocation forms are present, but most guidance is prose and table rows rather than executable commands; code blocks are limited to a Max Mode prompt template, and template references live in linked files.

2 / 3

Workflow Clarity

Clear sequencing: mandatory bootstrap, depth calibration, signal-to-tool detection table, hard-gate ordering rule, parallel-execution terminal-state wait, and a synthesis/persistence checklist with explicit validation and error-handling checkpoints.

3 / 3

Progressive Disclosure

References are mostly one-level deep and clearly signaled (references/max-mode.md, synthesis-rules.md, prompt-templates.md, type-a-notes.md all exist), but gotchas.md is referenced in two places and is absent from the bundle, breaking navigation.

2 / 3

Total

9

/

12

Passed

Description

100%

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, trigger-rich, complete, and distinctive — it lists concrete tools and actions with an explicit 'Use when' clause. It is dense and somewhat jargon-heavy but scores well because the trigger terms and actions are concrete.

DimensionReasoningScore

Specificity

Names concrete actions ('orchestrates MCP servers', 'synthesizes findings') and enumerates specific servers and agents (perplexity/exa/deepwiki/context7, explore/librarian/oracle/multimodal-looker) with a concrete Max Mode behavior.

3 / 3

Completeness

Answers both 'what' (orchestrates research tools and synthesizes) and 'when' via an explicit 'Use when the user asks to research, investigate...' trigger clause.

3 / 3

Trigger Term Quality

Includes natural trigger phrasing users would say ('research, investigate, look up, or understand something') plus Max Mode trigger ('prism', '--max'), giving good coverage of common variants.

3 / 3

Distinctiveness Conflict Risk

The specific enumerated toolchain (MCP servers + agy-agent + OMO agents + Max Mode) carves a clear research-orchestrator niche unlikely to trigger for adjacent implementation skills.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
quangtran88/x-skills
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.