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

71

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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-structured router skill body with tight, actionable, table-driven guidance and explicit validation checkpoints for parallel dispatch. The main defect is a dangling reference: 'gotchas.md' is named in three places but is not present in the bundle.

Suggestions

Add the missing 'gotchas.md' file to the bundle, or remove/replace its three references (bootstrap step 4, Dependencies, Gotches section) with a pointer to an existing file such as ../x-shared/common-gotchas.md.

Tighten the repeated ≤1-agy-lane and fan-out rule prose — the default-agy-fan-out block and the HARD GATE both restate overlapping sequencing constraints and could be consolidated.

Confirm the ../x-shared/* and ../x-omo/SKILL.md cross-skill references resolve in the deployed plugin, since the routing table depends on them being loadable at bootstrap.

DimensionReasoningScore

Conciseness

Dense, table-driven, imperative prose that assumes Claude's intelligence and avoids explanatory padding ('x-research is a router. It classifies ... and synthesizes'), though the 159-line body repeats some gate/fan-out rules that could be tightened.

4 / 5

Actionability

Provides concrete, executable invocation forms ('agy-agent --model pro --grounded', 'gitnexus → query', 'mcp__basic-memory__search_notes(...)') and a signal→tool routing table, with only minor gaps where detail is deferred to linked skills.

4 / 5

Workflow Clarity

Sequenced bootstrap, depth calibration, explicit validation checkpoints (read primary before dispatching OMO via the HARD GATE, MANDATORY cost guard before Max dispatch, wait-for-terminal-state before synthesis), and a partial-failure recovery path — clear feedback loops for batch/parallel dispatch.

5 / 5

Progressive Disclosure

SKILL.md is an overview with well-signaled one-level-deep references into references/*.md (all four present), but 'gotchas.md' is referenced in bootstrap step 4, Dependencies, and the Gotchas section yet is absent from the bundle — a dangling reference that breaks navigation.

3 / 5

Total

16

/

20

Passed

Description

95%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, concrete description with explicit 'Use when' trigger phrasing and specific named tooling. It clearly answers both what the skill does and when to use it, with low conflict risk; the only minor gap is that the headline action is a single 'orchestrates' verb rather than an enumerated list of distinct actions.

DimensionReasoningScore

Specificity

Names concrete tooling axes — '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' — multiple specific capabilities with only minor coverage gaps (the headline verb is a single 'orchestrates' rather than a list of distinct user-facing actions).

4 / 5

Completeness

Explicitly answers both: what it does ('orchestrates MCP servers ... agy-agent ... OMO agents ... Max Mode for parallel multi-lane synthesis') and when to use it ('Use when the user asks to research, investigate, look up, or understand something').

5 / 5

Trigger Term Quality

'Use when the user asks to research, investigate, look up, or understand something' gives comprehensive natural trigger coverage with multiple synonyms a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche as a research-orchestration router with named, specific tooling and distinct 'research/investigate/look up/understand' triggers — minimal overlap risk with unrelated skills.

5 / 5

Total

19

/

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.

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.