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

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A dense, highly actionable router skill with concrete tool invocations, explicit validation gates, and clean one-level reference splitting. Its one notable weakness is conciseness: parallelism/sequencing rules are restated across several emphasized sections and could be consolidated.

Suggestions

Merge the overlapping dispatch-sequencing guidance in 'Default Agy Fan-Out', 'HARD GATE', 'Parallel Execution Rules', and 'Parallel only when axes differ' into a single canonical sequencing section to remove redundancy.

Reduce repeated emphasis markers (⚠/🟢/⛔) and inline restatements of the ≤1-agy rule; state each constraint once at its canonical location.

Confirm gotchas.md exists at the skill root alongside references/, since it is referenced as 'gotchas.md' rather than under references/.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and never explains known concepts, but dispatch-sequencing guidance is spread redundantly across 'Default Agy Fan-Out', 'HARD GATE', 'Parallel Execution Rules', and 'Parallel only when axes differ', and heavy ⚠/🟢/⛔ emphasis markers could be consolidated — so it could be tightened.

2 / 3

Actionability

It gives concrete, copy-paste-ready invocations — 'agy-agent --model pro --grounded "<question>"', 'exa → get_code_context_exa', 'mcp__plugin_agentmemory_agentmemory__memory_smart_search({ query: ..., limit: 5 })' — and a signal→tool table mapping each case to a specific primary and escalation tool.

3 / 3

Workflow Clarity

The flow (Bootstrap → Mode → Depth Calibration → Detection → dispatch → Synthesis → Follow-Up) is sequenced with explicit validation gates (the HARD GATE requiring primary output to be read before OMO dispatch, the Max Mode cost guard), an error-recovery feedback loop (partial-failure synthesis naming failed lanes), and a persist-insight checklist.

3 / 3

Progressive Disclosure

SKILL.md acts as a router overview with well-signaled, one-level-deep references — 'See references/max-mode.md for...', plus synthesis-rules.md, prompt-templates.md, and type-a-notes.md — and all four referenced files exist in references/, with detail appropriately split out rather than inlined.

3 / 3

Total

11

/

12

Passed

Description

92%

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, third-person description with explicit 'Use when' triggers, concrete named tools, and a clear action (orchestration/synthesis). Its main weakness is trigger-term breadth: 'research/investigate/look up/understand something' is generic and could overlap with sibling research skills.

Suggestions

Narrow the trigger terms toward research-orchestration specifics (e.g. 'multi-source research', 'cross-repo investigation', 'compare libraries/versions') so it is less likely to fire for simple lookups that other skills handle.

Consider signaling the routing/orchestration nature in the trigger clause (e.g. 'Use when a question spans multiple sources or needs tool/agent selection') to sharpen distinctiveness.

DimensionReasoningScore

Specificity

The description enumerates concrete, specific components — 'orchestrates MCP servers (perplexity/exa/deepwiki/context7), agy-agent, and OMO agents (explore/librarian/oracle/multimodal-looker)' plus the concrete action 'parallel multi-lane synthesis' — rather than vague language.

3 / 3

Completeness

It explicitly answers both 'what' (orchestrates the named MCP servers/agents with Max Mode synthesis) and 'when' via an explicit 'Use when...' trigger clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

'Use when the user asks to research, investigate, look up, or understand something' provides good coverage of natural phrases a user would actually say, matching the high-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The named toolset pins a clear research-orchestration niche, but the trigger verbs 'research, investigate, look up, or understand something' are generic enough to overlap with other research or explanation skills, so it is not clearly conflict-free.

2 / 3

Total

11

/

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.