CtrlK
BlogDocsLog inGet started
Tessl Logo

rill-analysis

Overview of how to analyze data in a Rill project

52

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 content is a well-structured, actionable agent playbook with concrete tool sequencing, chart-selection guidance, data-accuracy guardrails, and a defined output format. Its main weakness is mild redundancy of the reflection guidance across several sections.

Suggestions

Consolidate the reflection guidance that currently appears in Phase 2, the Analysis guidelines, and the standalone "Reflection between queries" section into one place to remove redundancy.

Add one concrete example of a query_metrics_view call with representative arguments so the tool-use guidance is copy-paste ready.

Tighten the duplicated Phase 1/Phase 2 framing across "## Process" and "## Analysis guidelines" by merging guidelines into the corresponding phase steps.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude's competence, and avoids explaining concepts Claude already knows; the only minor trim opportunity is that reflection guidance is restated across the Phase 2 OODA loop, the Analysis guidelines, and its own section, fitting the score-4 anchor of efficient with minor instances that could be tightened.

4 / 5

Actionability

It names specific tools (list_metrics_views, get_metrics_view, query_metrics_view, create_chart), maps data shapes to concrete chart types, sets a 4-6 query minimum and a 10000-row budget, and gives an exact output format, matching the score-4 anchor of mostly executable guidance with minor gaps (no example query payloads/arguments).

4 / 5

Workflow Clarity

The three phases are clearly sequenced with an OODA feedback loop in Phase 2 and an adapt-on-failure checkpoint in Phase 1, fitting the score-4 anchor of a clear sequence with most checkpoints present; it stops short of score 5 because the checkpoints are reflective rather than hard validation gates.

4 / 5

Progressive Disclosure

The single-file skill is well-organized with clear section headers (Role, Process, Analysis guidelines, Guardrails, Output format) and no nested references, matching the score-4 anchor of good structure with minor organization gaps such as the duplicated reflection guidance; it is not a 5 because the redundant sections could be consolidated.

4 / 5

Total

16

/

20

Passed

Description

40%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 is short and identifies a clear niche (Rill), but it states a topic rather than concrete capabilities and omits any "Use when..." trigger guidance. It reads more like a section header than a skill description.

Suggestions

Replace the topic-style phrasing with concrete actions, e.g. "Explores Rill metrics views, runs analytical queries, and generates charts to surface business insights from a Rill project."

Add an explicit trigger clause: "Use when the user wants to analyze data, explore metrics, or build dashboards in a Rill project."

Include natural synonyms users might say (e.g. "Rill dashboard", "Rill metrics", "explore Rill data") to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("analyze data in a Rill project") but the only action phrased is "Overview of how to analyze data", which is a topic statement rather than a concrete action, matching the score-2 anchor of naming a domain with minimal/generic actions.

2 / 5

Completeness

It offers only a vague "what" ("Overview of how to analyze data") and no "when"/Use-when clause at all, matching the score-2 anchor of a vague what with no when; the missing trigger guidance also caps completeness at 3 per guidelines, and this falls below that.

2 / 5

Trigger Term Quality

"analyze data" and "Rill project" are relevant natural keywords, but coverage is thin with no synonyms or variations a user might say, fitting the score-3 anchor of some relevant keywords missing common variations.

3 / 5

Distinctiveness Conflict Risk

"Rill project" carves out a clear niche (a specific BI tool) with minimal conflict risk against unrelated skills, fitting the score-4 anchor of mostly distinct with only minor overlap risk with closely related data-analysis skills.

4 / 5

Total

11

/

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
rilldata/agent-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.