CtrlK
BlogDocsLog inGet started
Tessl Logo

data-programs

Save a run-code fetch/join/aggregate script as a stored, refreshable data source any app's own charts/tables can render, instead of a hardcoded provider action or a per-view re-fetch. Use when an ad-hoc run-code or provider-api-request analysis should become a live, cached data source other users or panels can reuse.

67

Quality

80%

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 ./.agents/skills/data-programs/SKILL.md
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.

A well-structured, navigable body with an explicit validation loop in its workflow and clean section-based progressive disclosure. It loses points on actionability for describing rather than showing executable code, and on conciseness for the persuasive 'Why this exists' framing.

Suggestions

Add one short executable snippet showing `emit(rows, schema)` and a `save-data-program({...})` call so the workflow is copy-paste ready rather than prose-described.

Trim the 'Why this exists' motivation paragraph to one or two sentences; Claude can infer the value from the caching model that follows.

Consider moving the full caching/refresh table into a reference file if the skill grows, to keep SKILL.md an overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient and free of obvious padding, but the 'Why this exists' section spends several sentences arguing for the primitive's value and the caching table re-explains behavior that experienced readers can infer, so it could be tightened toward lean every-token-earns-its-place prose.

2 / 3

Actionability

The workflow names the actions and parameter shapes concretely, but the actual JS usage is prose-described rather than shown as executable, copy-paste code (e.g. an `emit(rows, schema)` or `save-data-program({...})` snippet), leaving it instructive but not fully executable.

2 / 3

Workflow Clarity

The authoring workflow is a clear five-step sequence with an explicit validation checkpoint: step 3 dry-runs the code with defaultParams and rejects the save on failure, and step 4/5 explain how to consume and iterate, giving an explicit feedback loop.

3 / 3

Progressive Disclosure

The content is organized into well-signaled one-level-deep sections (workflow, sandbox surface, caching, security, related skills) with no nested bundle references to chase; no bundle files exist and none are referenced, so the inline structure is appropriately self-contained.

3 / 3

Total

10

/

12

Passed

Description

90%

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 description with explicit what/when structure, good natural trigger terms, and a clearly distinctive niche. It is capped below top specificity because it describes the product concept rather than naming the concrete actions the skill registers.

Suggestions

Name the concrete registered actions (save-data-program, run-data-program, preview-data-program) in the description so users triggering by action name land here.

Consider shortening the 'instead of a hardcoded provider action or a per-view re-fetch' contrast to tighten the description while keeping the trigger terms.

DimensionReasoningScore

Specificity

It names concrete actions ("fetch/join/aggregate script", "stored, refreshable data source", "charts/tables can render") but speaks at a conceptual product level rather than enumerating the multiple specific primitive actions the skill actually exposes (save/preview/run/list/delete-data-program), so it is not the fully concrete list of a 3.

2 / 3

Completeness

It explicitly answers both halves: the "what" (save a fetch/join/aggregate script as a stored refreshable data source) and the "when" via an explicit "Use when an ad-hoc run-code or provider-api-request analysis should become a live, cached data source other users or panels can reuse."

3 / 3

Trigger Term Quality

It surfaces natural trigger phrases a user would say ("run-code", "provider-api-request analysis", "live, cached data source", "ad-hoc", "re-fetch"), giving good coverage of the terms that would lead Claude here.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and distinctive (persisting run-code output as a refreshable cached data source rather than a hardcoded action or per-view re-fetch), with triggers unlikely to fire for unrelated skills like `actions` or `security`.

3 / 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
BuilderIO/agent-native
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.