CtrlK
BlogDocsLog inGet started
Tessl Logo

actions

How to create and run agent actions. Actions are the single source of truth for app operations — the agent calls them as tools and frontend code calls them through client hooks. Use when creating a new action, adding an API integration, or wiring up frontend data fetching.

68

Quality

85%

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

86%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 high-quality, well-structured reference skill: executable code, a clear decision order with a stop-trigger checkpoint, and clean one-level-deep references to real bundle files. The only drag is a few over-long anecdotal passages that could be tightened for token efficiency.

Suggestions

Trim war-story asides (e.g. 'One production run spent 32% of its cost on three rejected writes...') to the concrete rule they illustrate, to lift conciseness toward the top anchor.

Tighten the multi-clause Do/Don't bullets (e.g. the fail() status-code item) by splitting each into a one-line rule plus a short rationale.

Add a brief validate/retry note for action results that mutate shared state (e.g. re-read after write) to give workflow_clarity an explicit feedback loop.

DimensionReasoningScore

Conciseness

Dense, expert-level prose with no padding about concepts Claude already knows, and copy-paste code blocks. It is not a 5 because a few passages run long, e.g. the 'One production run spent 32% of its cost...' anecdote and several heavily compounded sentences in the Do/Don't list could be trimmed.

4 / 5

Actionability

Multiple fully executable, copy-paste-ready blocks (defineAction, useActionQuery/useActionMutation, pnpm action command) plus exact concrete patterns like z.enum(['open','closed']).default('open').describe(...) cover the common cases. Not below 5 since guidance is concrete and executable throughout.

5 / 5

Workflow Clarity

A clear decision sequence ('existing action → extend/create a defineAction → custom route as last resort') with an explicit stop-trigger checkpoint before adding /api/ routes. It is not a 5 because there is no explicit validate→fix→retry feedback loop, though the skill is not primarily destructive/batch so the cap does not apply.

4 / 5

Progressive Disclosure

Clear sectioned overview with well-signaled one-level-deep references (references/provider-apis.md, references/action-fields.md, references/examples.md — all verified present) and detail like outputSchema/authorize/needsApproval correctly pushed to references. Not below 5 since structure, signaling, and split are all appropriate.

5 / 5

Total

18

/

20

Passed

Description

83%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, third-person description that answers both what and when with concrete, natural triggers. Minor gaps in action-lifecycle coverage and a small overlap with provider-API integration keep specificity and distinctiveness just below the top anchor.

DimensionReasoningScore

Specificity

Names the domain ('agent actions') and several concrete operations — 'create and run', 'adding an API integration', 'wiring up frontend data fetching' — with minor gaps (no update/delete). It is not a 5 because coverage of the action lifecycle is not fully comprehensive.

4 / 5

Completeness

It explicitly states what ('How to create and run agent actions... the agent calls them as tools and frontend code calls them through client hooks') and when ('Use when creating a new action, adding an API integration, or wiring up frontend data fetching') with concrete triggers. Not below 5 since both are clearly and explicitly present.

5 / 5

Trigger Term Quality

The 'Use when creating a new action, adding an API integration, or wiring up frontend data fetching' clause uses natural phrases a developer would say. It is not a 5 because it lacks synonym variation and a couple of common alternate phrasings.

4 / 5

Distinctiveness Conflict Risk

'Agent actions' as the single source of truth for app operations is a distinct niche. It is not a 5 because 'adding an API integration' overlaps with the related provider-apis concern, creating minor conflict risk.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

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.