CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

81%

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

The canonical home for this skill is actions in BuilderIO/agent-native

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.

A highly actionable, well-structured reference for the framework's action system with excellent code examples and clearly signaled, real reference files. Its main weakness is token efficiency: at 239 lines it repeats several rules and inlines detail that belongs in references, pushing conciseness to the midpoint.

Suggestions

State the 'return structured data, never JSON.stringify()' rule once in Return Values and reference it from the code comment and Troubleshooting entry instead of repeating it three times.

Merge the two near-duplicate Do bullets about fail() vs bare Error into a single bullet covering errorCode/statusCode/details and the retry-status guidance.

Move the write-receipts and failed-write classification detail (or the save-conflict section) into references/action-fields.md, keeping only the decision rules and one compact example inline.

DimensionReasoningScore

Conciseness

The body is dense with genuinely framework-specific rules and pads nothing Claude already knows, but it could be tightened noticeably: the 'return structured data, not JSON.stringify()' rule appears three times (code comment, Return Values, Troubleshooting), two near-duplicate Do bullets cover fail() vs bare Error, and the default-export rule is repeated in Troubleshooting.

3 / 5

Actionability

Every major surface has copy-paste-ready code or commands with exact imports, function names, and flags: a complete defineAction example, useActionQuery/useActionMutation/callAction usage, a WriteReceipt snippet, and 'pnpm action log-meal --name "Salad" --calories 350'. It matches the fully-executable anchor covering the common cases.

5 / 5

Workflow Clarity

An explicit decision order ('existing action → extend/create a defineAction → custom route as last resort') with a stop trigger, plus a testing checkpoint (checkActionProperties) and a symptom→fix Troubleshooting section give a clear sequence. Not 5 because validation/testing is presented as a standalone paragraph rather than woven into a stepwise create-validate-fix flow.

4 / 5

Progressive Disclosure

All three cited references (action-fields.md, provider-apis.md, examples.md) exist, are one level deep, are linked inline at point of use, and are summarized with one-line descriptions in a References section. Not 5 because long deep-dive material (write receipts, failed-write classification, save conflicts) is inlined at full length in SKILL.md rather than split into the reference layer.

4 / 5

Total

16

/

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 description that clearly and explicitly states both what the skill does and when to use it, with concrete natural-language triggers. The only soft spots are minor overlap risk with adjacent integration/frontend skills and the absence of synonym trigger terms.

DimensionReasoningScore

Specificity

'How to create and run agent actions... the agent calls them as tools and frontend code calls them through client hooks' lists several concrete capabilities with mechanisms. Not 5 because 'the single source of truth for app operations' is abstract and the description omits much of the skill's concrete surface (conflict handling, receipts, testing).

4 / 5

Completeness

It explicitly answers both: what ('How to create and run agent actions... single source of truth... agent calls them as tools... through client hooks') and when ('Use when creating a new action, adding an API integration, or wiring up frontend data fetching') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'creating a new action', 'adding an API integration', and 'wiring up frontend data fetching' are phrases a developer would naturally say. Not 5 because there are no synonyms or variations such as 'calling an action', 'updating an action', or 'API route'.

4 / 5

Distinctiveness Conflict Risk

'Agent actions' carves a clear niche with distinct tool/hook mechanics. Not 5 because 'adding an API integration' and 'wiring up frontend data fetching' risk firing for closely related skills (provider integrations, client-methods) named in the skill's own Related Skills section.

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.

Validation — 13 / 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

Path

community-templates/account-expert/.agents/skills/actions/SKILL.md

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.