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

84%

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

82%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.

An actionable, well-organized reference: executable code and exact commands cover the common cases, validation and error-recovery loops are built in, and detail is progressively disclosed to three well-signaled reference files. The main costs are mild redundancy in the Do/Don't section and a main file that carries more fine-grained detail than an overview ideally would.

DimensionReasoningScore

Conciseness

The body is dense with framework-specific rules Claude cannot know (save-conflict semantics, write receipts, failed-write classification) and explains no general concepts, but the two overlapping fail() bullets in Do/Don't and triple statement of the no-JSON.stringify rule across the example, Return Values, and Troubleshooting could be trimmed.

4 / 5

Actionability

Every common case has copy-paste-ready material: a complete defineAction example with imports and schema, useActionQuery/useActionMutation/callAction snippets, the `pnpm action log-meal` command, and named helpers with exact module paths (saveIfCurrent, nextFreeName, checkActionProperties).

5 / 5

Workflow Clarity

A clear decision order (existing action → defineAction → custom route as last resort), a stop trigger for /api/ routes, validation via checkActionProperties/outputSchema, and feedback loops (conflict retry on details.current, honest-reconciliation retry, Troubleshooting section) are all present; the creation sequence is however spread across sections rather than given as one explicit ordered flow with checkpoints.

4 / 5

Progressive Disclosure

Three real, one-level-deep reference files are clearly signaled both inline and in a dedicated References section with one-line purposes, and the headers aid navigation; the main file is nonetheless a dense 239-line rulebook whose deeper detail (receipt supersession rules, MCP keyToolNames configuration) could largely live in references.

4 / 5

Total

17

/

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: it states what actions are, how both the agent and frontend consume them, and gives an explicit 'Use when' clause with three natural trigger phrases. It falls just short of the top anchors on specificity and trigger coverage, and its broader triggers carry minor conflict risk with adjacent skills.

DimensionReasoningScore

Specificity

"How to create and run agent actions" plus "the agent calls them as tools and frontend code calls them through client hooks" names the domain, two concrete operations, and both calling surfaces, but coverage of the action lifecycle (updating, testing, deleting) is incomplete.

4 / 5

Completeness

The "what" is explicit ("single source of truth for app operations", called as tools by the agent and via client hooks by the frontend) and the "when" is an explicit 'Use when' clause with three concrete triggers, matching the top anchor.

5 / 5

Trigger Term Quality

"creating a new action", "adding an API integration", and "wiring up frontend data fetching" are phrases a user would naturally say, matching the good-example register; common synonyms like "endpoint", "API route", or "REST" are missing.

4 / 5

Distinctiveness Conflict Risk

The agent-actions niche is distinct with framework-specific triggers, but "adding an API integration" and "frontend data fetching" are broad enough to overlap with general API-integration or data-fetching skills.

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

.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.