CtrlK
BlogDocsLog inGet started
Tessl Logo

eve

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

70

Quality

85%

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

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.

An exemplary router skill body: concise, points to a version-matched source of truth, and cleanly defers detail to bundled docs and one reference file. Its only limitation is inherent to the router pattern — it offers navigation rather than executable eve examples, which slightly caps actionability.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it states the source of truth, the entry path (node_modules/eve/docs/README.md), and the install/scaffold fallback, with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

It gives concrete, executable commands (npm install eve, npx eve init <agent-name>) and a specific path to read, but the primary instruction ('read the bundled docs') is a pointer to external material rather than copy-paste-ready working code, leaving a small gap versus fully executable guidance.

4 / 5

Workflow Clarity

There is a clear sequence: read bundled docs first, install/scaffold if eve is missing, then read the relevant guide before writing code, plus a handoff boundary reference. It lacks an explicit validation/feedback checkpoint, but this routing skill does not perform destructive or batch operations, so the destructive-cap does not apply.

4 / 5

Progressive Disclosure

The body is an overview router that points one level deep to the bundled docs and to references/source-of-truth.md (a real file), with clearly signaled navigation and no inline bulk content that belongs elsewhere.

5 / 5

Total

18

/

20

Passed

Description

85%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, well-formed description that clearly states capability and trigger conditions with an enumerated scope list in third-person voice. Minor gains would come from richer verb variety and synonym coverage, but it does not over-claim or pad.

DimensionReasoningScore

Specificity

The description names the domain ('durable backend AI agents', 'eve framework') and lists a concrete enumerated set of artifacts ('agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals'), giving several specific actions (create/edit/debug), though the verbs are broad and the list is one cluster rather than multiple distinct concrete actions.

4 / 5

Completeness

It explicitly answers both 'what' ('Build durable backend AI agents with the eve framework') and 'when' ('Use when creating, editing, or debugging an eve project') with concrete trigger phrases and an enumerated scope list.

5 / 5

Trigger Term Quality

It includes natural trigger phrasing ('creating, editing, or debugging an eve project') plus domain keywords users would say (agents, skills, tools, subagents, schedules, evals), but it lacks synonyms or extension-style variations beyond 'eve'.

4 / 5

Distinctiveness Conflict Risk

The 'eve framework' niche is specific and the enumerated eve-specific artifact types give distinct triggers with minimal overlap risk against other skills.

5 / 5

Total

18

/

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
ComposioHQ/composio
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.