CtrlK
BlogDocsLog inGet started
Tessl Logo

agents-sdk

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks.

83

1.26x
Quality

78%

Does it follow best practices?

Impact

95%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/opencode/test/fixture/skills/agents-sdk/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 efficient, actionable reference with good code examples and API tables, but it is undercut by missing bundle files: most referenced reference paths do not exist, and the workflow lacks explicit validation checkpoints.

Suggestions

Create the missing reference files referenced in the References section (workflows.md, state-scheduling.md, streaming-chat.md, mcp.md, email.md, codemode.md) or remove the dead links so navigation matches the bundle structure.

Add an explicit validation/verification step after agent creation (e.g. `npm ls agents` plus a wrangler dev smoke test with a curl check) to give the workflow a concrete checkpoint.

Trim the Capabilities section since its items duplicate the Documentation table and the description, reclaiming token budget.

DimensionReasoningScore

Conciseness

Mostly lean with tables and copy-paste code and a brief "STOP / prefer retrieval" warning, but the Capabilities section repeats items already in the docs table and description and could be trimmed; not verbose enough to drop to 3.

4 / 5

Actionability

Provides concrete executable TypeScript/TSX, install commands, and a Core APIs table with specific syntax for common cases, but some APIs are only named in tables without full runnable examples, leaving minor gaps below 5.

4 / 5

Workflow Clarity

A rough sequence exists (verify install → wrangler config → agent class → routing → client) with an implicit "Should show agents package" check, but there are no explicit validation checkpoints or feedback loops; this is not a destructive/batch skill so the 3-cap rule is not triggered, yet the gaps still fit anchor 3 better than 4.

3 / 5

Progressive Disclosure

Good high-level structure with a clearly signaled one-level-deep References section, but the actual bundle only contains references/callable.md while the body links to 7 reference files — 6 of 7 referenced paths are dead, so navigation is broken and organization is only partially effective.

3 / 5

Total

14

/

20

Passed

Description

92%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 clearly states what the skill does and gives concrete, natural trigger phrases. Trigger-term coverage is good but could add a few synonyms to be fully comprehensive.

DimensionReasoningScore

Specificity

Lists multiple specific concrete capabilities — "stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications" plus "Agent class, state management, callable RPC, Workflows integration, and React hooks" — giving comprehensive coverage; no neighboring anchor fits better since actions are concrete and numerous.

5 / 5

Completeness

Explicitly answers both what ("Build AI agents on Cloudflare Workers using the Agents SDK") and when ("Load when creating..." with concrete trigger phrases), matching the anchor 5 example.

5 / 5

Trigger Term Quality

"Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications" provides good natural keyword coverage a user would say, but lacks synonyms/variations (e.g. "cron", "durable objects") that would lift it to 5.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche ("Cloudflare Workers using the Agents SDK") with distinct triggers, minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 missing

Warning

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

14

/

16

Passed

Repository
elastic/elastic-ramen
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.