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. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

74

Quality

92%

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 agents-sdk in cloudflare/skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable workflow skill with clear sequencing and verification across build, eval, and deploy paths. Its only weakness is mild redundancy between the Build and Deploy sections that could be consolidated.

Suggestions

Consolidate the repeated PORT / `uv run python main.py` / `/health` guidance so it appears once, then have the Deploy checklist reference the Build section rather than restating it.

Extract the deployable-signal checklist (Deploy step 1) into a single shared "deployable app" definition referenced by both Build and Deploy to remove the duplicated signal list.

Tighten the Done Criteria and Deploy verification blocks so each observable check is stated once across the skill.

DimensionReasoningScore

Conciseness

The body is directive-dense and avoids explaining concepts Claude already knows, but the PORT / `uv run python main.py` / `/health` guidance and the deployable-signal checklist are repeated across the Build and Deploy sections and could be tightened.

2 / 3

Actionability

It provides concrete, executable guidance throughout — `make -C "$MANAGER_DIR" deploy PROJECT_PATH=…`, `uv run python main.py`, `curl -fsS …/health`, file-layout trees, `@function_tool`, and `Runner.run` — copy-paste ready commands.

3 / 3

Workflow Clarity

Build (7 steps) and Deploy (5 steps) are clearly numbered, with explicit verification checkpoints (Deploy "Verify the result", Build smoke step, eval "exit non-zero on failures") and a Done Criteria checklist for recovery.

3 / 3

Progressive Disclosure

Content is organized into clearly labeled sections with a one-level-deep References block pointing to official docs URLs; no bundle files exist and there is no deep nesting or monolithic wall of text.

3 / 3

Total

11

/

12

Passed

Description

100%

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, specific description that states concrete capabilities and provides an explicit, well-scoped "Use when" trigger covering the skill's main entry points. It uses third-person/trigger voice and avoids vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "Build, run, deploy, and evaluate", plus "create or adapt… build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally" — rather than vague language.

3 / 3

Completeness

It explicitly states what the skill does ("Build, run, deploy, and evaluate OpenAI Agents SDK apps from Codex") and when to use it via an explicit "Use when…" trigger clause, satisfying both what and when.

3 / 3

Trigger Term Quality

The "Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally" clause covers natural terms the target audience would actually say.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche around the OpenAI Agents SDK, Codex threads, eval harnesses, and the Deployment Manager, with triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
openai/plugins
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.