agentleFS
Sign inStart free
ShurikenTradeShurikenTrade/shuriken-skills/skills/api-integration/SKILL.md

api-integration

Skill90 starsChanged 7 months agoMITView on GitHub

Use when a user wants to integrate with or develop against the Shuriken API or SDK — covers proficiency assessment, path routing (quickstart / raw API / SDK), and tells you which deepening reference tool to reach for (OpenAPI for HTTP endpoints, the stream catalog for WebSockets, platform docs as fallback).

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use data-analysis and code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • shanggqmSkill

    data-analysis

    数据分析技能，提供结构化的数据查询、统计分析和报告生成工作流。当用户需要查询数据库、进行数据统计分析、生成分析报告时使用。按规范输出原始数据、计算结果、Markdown报告和HTML可视化报告。

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before pointing the user at code, establish two things:

    line 12
  2. Very specific:

    Every integration needs an agent key.

    line 38
  3. Distinctive:

    Do not preload the entire API reference into the conversation.

    line 42
  4. Distinctive:

    Never guess an endpoint or stream name from memory — the API evolves.

    line 48
  5. Distinctive:

    Before writing code, confirm:

    line 60

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Integrating and building with Shuriken

This skill covers the full "I want to call Shuriken programmatically" surface. It is intentionally thin up front — use the deepening tools below rather than pasting long code into the session.

Phase 1 — orient before writing anything

Before pointing the user at code, establish two things:

1. Technical proficiency

  • Absolute beginner. New to programming, or scripting at the level of "I can run a CLI if someone tells me exactly what to type." Needs hand-holding, copy-pasteable examples, environment setup spelled out.
  • Intermediate / power user. Comfortable with a terminal, editing configs, running scripts. Will follow a README but gets stuck on non-obvious toolchain setup.
  • Software engineer. Fluent in at least one language, reads types and API surfaces, skims READMEs and dives into code. Wants reference material, not prose.

Calibrate vocabulary and level of detail to this. If ambiguous, ask one clarifying question before firing off a long answer.

2. Integration path

Three ways to call Shuriken. Help the user pick.

Rough default: quickstart for beginners/intermediates, SDK for software engineers, raw HTTP only when they've said why.

3. Agent key

Every integration needs an agent key. See shuriken:agent-keys for lifecycle and shuriken:scoping for least-privilege scope selection. Point the user at app.shuriken.trade/agents to create one.

Phase 2 — deepen only when the question demands it

Do not preload the entire API reference into the conversation. Pull deeper references only when the user's next question needs them:

  • HTTP endpoint questions ("what fields does /v1/foo return", "is there an endpoint for X", schema/signature questions) → call fetch_shuriken_openapi. This returns the live OpenAPI spec — the source of truth for HTTP endpoints.
  • WebSocket / streaming questions ("what streams exist", "how do I subscribe to X", "what filters does this channel take") → call fetch_shuriken_streams. This returns the live v1 stream catalog with channel names, required filters, and payload formats.
  • Anything not answered by the two above (guides, conceptual overviews of how a feature works, SDK-specific how-tos) → fall back to fetch_shuriken_docs and read the relevant page under llms.txt.

Never guess an endpoint or stream name from memory — the API evolves.

Best practices

  • Use agent keys, not raw session tokens. See shuriken:agent-keys.
  • Request only the scopes you need. See shuriken:scoping.
  • Honour rate limits. Back off on 429; the response headers tell you the retry window.
  • Don't poll when you can subscribe. For live data, use the streams over repeated REST polls. Consult the stream catalog first.
  • Branch on structured error codes, not message text. The API returns machine-readable error codes — see the OpenAPI spec for the taxonomy.

When to ask clarifying questions

Before writing code, confirm:

  • Technical proficiency level (see above).
  • Which chain(s) the user is integrating against (Solana, EVM L1s, Base, BSC, Monad — support matrix varies).
  • Deployment shape (one-off script, long-running service, serverless function).
  • Integration path (quickstart / SDK / raw).

Pointers

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free