Adding a new anchor

VerifiedSafe

Guide to add an anchor integration with client, API, routes, and pages. Decide between ANCHORS and HONORABLE_MENTIONS.

Sby Skills Guide Bot
DevelopmentAdvanced
7/28/2026
Claude Code
#sveltekit#integration#anchor#scaffolding#architecture

Recommended for

Automated summary

Walks through the full procedure for adding a new anchor (Stellar provider) to a SvelteKit project, from client and API routes to flow pages and docs.

Strengths

  • Breaks the integration into ten ordered, checkable steps
  • States the per-provider isolation rule and forbids sharing flow logic across anchors
  • Explains how to add an anchor to ANCHORS or demote it to HONORABLE_MENTIONS
  • Covers the special case of adding a missing SEP implementation

Limitations

  • Assumes prior familiarity with the project's architecture and conventions
  • Tightly coupled to this repository's file layout, not portable to other codebases
  • Does not spell out the expected contents of each file or the exact acceptance bar
When to use it

Use when integrating a new anchor provider into this SvelteKit project or deciding between ANCHORS and HONORABLE_MENTIONS.

When not to use it

Avoid it for researching a candidate that is still under evaluation, which belongs to the assessing-an-anchor skill, or for projects lacking this file structure.

Security analysis

Safe
Quality score80/100

This is a purely procedural contributor guide for extending a SvelteKit-style anchor project. It only describes creating files, wiring singletons that read env vars, and adding config entries; it contains no shell commands, network calls, credential handling, obfuscated payloads, or instructions to disable safety. Environment variables are only referenced (the singleton reads them), not printed or transmitted. Listing it carries no meaningful execution risk.

No concerns found

How this analysis is made

Examples

Add a new anchor end to end
Add the Acme anchor to the project: create its client, server singleton, API wrappers, proxy routes and flow pages, then register it in constants, ANCHORS and regions, with tests and a README.
Decide whether it clears the bar
I've been looking at a new anchor called StellarPay — help me decide whether it should go in ANCHORS or HONORABLE_MENTIONS, and add it with a scorecard if it doesn't clear the bar.
Add missing SEP support
This anchor needs SEP-31 which we don't implement yet — add src/lib/anchors/sep/sep31.ts modeled on the existing modules, wire up the types and exports, and cover it with tests.

name: adding-an-anchor description: Use when adding a new anchor integration to this project — creating an anchor client, its server singleton, API wrappers, proxy routes, and flow pages, or deciding whether a new anchor belongs in ANCHORS vs HONORABLE_MENTIONS.

Adding a new curated anchor

Each curated anchor owns its own client, server-side instance singleton, client-side API wrapper, API routes, and bespoke flow pages. Nothing is shared — see the per-provider isolation decision in CLAUDE.md.

  1. src/lib/anchors/<name>/{client,types,index}.ts — shaped however the anchor's API actually works. No interface to satisfy. Define your own error class. Include the debug?: boolean flag described in CLAUDE.md and cover both logging behaviors with tests.
  2. src/lib/server/<name>Instance.ts — singleton getter reading env vars, passing debug: dev from $app/environment.
  3. src/lib/api/<name>.ts — client-side fetch wrappers per route. Mirror the per-provider shape in etherfuse.ts / testanchor.ts.
  4. src/routes/api/anchor/<name>/<operation>/+server.ts — one route per operation.
  5. src/routes/anchors/<name>/+page.svelte (landing) and <name>/<flow>/+page.svelte per flow. Compose primitives from src/lib/components/. Use AnchorRegionSelector for the region section. Don't try to share flow logic with another anchor in this PR — let it duplicate.
  6. Add the provider to src/lib/constants.ts (PROVIDER).
  7. Add to src/lib/config/anchors.ts (ANCHORS).
  8. Add to src/lib/config/regions.ts if the anchor serves a region.
  9. Add tests under tests/anchors/<name>/.
  10. Document in src/lib/anchors/<name>/README.md.

If it doesn't clear the bar

Add it to HONORABLE_MENTIONS in src/lib/config/anchors.ts instead — no client code needed. Give it a scorecard (via makeCriteria) so its gaps render. For a candidate you're still researching rather than rejecting, use the assessing-an-anchor skill.

Adding SEP support

If the anchor needs a SEP this project doesn't implement yet: create src/lib/anchors/sep/sep<N>.ts modeled on the existing modules (pure functions, optional fetchFn), add types to sep/types.ts, export from sep/index.ts, and cover it under tests/anchors/sep/.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/adding-a-new-anchor-ms47vo7k' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/adding-a-new-anchor-ms47vo7k/download' --output '.skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md.part' && mv '.skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md.part' '.skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md' && test -s '.skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/adding-an-anchor' && cp -R '.skill-downloads/adding-a-new-anchor-ms47vo7k' '.claude/skills/adding-an-anchor'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/adding-a-new-anchor-ms47vo7k'

openskills read 'adding-a-new-anchor-ms47vo7k'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/adding-a-new-anchor-ms47vo7k/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills