build-llm-seam SKILL.md skillA
build-llm-seam from velimirmueller/lab-claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add velimirmueller/lab-claude-skills/build-llm-seam@git:20261009.d042141Pins git:20261009.d042141 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- velimirmueller/lab-claude-skills
- Path
skills/ai/build-llm-seam/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261009.d042141, committed Oct 9, 2026
- First version recorded
- Oct 9, 2026
- Size
- 7,131 bytes
- Repository stars
- 5
- License
- MIT
Use when adding the first LLM call to a service, or when model calls are scattered through it — one module owns every call - model tiers from config, retries, validated structured output, streaming, prompt caching, OTel gen_ai spans with cost, versioned prompt files, PII redaction.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Build the LLM Seam Every model call in the codebase goes through one module. Call sites say *what* they want (a task, a tier, a prompt name, a schema); the seam decides *how*: which model, how long to wait, when to retry, what to log, what to redact. A vendor swap, a model upgrade or a cost cap is then a one-file change. Provider default: `ai.provider` in the profile (`anthropic`). ## 1. Audit current state Read `.claude/stack-profile.md` (`languages`, `backend.track`, `ai.provider`, `observability.otel`, `tests`). If absent, detect from lockfiles and manifests per [stack-profile.md](../../core/_shared/stack-profile.md). Then change nothing and look: ```bash grep -rnE "from ['\"](@anthropic-ai/sdk|openai|@google/genai)|^(import|from) (anthropic|openai)" src | grep -v "platform/llm" # SDK use outside the seam grep -rnE "claude-(opus|sonnet|haiku|fable)-|gpt-[0-9]|gemini-[0-9]" src | grep -v "platform/llm" # hard-coded model ids grep -rnE "max_tokens|maxTokens|temperature" src | grep -v "platform/llm" # per-call knobs ls src/platform/llm prompts config/llm.models.json 2>/dev/null …
Read the whole file at its exact version.
How to install
mdr add velimirmueller/lab-claude-skills/build-llm-seam@sha256:949e345cdbae932eThe line at the top of this page pins the label git:20261009.d042141, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cfdakquqqdjew6is)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 9, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.d042141 latest | 2026-10-09 | d042141 | 7,131 B | A | view · diff |
| git:20261009.b6d037a | 2026-10-09 | b6d037a | 7,134 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7131 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
velimirmueller/lab-claude-skills · 5 stars · license MIT · pushed 2026-10-12 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cfdakquqqdjew6is GET https://markdownregistry.com/api/v1/resolve?ref=velimirmueller/lab-claude-skills/build-llm-seam GET https://markdownregistry.com/api/v1/blob/949e345cdbae932e6e8788820ee4eaaeea75fd031ea534b766b37b93df9e399a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from velimirmueller/lab-claude-skills
Every file in velimirmueller/lab-claude-skills