validate-genai-spans SKILL.md skillA
validate-genai-spans from contextjet-ai/awesome-llm-observability is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add contextjet-ai/awesome-llm-observability/validate-genai-spans@git:20261015.76d5de4Pins git:20261015.76d5de4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- contextjet-ai/awesome-llm-observability
- Path
skills/validate-genai-spans/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261015.76d5de4, committed Oct 15, 2026
- First version recorded
- Jul 5, 2026
- Size
- 2,600 bytes
- Repository stars
- 45
- License
- a license file GitHub does not identify
Use this to check that your LLM tracing actually emits complete, spec-compliant spans, so cost/latency/model dashboards downstream are not full of holes. Trigger on "are my traces complete", "validate my instrumentation", "my spans are missing fields", "lint my OTel GenAI spans", "test my tracing". Ships a runnable, tested validator you can drop into your instrumentation tests.
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
# Validate GenAI spans Broken instrumentation fails silently: the app works, the dashboards just quietly miss the model, the tokens, or the cost. This skill ships a validator that asserts your spans carry the required OpenTelemetry `gen_ai.*` fields, so you catch gaps in a test instead of in a half-empty dashboard. ## Use the bundled script [`scripts/validate_span.py`](scripts/validate_span.py) is pure Python, no install needed: ```python from validate_span import validate_gen_ai_span, is_valid_gen_ai_span problems = validate_gen_ai_span(span_attributes) # [] means valid validate_gen_ai_span(span_attributes, strict=True) # also flag recommended fields assert is_valid_gen_ai_span(span_attributes) # use in an instrumentation test ``` It checks the required fields (`gen_ai.provider.name`, `gen_ai.operation.name`, `gen_ai.request.model`) and, in strict mode, the recommended usage fields (`gen_ai.usage.input_tokens`/`output_tokens`, `gen_ai.response.model`) that cost analysis depends on. Spans still using the pre-2025 `gen_ai.system` name pass but get a deprecation note, so you can migrate at your own pace. ## How to apply it …
Read the whole file at its exact version.
How to install
mdr add contextjet-ai/awesome-llm-observability/validate-genai-spans@sha256:332c9381f8f090ceThe line at the top of this page pins the label git:20261015.76d5de4, 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_igooltnuib5fe6s4)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 5, 2026 and Oct 15, 2026, about one every 102 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.76d5de4 latest | 2026-10-15 | 76d5de4 | 2,600 B | A | view · diff |
| git:20260705.4a31848 | 2026-07-05 | 4a31848 | 2,433 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 (2600 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
contextjet-ai/awesome-llm-observability · 45 stars · license a license file GitHub does not identify · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_igooltnuib5fe6s4 GET https://markdownregistry.com/api/v1/resolve?ref=contextjet-ai/awesome-llm-observability/validate-genai-spans GET https://markdownregistry.com/api/v1/blob/332c9381f8f090ce142898f40d80882fb667c9ca3b77fad8bf6e33819327b43c
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.