Agent skill

Observability LLM Obs

Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration.

Install Observability LLM Obs

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .claude/skills/observability-llm-obs && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .claude/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .agents/skills/observability-llm-obs && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .agents/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .cursor/skills/observability-llm-obs && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .cursor/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/aspectrr/deer.git --path deer-cli/internal/skill/defaults/observability-llm-obs

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .gemini/skills/observability-llm-obs && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .gemini/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .github/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .github/skills/observability-llm-obs && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .github/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aspectrr/deer --skill observability-llm-obs -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install aspectrr/deer observability-llm-obs --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aspectrr/deer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/deer-cli/internal/skill/defaults/observability-llm-obs .opencode/skills/observability-llm-obs && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "observability-llm-obs" agent skill from https://github.com/aspectrr/deer/tree/main/deer-cli/internal/skill/defaults/observability-llm-obs into .opencode/skills/observability-llm-obs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "observability-llm-obs", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: observability-llm-obs
GitHub stars: 405
Token cost: ~858 tokens
SKILL.md length: 160 words
Files: 1
Skills in repo: 14
Repo updated: Apr 21, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration.

The user asks about LLM monitoring
SKILL.md covers Where to look, Data available, Use cases and query patterns and Workflow, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
GenAI observability

What it does

Observability LLM Obs is an agent skill from aspectrr/deer. Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration. Use when the user asks about LLM monitoring, GenAI observability, or AI cost/quality.

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Observability, LLM cost and token optimization and LLM observability. It works with OpenTelemetry. The repository describes itself as: 🦌 The AI Elasticsearch Engineer. The licence is MIT.

When your agent uses it

The user asks about LLM monitoring
GenAI observability
AI cost/quality

Example prompts

“/observability-llm-obs”

What it can do on your machine

Read from SKILL.md and the folder at commit e4f9845. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are esql).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Observability LLM Obs loads about 858 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 160 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~52
When it runs · the whole SKILL.md, loaded when a task matches: ~858

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aspectrr/deer at commit e4f9845, republished under its MIT licence (© aspectrr). 160 words, ~858 tokens.

Download SKILL.mdSave it as .claude/skills/observability-llm-obs/SKILL.md (or your agent's skills folder).

name: observability-llm-obs
description: Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration. Use when the user asks about LLM monitoring, GenAI observability, or AI cost/quality.
metadata.author: elastic
metadata.version: 0.1.0
metadata.source: elastic/agent-skills//skills/observability/llm-obs

LLM and Agentic Observability

Monitor LLMs and agentic components using data ingested into Elastic. Focus on performance, cost/token utilization, response quality, and call chaining.

Where to look

Trace data (APM / OTel): traces* for LLM spans from OTel/EDOT instrumentations
Integration metrics/logs: metrics* and logs* from Elastic LLM integrations (OpenAI, Azure, Bedrock, Vertex AI)
Discover first: Use GET _data_stream or GET traces*/_mapping to find available data

Data available

From traces (traces*)

Purpose	Example attribute names (OTel GenAI)
Operation / provider	`gen_ai.operation.name`, `gen_ai.provider.name`
Model	`gen_ai.request.model`, `gen_ai.response.model`
Token usage	`gen_ai.usage.input_tokens`, `gen_ai.usage.output_tokens`
Errors	`error.type`

Use duration and event.outcome for latency and success/failure. Use trace.id and parent/child relationships for call chaining analysis.

Use cases and query patterns

LLM performance

esql

FROM traces*
| WHERE @timestamp >= "2025-03-01T00:00:00Z" AND @timestamp <= "2025-03-01T23:59:59Z"
  AND span.attributes.gen_ai.provider.name IS NOT NULL
| STATS request_count = COUNT(*), failures = COUNT(*) WHERE event.outcome == "failure",
    avg_duration_us = AVG(span.duration.us)
  BY span.attributes.gen_ai.request.model
| EVAL error_rate = failures / request_count
| LIMIT 100

Token usage over time

esql

FROM traces*
| WHERE @timestamp >= "2025-03-01T00:00:00Z" AND @timestamp <= "2025-03-01T23:59:59Z"
  AND span.attributes.gen_ai.provider.name IS NOT NULL
| STATS input_tokens = SUM(span.attributes.gen_ai.usage.input_tokens),
    output_tokens = SUM(span.attributes.gen_ai.usage.output_tokens)
  BY BUCKET(@timestamp, 1 hour), span.attributes.gen_ai.request.model
| SORT @timestamp
| LIMIT 500

Agentic workflow (trace-level view)

esql

FROM traces*
| WHERE @timestamp >= "2025-03-01T00:00:00Z" AND @timestamp <= "2025-03-01T23:59:59Z"
  AND span.attributes.gen_ai.operation.name IS NOT NULL
| STATS span_count = COUNT(*), total_duration_us = SUM(span.duration.us) BY trace.id
| WHERE span_count > 1
| SORT total_duration_us DESC
| LIMIT 50

Workflow

text

- [ ] Step 1: Determine available data (traces*, metrics*, integration data streams)
- [ ] Step 2: Discover LLM-related field names (mapping or sample doc)
- [ ] Step 3: Run ES|QL queries for the user's question
- [ ] Step 4: Check active alerts/SLOs on LLM-related data
- [ ] Step 5: Summarize findings from ingested data only

Guidelines

Use only data collected in Elastic. Do not rely on external UIs.
Discover field names from _mapping or sample documents before querying.
Prefer ES|QL and Elasticsearch APIs over Kibana UI.
Use LIMIT and coarse time buckets for performance.

Files

Just SKILL.md in deer-cli/internal/skill/defaults/observability-llm-obs of aspectrr/deer.

Open the folder on GitHubat commit e4f9845

Compare with similar skills

Observability LLM Obs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Observability LLM Obs compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Observability LLM Obs this skillaspectrr/deer	405	—	~858	Automated safety check: Pass	MIT	5 mo ago
Caveman Gateway SetupJuliusBrussee/caveman	110k	1 repos	~2.6k	Automated safety check: Warn	Apache-2.0	today
Agent Kill Switchvivekchand/clawmetry	425	—	~1.1k	Automated safety check: Pass	MIT	today
Clawmetry Selfcheckvivekchand/clawmetry	425	—	~515	Automated safety check: Pass	MIT	today
Agent Platform Alert Configurationgoogle/skills	21k	—	~4.2k	Automated safety check: Pass	Apache-2.0	today
Clawmetryvivekchand/clawmetry	425	—	~992	Automated safety check: Pass	MIT	today

Similar skills

Caveman Gateway Setup
JuliusBrussee/caveman
Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.
110k GitHub starsUsed in 1 repo~2.6k tokens
DevOps & CloudAuto-check: warnings
Agent Kill Switch
vivekchand/clawmetry
Give the human an off switch and a cost meter for the coding agents on this machine, using ClawMetry.
425 GitHub stars~1.1k tokensUpdated today
DevOps & CloudAuto-check passed
Clawmetry Selfcheck
vivekchand/clawmetry
Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task.
425 GitHub stars~515 tokensUpdated today
DevOps & CloudAuto-check passed
Agent Platform Alert Configuration
google/skills
Official
Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.
21k GitHub stars~4.2k tokensUpdated today
DevOps & CloudAuto-check passed
Clawmetry
vivekchand/clawmetry
Real-time observability for OpenClaw agents — local dashboard + optional encrypted cloud sync.
425 GitHub stars~992 tokensUpdated today
DevOps & CloudAuto-check passed
Arize Phoenix
Arize-ai/phoenix
Open-source AI observability platform for tracing, evaluating, and improving LLM applications with OpenTelemetry integration
12k GitHub starsUsed in 1 repo~3.8k tokens
DevOps & CloudAuto-check passed

Questions about Observability LLM Obs

What does Observability LLM Obs do?

Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration. Observability LLM Obs is an agent skill from aspectrr/deer. Monitor LLMs and agentic apps: performance, token/cost, response quality, and workflow orchestration.

When should I use Observability LLM Obs?

Observability LLM Obs fits situations like: the user asks about LLM monitoring; genAI observability; AI cost/quality.

How do I install Observability LLM Obs in Claude Code?

Run `npx skills add aspectrr/deer --skill observability-llm-obs -a claude-code`. Or copy the skill folder (deer-cli/internal/skill/defaults/observability-llm-obs in aspectrr/deer) into .claude/skills/observability-llm-obs in your project. Claude Code loads it when a task matches its description.

How do I install Observability LLM Obs in Codex?

Run `npx skills add aspectrr/deer --skill observability-llm-obs -a codex`. Or copy the skill folder (deer-cli/internal/skill/defaults/observability-llm-obs in aspectrr/deer) into .agents/skills/observability-llm-obs in your project. Codex loads it when a task matches its description.

Can I use Observability LLM Obs in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aspectrr/deer --skill observability-llm-obs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/observability-llm-obs, .gemini/skills/observability-llm-obs, .github/skills/observability-llm-obs and .opencode/skills/observability-llm-obs in your project.

What does Observability LLM Obs need to run?

SKILL.md names no scripts, command-line tools or credentials: Observability LLM Obs is instructions for the agent only.

Does Observability LLM Obs access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Observability LLM Obs safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Observability LLM Obs use?

Observability LLM Obs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Observability LLM Obs use?

About 858 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Observability LLM Obs?

Skills that share tags, products or a category with Observability LLM Obs: Caveman Gateway Setup (JuliusBrussee/caveman, 110k stars), Agent Kill Switch (vivekchand/clawmetry, 425 stars), Clawmetry Selfcheck (vivekchand/clawmetry, 425 stars) and Agent Platform Alert Configuration (google/skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Observability LLM Obs?

aspectrr (a GitHub user) maintains it in aspectrr/deer, which has 405 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on April 21, 2026.

Source: aspectrr/deer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Observability LLM Obs

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

LLM and Agentic Observability

Where to look

Data available

From traces (traces*)

Use cases and query patterns

LLM performance

Token usage over time

Agentic workflow (trace-level view)

Workflow

Guidelines

Files

Compare with similar skills

Similar skills

More from aspectrr/deer

Related

Questions about Observability LLM Obs