26 instruction files for AI agents, collected from contextjet-ai/awesome-llm-observability. Install any of them at an exact version with mdr add contextjet-ai/awesome-llm-observability/<name>.
add-llm-evals SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/add-llm-evals/SKILL.md · Use this when adding evaluation to an LLM/agent app - measuring output quality (correctness, faithfulness, relevance…
git:20260705.23078be · audit A · 45 stars
add-llm-fallbacks SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/add-llm-fallbacks/SKILL.md · Use this to make an LLM app resilient to provider failures, rate limits, timeouts, and outages. Trigger on "handle LLM…
git:20260705.6b497b1 · audit A · 45 stars
add-llm-guardrails SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/add-llm-guardrails/SKILL.md · Use this to add safety and security guardrails to an LLM/agent app - blocking prompt injection, PII leakage…
git:20261015.76d5de4 · audit A · 45 stars
annotate-traces-for-review SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/annotate-traces-for-review/SKILL.md · Use this to set up human review and annotation of LLM traces, so people (often domain experts) can label outputs, do…
git:20260705.95f5cea · audit A · 45 stars
build-eval-dataset SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/build-eval-dataset/SKILL.md · Use this to build a good evaluation dataset for an LLM app, the part everyone underestimates. Trigger on "make an eval…
git:20260705.4a58130 · audit A · 45 stars
check-answer-consistency SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/check-answer-consistency/SKILL.md · Use this to get a cheap, reference-free signal that an LLM answer might be made up, by sampling the same prompt a few…
git:20260705.4a31848 · audit A · 45 stars
choose-observability-stack SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/choose-observability-stack/SKILL.md · Use this to recommend an LLM observability / evaluation tool or stack for a specific situation. Trigger on "which…
git:20261015.76d5de4 · audit A · 45 stars
collect-user-feedback SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/collect-user-feedback/SKILL.md · Use this to capture user feedback on LLM outputs (thumbs up/down, edits, corrections, implicit signals) and feed it…
git:20260705.6b497b1 · audit A · 45 stars
compare-llm-models SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/compare-llm-models/SKILL.md · Use this to pick or switch the LLM behind a feature, based on evidence instead of hype or the newest release. Trigger…
git:20260705.4a58130 · audit A · 45 stars
debug-agent-from-traces SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/debug-agent-from-traces/SKILL.md · Use this to diagnose WHY an LLM agent or chain produced a wrong, empty, slow, or expensive result, by reading its…
git:20260705.23078be · audit A · 45 stars
detect-hallucinations SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/detect-hallucinations/SKILL.md · Use this to detect when an LLM is making things up, so you can flag or block confident-but-wrong answers before users…
git:20260705.2cc0ac5 · audit A · 45 stars
estimate-llm-cost SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/estimate-llm-cost/SKILL.md · Use this to estimate what an LLM call or feature will cost, and to compare models on price, before or after shipping…
git:20261020.4f317d3 · audit A · 45 stars
eval-driven-development SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/eval-driven-development/SKILL.md · Use this to build or change an LLM feature the reliable way, by writing evals first and iterating against them, instead…
git:20260705.23078be · audit A · 45 stars
instrument-llm-observability SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/instrument-llm-observability/SKILL.md · Use this when adding tracing/observability to an LLM or AI-agent application - capturing prompts, tool calls, token…
git:20260705.23078be · audit A · 45 stars
measure-agent-task-success SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/measure-agent-task-success/SKILL.md · Use this to measure whether an AI agent actually completed its task end to end, not just whether individual LLM calls…
git:20260705.95f5cea · audit A · 45 stars
monitor-rag-quality SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/monitor-rag-quality/SKILL.md · Use this to measure and monitor the quality of a RAG (retrieval-augmented generation) pipeline - whether it retrieves…
git:20260705.23078be · audit A · 45 stars
optimize-prompts SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/optimize-prompts/SKILL.md · Use this to improve a prompt systematically instead of hand-tweaking it by feel. Trigger on "optimize my prompt", "make…
git:20260705.6b497b1 · audit A · 45 stars
red-team-llm-app SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/red-team-llm-app/SKILL.md · Use this to adversarially test an LLM/agent app before attackers do - prompt injection, jailbreaks, data exfiltration…
git:20260705.2cc0ac5 · audit B · 45 stars
redact-pii-for-tracing SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/redact-pii-for-tracing/SKILL.md · Use this when adding LLM observability to an app that handles sensitive data (finance, healthcare, PII) and you must…
git:20261015.76d5de4 · audit A · 45 stars
reduce-llm-cost SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/reduce-llm-cost/SKILL.md · Use this to cut the cost of an LLM app using observability data. Trigger on "my OpenAI/Anthropic bill is too high"…
git:20260705.23078be · audit A · 45 stars
scrub-pii-from-text SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/scrub-pii-from-text/SKILL.md · Use this to strip PII (emails, credit cards, SSNs, phone numbers, IPs, IBANs) out of text before it is logged to a…
git:20261015.76d5de4 · audit A · 45 stars
set-up-ab-testing SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/set-up-ab-testing/SKILL.md · Use this to test an LLM change (new prompt, new model, new retrieval) on real traffic before rolling it out to…
git:20260705.95f5cea · audit A · 45 stars
set-up-drift-alerts SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/set-up-drift-alerts/SKILL.md · Use this to catch an LLM app silently getting worse in production - quality dropping, cost creeping up, inputs shifting…
git:20261015.76d5de4 · audit A · 45 stars
trace-based-testing SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/trace-based-testing/SKILL.md · Use this to turn real production traces into a regression test suite, so bugs you saw once never come back. Trigger on…
git:20260705.4a58130 · audit A · 45 stars
trace-multi-agent-system SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/trace-multi-agent-system/SKILL.md · Use this to add observability to a multi-agent or agentic system (multiple agents, sub-agents, tool loops, handoffs)…
git:20260705.23078be · audit A · 45 stars
validate-genai-spans SKILL.md skill
contextjet-ai/awesome-llm-observability · skills/validate-genai-spans/SKILL.md · Use this to check that your LLM tracing actually emits complete, spec-compliant spans, so cost/latency/model dashboards…
git:20261015.76d5de4 · audit A · 45 stars