Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/microsoft/eval-guide/eval-result-interpreternpx skills add microsoft/eval-guide --skill eval-result-interpretergit clone --depth 1 https://github.com/microsoft/eval-guideWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.08510 |
| Opus 5 | $0.00032 | $0.04255 |
| Sonnet 5 | $0.00013 | $0.01702 |
| Haiku 4.5 | $0.00006 | $0.00851 |
Grade A, and why
eval-result-interpreter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
This skill takes eval results — a Copilot Studio evaluation CSV file, a pasted summary, or plain-English description of results — and produces a structured triage report. It is the standalone Interpret skill in the operational workflow: plan → generate → run → interpret. In the 10-step playbook, it reads the baseline (Step 6), drives diagnosis (Step 7), and designs the Step 9 optimization loop. The output tells you whether to ship, what broke, why it broke, and what to fix first.
This skill is grounded in Practical Guidance on Agent Evaluation: a 10-step playbook. It uses Step 6 to read baseline results with agent version and timestamp, Step 7 to classify failures into eval-setup vs agent-quality problems, and Step 9 to define the production feedback loop. MS Learn evaluation resources remain useful supporting references, but the 10-step playbook is the canonical methodology.
Knowledge source: This skill's analysis framework is grounded in the 10-step playbook plus Microsoft's Triage & Improvement Playbook diagnostics — SHIP/ITERATE/BLOCK gate interpretation, failure verification, remediation mapping, and pattern analysis.
When to use this skill vs. eval-triage-and-improvement
These two skills share the same triage framework but serve different modes of work:
| Use eval-result-interpreter when… | Use eval-triage-and-improvement when… |
|---|---|
| You have a CSV file or concrete results and want a one-shot structured report | You want interactive guidance walking through diagnosis step by step |
| This is your first look at results — you need a verdict and top actions fast | You are in an ongoing improvement loop — fixing, re-running, and re-triaging |
| You want a customer-deliverable artifact (the .docx triage report) | You need detailed remediation help for specific eval-set failures (e.g., "wrong tool fires — now what?") |
| The eval run is relatively straightforward (<20 failures) | You have many failures (15+) and need help prioritizing which to investigate |
| You need the activity map / result comparison tool recommendations inline | You need the playbook worked examples and deeper diagnostic walkthroughs |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 437 lines · 65 tokens per session scan A 1c953ef77141
eval-result-interpreter is a skill published in the GitHub repository microsoft/eval-guide (127 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 8,510 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…