Os Graph Report

• Source: Built by Jonathan Kvarfordt. Standalone bundle v0.2.
• Frameworks applied: Core, install first

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

1. 1.Copy the SKILL.md text below, or download the raw file.
2. 2.Create a folder named exactly os-graph-report in your agent's skills directory.
3. 3.Save the file inside that folder as SKILL.md.
4. 4.Ask the agent one of the trigger requests below.
5. 5.Check the output against what you already know before it leaves your desk.

• how is the OS doing
• graph report
• is this actually learning

---
name: os-graph-report
description: Reports harness health and learning over time from the workspace's own signals log and evolve records: evaluator pass rate, override rate, signal freshness, records with doubt filled, proposals approved, plus week-one baseline versus now. Use when the user says "how is the OS doing", "graph report", "is this actually learning", "baseline vs now", or when the user needs an evidence-based progress review.
---

# os-graph-report

Compute from the log. Never estimate. If the log is thin, say so and report what exists.

## Preflight (every run)
1. Confirm `GTM-AI-OS/` is accessible. If not: "I need access to your GTM-AI-OS folder. Select it in Cowork's folder picker, or run `os-install` from the core plugin." Stop until it is.
2. Read `CLAUDE.md`, `INDEX.md`, `context/fence.md`, and the last 20 lines of `signals/log.md`.
3. Check the prerequisites below. For anything missing, ask the cold-start questions and offer: (a) run the earlier skill now, or (b) fast path: answer the questions and this skill writes a minimal version of the missing artifact marked `status: draft (fast path)`.
4. Before any connector write or external send, check `context/fence.md` for the account's bucket and the action. Auto = proceed. Approve = ask. Never = decline and name the row.
5. On finish, update the artifact row in `INDEX.md` (with `[[wikilinks]]` to the files this run read) and append one line to `signals/log.md`: `<date> | <skill> | <files read> | <produced> | <human changed> | <open question>`.

## Metrics
| Metric | Source | Healthy |
|---|---|---|
| Evaluator first-round pass rate | evaluator lines in `signals/log.md` | Rising toward 80% |
| Human override rate on approved sends | approval lines | Falling; never zero |
| Drafts refused on insufficient evidence | refusal lines | Present (the gate works) |
| Median age of cited signals | account records | Under 30 days |
| Records with contradicting evidence and doubt filled | account records | 100% |
| Signals tested against losses before entering the library | `signal-library.md` | 100% |
| Proposals approved per week | `evolve/` | 2 to 5 |
| Fence: Approve → Auto changes | `context/fence.md` history | Only with the thresholds met |
| Dead nodes, duplicates, broken links | `INDEX.md` wikilinks | Zero |

## Output
`evolve/REPORT-<date>.md`: the table, week-one baseline vs now for each metric, three sentences on what changed and why, and the one thing to fix first. This report is the user's evidence of progress.

What does the Os Graph Report skill do?

Reports harness health and learning over time from the workspace's own signals log and evolve records: evaluator pass rate, override rate, signal freshness, records with doubt filled, proposals approved, plus week-one baseline versus now.

Where does the Os Graph Report skill come from?

Built by Jonathan Kvarfordt. Standalone bundle v0.2.. The source and included files are shown on this page and in the package download.

Why was the Os Graph Report skill chosen for this library?

It covers a job one of the eight revenue seats has to finish, and it states its process, decision rules, and output format clearly enough for an agent to follow.

When should the Os Graph Report skill not be used?

Use it only for the job named above. A skill applied outside its scope produces confident output on the wrong question.

How do I install the Os Graph Report SKILL.md file?

Download the file, create a folder named exactly os-graph-report inside your agent's skills directory, and save the file inside it as SKILL.md. The agent loads it when a request matches the description.