# mentor ## a skill that reads your local session history and writes report on how you actually work.

Agents now do the work juniors used to. But juniors became seniors by getting feedback from seniors. Give agents to juniors and retire the seniors, and that feedback loop disappears. This skill is that loop, packaged as an agent skill you install once and run every week.


## What the skill does

- **Reads your local session history.** Claude Code transcripts under `~/.claude` and Codex rollouts under `~/.codex`. Nothing is uploaded; the skill runs entirely on your machine. - **Aggregates many sessions** into headline numbers (messages, sessions, tool calls, edits, files touched, tokens) plus per-day activity, tool mix, and languages. - **Writes one self-contained `report.html`** with eight sections, inline SVG icons, count-up numbers, and an animated chart. No dependencies and no build step, so any browser opens it.

| Section | What it gives you | |---|---| | What you work on | Your sessions clustered into themes, with rough share | | How you use the agent | Tool ratios, languages, model tiering, checkpoints | | What you did well | Real wins, handed back | | Where things go wrong | Friction points, each with evidence and a concrete fix | | Features worth trying | Capabilities you under-use | | Suggested CLAUDE.md additions | Copy-paste lines that kill a recurring friction | | New ways to use it | Better workflows for your patterns | | On the horizon | Where your workflow is heading |

The friction section is the point of the skill: every friction names a repeatable fix, a CLAUDE.md line, a hook, or a habit, so the same mistake stops showing up next week.

## Install the skill

Recommended, via [skills.sh](https://skills.sh), the open marketplace for agent skills. One command installs the skill into any supported agent:

```bash npx skills add smixs/mentor ```

Useful flags:

```bash # glo