session-insights SKILL.md skillA
session-insights from luiseiman/dotforge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add luiseiman/dotforge/session-insights@git:20261007.217cdf3Pins git:20261007.217cdf3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- luiseiman/dotforge
- Path
skills/session-insights/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261007.217cdf3, committed Oct 7, 2026
- First version recorded
- Mar 20, 2026
- Size
- 5,907 bytes
- Repository stars
- 8
- License
- MIT
Per-project insights from dotforge data — CLAUDE_ERRORS.md, session-report metrics, agent memory, registry score trend — fed into the practices pipeline. General friction analysis across transcripts is native (/insights).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Session Insights
Analyze the current project's Claude Code usage patterns and generate actionable recommendations.
**Scope (native-first boundary, v4.7.0)**: Claude Code's `/insights` already analyzes up to 200 recent sessions across every project on the machine from transcripts (misunderstood requests, buggy code, auto-mode recommendation) → `~/.claude/usage-data/report.html`. This skill does NOT read transcripts and does not duplicate that. It covers only what native has no access to: `CLAUDE_ERRORS.md` by Area/Type, `session-report.sh` hook metrics, `.claude/agent-memory/`, the registry score trend, and the automatic feed into `practices/inbox/`. Start by pointing the user to `/insights` for the cross-project friction picture.
## Step 1: Gather session data
Collect data from available sources in the current project:
1. **Session metrics** — `~/.claude/metrics/{project-slug}/*.json` (structured JSON from session-report hook)
2. **CLAUDE_ERRORS.md** — error frequency by Area and Type
3. **Git log** — files most frequently modified in commits mentioning "fix", "bug", "error"
4. **.claude/agent-memory/** — learnings accumulated by agents
…Read the whole file at its exact version.
How to install
mdr add luiseiman/dotforge/session-insights@sha256:460872d1162ffbdcThe line at the top of this page pins the label git:20261007.217cdf3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_zml6vr2b4vqvovhc)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 20, 2026 and Oct 7, 2026, about one every 50 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261007.217cdf3 latest | 2026-10-07 | 217cdf3 | 5,907 B | A | view · diff |
| git:20261007.6815eee | 2026-10-07 | 6815eee | 5,901 B | A | view · diff |
| git:20260405.f2216fd | 2026-04-05 | f2216fd | 5,115 B | A | view · diff |
| git:20260320.cef3d93 | 2026-03-20 | cef3d93 | 5,119 B | A | view · diff |
| git:20260320.94c3481 | 2026-03-20 | 94c3481 | 3,460 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5907 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
luiseiman/dotforge · 8 stars · license MIT · pushed 2026-10-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_zml6vr2b4vqvovhc GET https://markdownregistry.com/api/v1/resolve?ref=luiseiman/dotforge/session-insights GET https://markdownregistry.com/api/v1/blob/460872d1162ffbdc04d370500ec74bbf4a1213094b46a4883740900664f2a528
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.