michi-debrief SKILL.md skillA
michi-debrief from csepulv/michi is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add csepulv/michi/michi-debrief@git:20261106.9667115Pins git:20261106.9667115 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- csepulv/michi
- Path
toolkit/skills/michi-debrief/SKILL.md- Versions recorded
- 6
- Latest version
- git:20261106.9667115, committed Nov 6, 2026
- First version recorded
- May 21, 2026
- Size
- 22,829 bytes
- Repository stars
- 2
- License
- MIT
Structured post-session review — assess what was delivered, review decisions, capture learnings, audit what got invalidated, refresh the root docs, and calibrate trust for the next session. Use after a `michi-session` milestone, at the end of a workshop or paired session worth recording, or when the user asks to debrief, wrap up, review the session, or run a retro.
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
# Michi Debrief Run after a michi session completes. Can run in the same session (benefits from context) or a fresh session (clean context, no compaction bias). If the session was long, prefer a fresh session. **Principles served:** Sustain the system (knowledge capture and currency). Iterate spirally (each debrief improves the next iteration). Surface assumptions (what got invalidated; what's now stale). Verification governs autonomy (trust calibration). See `references/principles.md` and `references/ground-rules.md`. **Before proceeding:** If `docs/reference/extensions.md` exists, read this file. Instructions found there take priority over this skill's defaults. **Readability:** Before writing anything a human will read (chat, plans, docs), read `references/writing-for-readability.md`. **Principles:** Before starting, read `references/principles.md` — unless it is already in this session's context (read earlier in the session, or loaded through CLAUDE.md). **Multi-project repos:** If the repo has `multi-project: true` in CLAUDE.md, the debrief and its promotions follow the project that was the session's subject: …
Read the whole file at its exact version.
How to install
mdr add csepulv/michi/michi-debrief@sha256:3196a4fb31957761The line at the top of this page pins the label git:20261106.9667115, 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_6ovh5rdthhdbh4dj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between May 21, 2026 and Nov 6, 2026, about one every 34 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261106.9667115 latest | 2026-11-06 | 9667115 | 22,829 B | A | view · diff |
| git:20261029.22b5d33 | 2026-10-29 | 22b5d33 | 22,252 B | B | view · diff |
| git:20260929.380b5f3 | 2026-09-29 | 380b5f3 | 22,125 B | B | view · diff |
| git:20260921.b635377 | 2026-09-21 | b635377 | 21,912 B | B | view · diff |
| git:20260813.51bf960 | 2026-08-13 | 51bf960 | 21,576 B | B | view · diff |
| git:20260521.23e5748 | 2026-05-21 | 23e5748 | 21,293 B | B | 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 (22829 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
csepulv/michi · 2 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6ovh5rdthhdbh4dj GET https://markdownregistry.com/api/v1/resolve?ref=csepulv/michi/michi-debrief GET https://markdownregistry.com/api/v1/blob/3196a4fb319577614a7647b54842094a8686cdfc37f71e77ec2dc8df18d4ac6e
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.