diagnose-session SKILL.md skillA

diagnose-session from escoffier-labs/skillet is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add escoffier-labs/skillet/diagnose-session@v0.1.0

Pins v0.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
escoffier-labs/skillet
Path
skillet/skills/diagnose-session/SKILL.md
Versions recorded
1
Latest version
v0.1.0, committed Oct 20, 2026
Size
5,472 bytes
Repository stars
4
License
MIT

Use only when the user asks why an agent run went wrong and wants evidence from the transcripts - "why did that take so long", "why was it so expensive", "it ignored the plan", "it kept redoing X", "that skill never fired", "what was it doing". Runs only when the user asks. Not for debugging product code (use refire).

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

# diagnose-session

When a dish goes wrong, the chef pulls the ticket and the line log and reconstructs what actually happened before blaming anyone. This skill does that for an agent run: it reads the transcripts and reports what happened, with a citation for every claim.

**Core principle:** every finding cites `path:line`; every number comes from the transcript or a command you ran, never from memory. No citation, no finding.

Unlike a pure reporting tool, this skill may diagnose skillet skills themselves. Keep the evidence and the interpretation separate: first what the transcript shows, then, labelled as diagnosis, what that suggests about the skill or the setup.

## Procedure

Make a todo per step.

1. **Intake before analysis.** Ask one question at a time until you can write a problem statement: the session(s), the turn range if known, what the user expected, what happened, and the observable they care about (wall-clock, tokens, repeated actions, one specific action). "It took too long" is a complaint, not a statement. Nothing below starts until the user has answered. If they are away, write the questions and stop; do not reconstruct a statement for them. A request that…
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add escoffier-labs/skillet/diagnose-session@sha256:4e8851f94904fe2d

The line at the top of this page pins the label v0.1.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rwhhllqg3zoszho6.svg)](https://markdownregistry.com/a/art_rwhhllqg3zoszho6)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 20, 2026.

versioncommittedcommitsizeaudit
v0.1.0 latest2026-10-20 522965c 5,472 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5472 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

GitHub

escoffier-labs/skillet · 4 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rwhhllqg3zoszho6
GET https://markdownregistry.com/api/v1/resolve?ref=escoffier-labs/skillet/diagnose-session
GET https://markdownregistry.com/api/v1/blob/4e8851f94904fe2d42b6493e6380c4320fdf5ff27d334034f482d091462cfb47

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.

More from escoffier-labs/skillet

brief SKILL.md skill
escoffier-labs/skillet · skillet/skills/brief/SKILL.md · Use when answering at a decision point - recommending an approach, reporting a verification result, finishing a task…
v0.2.0 · audit A · 4 stars
brigade-handoffs SKILL.md skill
escoffier-labs/skillet · skillet/skills/brigade-handoffs/SKILL.md · Use when setting up, checking, writing, linting, or troubleshooting Brigade memory handoffs for a repo or agent…
v0.1.1 · audit A · 4 stars
bug-hunt SKILL.md skill
escoffier-labs/skillet · skillet/skills/bug-hunt/SKILL.md · Use when asked to find bugs, hunt for correctness issues, sweep a codebase for defects, or verify a repo behaves as…
v0.1.0 · audit A · 4 stars
check SKILL.md skill
escoffier-labs/skillet · skillet/skills/check/SKILL.md · Use when about to claim anything works, is fixed, is complete, or passes - before committing, replying to the user, or…
v0.2.0 · audit A · 4 stars
demi SKILL.md skill
escoffier-labs/skillet · skillet/skills/demi/SKILL.md · Use before implementing, scaffolding, prototyping, or adding a feature when the work should start with the smallest…
v0.1.0 · audit A · 4 stars
eighty-six SKILL.md skill
escoffier-labs/skillet · skillet/skills/eighty-six/SKILL.md · Use when agents keep repeating the same mistake in a repository, the operator keeps correcting the same thing, or the…
v0.1.0 · audit A · 4 stars
expedite SKILL.md skill
escoffier-labs/skillet · skillet/skills/expedite/SKILL.md · Use when the user wants to act on an audit, fix the findings in a line-check/bug-hunt/security-sweep/latent-premises/ret…
v0.2.0 · audit A · 4 stars
fire SKILL.md skill
escoffier-labs/skillet · skillet/skills/fire/SKILL.md · Use when a written implementation plan is ready to execute, when the user says "fire", "execute the plan", "build it"…
v0.2.0 · audit A · 4 stars
fleet-conductor SKILL.md skill
escoffier-labs/skillet · skillet/skills/fleet-conductor/SKILL.md · Use when conducting a large backlog or multi-repository campaign across several worker lanes, especially when work…
v0.2.0 · audit A · 4 stars
garnish SKILL.md skill
escoffier-labs/skillet · skillet/skills/garnish/SKILL.md · Use when auditing or fixing discoverability metadata for a website before publication, including titles, descriptions…
v0.1.0 · audit A · 4 stars
graphtrail SKILL.md skill
escoffier-labs/skillet · skillet/skills/graphtrail/SKILL.md · Use when answering structural code questions in an indexed repo - who calls this, what does this call, what breaks if I…
v0.1.1 · audit A · 4 stars
grill SKILL.md skill
escoffier-labs/skillet · skillet/skills/grill/SKILL.md · Use when a technical writeup, blog post, war story, or "Show HN" is about to go to Hacker News, Lobsters, or any…
v0.1.3 · audit A · 4 stars

Every file in escoffier-labs/skillet

Browse by kind, by grade A, or by owner.