skmtc-retro-review SKILL.md skillA

skmtc-retro-review from skmtc/skmtc is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add skmtc/skmtc/skmtc-retro-review@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: skmtc/skmtc
Path: deno/docs/skills/skmtc-retro-review/SKILL.md
Versions recorded: 3
Latest version: v0.1.0, committed Oct 19, 2026
First version recorded: May 15, 2026
Size: 21,392 bytes
Repository stars: 19
License: Apache-2.0

Aggregate friction log files across a time period to identify recurring patterns, classify each cluster by intervention type, produce a prioritized action plan with success criteria, and calculate convergence metrics. Complements `skmtc-retro` (which captures per-session signal) by acting as the system's actuator: turning accumulated observations into decisions. The primary output is a review document that makes the "is it getting better?" question answerable. Use this skill when the user…

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

# Skmtc retro review

The friction log is a sensor. This skill is the actuator. Its job is to
read accumulated observations, detect patterns the per-session view cannot
see, classify each pattern by what kind of intervention would eliminate it,
and produce an action plan the user can execute.

Without this skill, the friction log is a cemetery: observations accumulate
but nothing systematically improves. The review closes the loop.

## 1. When to invoke

**Scheduled cadence (recommended):**
- Monthly: review all sessions in the prior month.
- Pre-release: audit open entries against the release's scope to catch
  unresolved blockers before they reach users.

**On-demand:**
- After 3+ sessions in the same feature area (e.g., "three sessions on
  enrichment config in a week — what's the systemic issue?").
- When the user suspects a pattern but can't see it from individual retros.
- After a significant skill or doc update: "did the change actually work?"

**Skip if:**
- Fewer than 3 session files have accumulated since the last review.
- The friction log is empty or contains only resolved entries.

## 2. Locating files

**Friction log:**

```
<skmtc-root>/skmtc/deno/docs/friction-log/
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add skmtc/skmtc/skmtc-retro-review@sha256:77bfe06b8d957601

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](https://markdownregistry.com/badge/art_55d37gpojgx565gt.svg)](https://markdownregistry.com/a/art_55d37gpojgx565gt)

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

Versions

The registry has recorded 3 versions of this file, between May 15, 2026 and Oct 19, 2026, about one every 78 days.

version	committed	commit	size	audit
v0.1.0 latest	2026-10-19	5b8d1a9	21,392 B	A	view · diff
v0.1.0	2026-08-29	8d49f74	21,392 B	A	view · diff
v0.1.0	2026-05-15	34b0f89	21,365 B	A	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 (21392 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

skmtc/skmtc · 19 stars · license Apache-2.0 · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_55d37gpojgx565gt
GET https://markdownregistry.com/api/v1/resolve?ref=skmtc/skmtc/skmtc-retro-review
GET https://markdownregistry.com/api/v1/blob/77bfe06b8d957601fa6510f2d43292923d1e0aa834a4491de2c562c3bd590354

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.