run-retrospective SKILL.md skillA

run-retrospective from tomzx/agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tomzx/agents/run-retrospective@git:20261007.b35fc4b

Pins git:20261007.b35fc4b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tomzx/agents
Path
skills/pdlc/skills/run-retrospective/SKILL.md
Versions recorded
3
Latest version
git:20261007.b35fc4b, committed Oct 7, 2026
First version recorded
Aug 5, 2026
Size
1,985 bytes
Repository stars
12
License
MIT

Capture what to keep, stop, and start after an initiative, sprint, or kill. Closes the PDLC cycle by turning experience into durable knowledge.

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

# Run Retrospective

Turns a completed initiative, a sprint, or a killed bet into organizational knowledge.
Produces a learning record in `.pdlc/learnings/`.
A kill without a retrospective wastes the effort — the point of killing is to learn cheaper than building would have taught.

## Prerequisites

- Apply the shared PDLC conventions in `skills/pdlc/references/shared.md`.
- A concluded initiative (shipped, iterated, or killed), or a sprint boundary.

## Steps

1. Frame the scope: which initiative or period, and what outcome occurred (shipped, iterated, killed).
2. Capture what to **keep** (what worked and should be repeated), what to **stop** (what to never do again), and what to **start** (new actions to try).
3. For each item, name the root cause, not just the symptom.
   "We were slow" is a symptom; "discovery and build ran in series with no handoff contract" is a root cause.
4. Tie each learning back to the artifact chain: which assumption, decision, or gate should have caught this earlier?
5. Convert the strongest start/stop items into concrete next actions with owners (feed the roadmap or a new initiative).
6. Write the record to `.pdlc/learnings/N-<slug>.md`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tomzx/agents/run-retrospective@sha256:70f4a44fc7f4fdfd

The line at the top of this page pins the label git:20261007.b35fc4b, 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_i775gixpewjf7moq.svg)](https://markdownregistry.com/a/art_i775gixpewjf7moq)

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

Versions

The registry has recorded 3 versions of this file, between Aug 5, 2026 and Oct 7, 2026, about one every 31 days.

versioncommittedcommitsizeaudit
git:20261007.b35fc4b latest2026-10-07 b35fc4b 1,985 BA view · diff
git:20261004.00bb0c52026-10-04 00bb0c5 1,982 BA view · diff
git:20260805.6b623072026-08-05 6b62307 1,973 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 (1985 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

tomzx/agents · 12 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_i775gixpewjf7moq
GET https://markdownregistry.com/api/v1/resolve?ref=tomzx/agents/run-retrospective
GET https://markdownregistry.com/api/v1/blob/70f4a44fc7f4fdfd4166cc69ef375e1dab9b645c7f020f8469e2e2cd9ecede4c

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 tomzx/agents

AGENTS.md AGENTS.md file
tomzx/agents · AGENTS.md
git:20261006.2803bc1 · audit A · 12 stars
CLAUDE.md CLAUDE.md file
tomzx/agents · CLAUDE.md
git:20260209.7ff04f3 · audit B · 12 stars
AGENTS.md@repositories/openchamber/openchamber AGENTS.md file
tomzx/agents · repositories/openchamber/openchamber/AGENTS.md
git:20260726.7244df1 · audit B · 12 stars
agents-section-daily-refresh SKILL.md skill
tomzx/agents · skills/agents-section-daily-refresh/SKILL.md · Curate the agent-maintained blog section (blog.tomrochette.com-content) by following the Daily refresh procedure in…
git:20261007.b35fc4b · audit A · 12 stars
analyze-git-churn SKILL.md skill
tomzx/agents · skills/analyze-git-churn/SKILL.md · Analyze git history to identify high-churn files and suggest targeted improvements such as refactoring, test coverage…
git:20261007.b35fc4b · audit A · 12 stars
analyze-test-coverage SKILL.md skill
tomzx/agents · skills/analyze-test-coverage/SKILL.md · Analyze a set of code changes (diff or files) and produce a structured test coverage report with three parts…
git:20261007.b35fc4b · audit A · 12 stars
arxiv-article SKILL.md skill
tomzx/agents · skills/arxiv-article/SKILL.md · Downloads an arXiv HTML article, converts it to markdown with pandoc, archives it, and returns a structured summary…
git:20261007.b35fc4b · audit A · 12 stars
arxiv-catchup SKILL.md skill
tomzx/agents · skills/arxiv-catchup/SKILL.md · Fetches new arXiv cs.AI papers published since the last processed date, processes each paper's HTML version via the…
git:20261007.b35fc4b · audit A · 12 stars
assess-pr-risk SKILL.md skill
tomzx/agents · skills/assess-pr-risk/SKILL.md · Estimate how risky a GitHub pull request is and how confident that estimate is, then recommend the next action for a…
git:20261007.b35fc4b · audit A · 12 stars
attach-assets SKILL.md skill
tomzx/agents · skills/attach-assets/SKILL.md · Upload files (images, logs, screenshots) to a dedicated orphan branch in the repository and embed them in a GitHub…
git:20261007.b35fc4b · audit A · 12 stars
audit-attention SKILL.md skill
tomzx/agents · skills/audit-attention/SKILL.md · Audit how your time splits between compounding and depreciating activities using the two-year test. Use when the user…
git:20261007.b35fc4b · audit A · 12 stars
audit-compatibility SKILL.md skill
tomzx/agents · skills/audit-compatibility/SKILL.md · Audit the codebase for compatibility, the ISO/IEC 25010 characteristic covering co-existence (running alongside other…
git:20261007.b35fc4b · audit A · 12 stars

Every file in tomzx/agents

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