ClawHub

Ucts Retro

v1.0.0

Weekly engineering retrospective. What shipped, what broke, what to improve, with concrete action items. Works directly in OpenClaw — no Claude Code session...

⭐ 0· 39·0 current·0 all-time
by@muthukumaran-k-1

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for muthukumaran-k-1/ucts-retro.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Ucts Retro" (muthukumaran-k-1/ucts-retro) from ClawHub.
Skill page: https://clawhub.ai/muthukumaran-k-1/ucts-retro
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install ucts-retro

ClawHub CLI

Package manager switcher

npx clawhub@latest install ucts-retro
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the runtime instructions: a structured weekly engineering retrospective. The skill requests no binaries, env vars, or installs, which is appropriate for a facilitator/guide.
ℹ
Instruction Scope
SKILL.md stays on-topic (what shipped, what broke, improvements, up to 3 action items). One small out-of-band instruction says "Spawn a Claude Code session" and to run `Load UCTS. Run /ucts guide <...>` if actions require code — this references another tool/session but does not itself access files, creds, or system state. Verify that any referenced external session/plugin (Claude Code/UCTS) is trusted before invoking it.
✓
Install Mechanism
No install spec and no code files — instruction-only skill (lowest install risk).
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced in the instructions.
✓
Persistence & Privilege
always is false and the skill does not request persistent or elevated privileges. Agent autonomous invocation is allowed (platform default) but the skill itself does not request extra persistence.
Assessment
This skill is an instruction-only facilitator for retrospectives and appears coherent. Before installing, note: (1) it references spawning a separate "Claude Code" session — confirm that external session or plugin is trustworthy before you follow that step; (2) retrospectives can include sensitive information (incidents, root causes, personnel), so consider where generated content is stored or shared by your agent; (3) the skill can be invoked autonomously by the agent (platform default) — if you have strict controls, restrict invocation or review outputs before sharing externally.

Like a lobster shell, security has layers — review code before you run it.

latestvk9713pp9mwn7ny4mkd31r926w185ms1v
39downloads
0stars
1versions
Updated 1d ago
v1.0.0
MIT-0
@muthukumaran-k-1
latest
Download

UCTS Retro

Weekly engineering retrospective. This is a structured conversation — guide the user through each section.

Format

🚀 What Shipped?

List everything that shipped this week:

  • Features, fixes, improvements
  • PRs merged, deployments completed
  • Documentation updated

For each item, note:

  • Did it take longer than expected? Why?
  • Any surprises during implementation?
  • What would you do differently?

💥 What Broke?

List everything that went wrong:

  • Bugs found in production
  • Incidents, outages, reverts
  • Build failures, flaky tests
  • Missed deadlines

For each item:

  • Root cause (not symptoms). Use /investigate methodology if needed.
  • Impact: who was affected, for how long?
  • Was it preventable? What guard would have caught it?

🔧 What to Improve?

Identify friction points:

  • Process: what takes too long, what's manual that should be automated?
  • Tooling: what's broken, slow, or missing?
  • Knowledge: what did you have to learn the hard way?
  • Communication: what was unclear or undocumented?

✅ Action Items

Maximum 3. More than 3 means none will get done.

Each action item must have:

  • Owner: one person (not "the team")
  • Deadline: specific date (not "soon")
  • Definition of done: how do you know it's complete?

Bad: "Improve testing" Good: "Add integration tests for the payment flow by Friday. Done = CI passes with payment tests."

Bad: "Look into performance" Good: "Profile the /api/search endpoint, identify top bottleneck, open a PR with a fix by Wednesday."

If Actions Require Code

Spawn a Claude Code session:

Load UCTS. Run /ucts guide <action item description>

Comments

Loading comments...