Skip to content
Agentmart
Submit a tool

scrum-master-lite

Skill by ejacklab

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ejacklab-scrum-master-lite

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
scrum-master-lite
Description
None
License
MIT
Instructions
54 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • invalid YAML frontmatter: Nested mappings are not allowed in compact mappings at line 2, column 14:
  • name: missing
  • description: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Scrum Master Lite

Default operating loop for this workspace.

## The 3 Triggers

```text
ON_FEATURE_START → PLAN
ON_FEATURE_END   → REVIEW
ON_TASK_COMPLETE → RETRO
```

Plus: **CEO_CHECK** anytime when direction feels muddy.

## Trigger 1: ON_FEATURE_START → PLAN

Use when starting any non-trivial task.

Do this:
1. Gather context from the relevant files
2. Create a short implementation plan with testable items
3. If the task looks large, split it
4. Present the plan before major edits when review is needed

## Trigger 2: ON_FEATURE_END → REVIEW

When implementation is done:
1. Verify acceptance criteria
2. Check for stale docs or obvious cleanup
3. Summarize what changed and any remaining risks

## Trigger 3: ON_TASK_COMPLETE → RETRO

When the task is actually complete:
1. Record what worked / what failed
2. Update `plans/diary.md`
3. Update `memory/YYYY-MM-DD.md` if the lesson matters beyond the task
4. Update docs/rules if a repeatable lesson was learned

## CEO_CHECK

Ask this whenever a task is ambiguous:
- Is this aligned with what Ejack actually wants?
- Is this the smallest useful step?
- Am I optimizing the artifact instead of the real goal?

## Anti-Patterns

- Starting long work without a plan
- Declaring done before verification
- Hiding uncertainty instead of surfacing it
- Skipping the retro because the task “basically worked”

From ejacklab/vtic, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Mar 13, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from ejacklab

Cite this page

scrum-master-lite skill. Agent Mart. https://agentmart.dev/skills/ejacklab-scrum-master-lite (last updated 2026-10-24)