Automated summary
Generates a structured Start-Stop-Continue retrospective as three actionable tables (Start, Stop, Continue), capped with a single top priority and a follow-up check-in.
Strengths
- The tables force an owner and a date on every action, which prevents retros that never lead anywhere
- The Continue section is explicitly protected by the guidelines, even though it is usually rushed
- A single top priority is highlighted at the end, limiting the number of parallel initiatives
- The guidelines push for specific, behavioral wording instead of vague intentions
Limitations
- Provides no live facilitation mechanics (voting, round-robin, timeboxing): it produces a document, not a meeting run-of-show
- Output quality depends entirely on the context given in the prompt; without real facts the items stay generic
- Guidelines ask to avoid focusing on people, so it is unsuitable for addressing interpersonal tension
Use it to prepare or write up a sprint retro, a project post-mortem, or a personal habit audit.
Avoid it for facilitating a live retro with team discussion or for analyzing quantitative process metrics.
Security analysis
SafeThis is a pure prompt/template skill with no declared tools and no executable content. It contains no shell commands, network calls, file operations, or credential handling—just a structured retrospective template with tables and placeholder text. The only variable is $ARGUMENTS, which is standard prompt interpolation and introduces no execution risk.
No concerns found
How this analysis is madeExamples
Run a Start-Stop-Continue retro for our team's last two-week sprint. Context: we shipped the billing migration two days late, standups often ran 25 minutes, and code review turnaround was slow. Use tables with owners and dates.Fais une rétro Start-Stop-Continue de mes trois derniers mois sur mon side project : j'ai livré une seule fonctionnalité, je passe mes soirées à refactoriser sans fin, mais j'ai gardé un rythme de commits quotidien.Prepare a Start-Stop-Continue process review of our weekly release process: releases need two manual sign-offs, rollbacks are frequent, and the post-release checklist works well. End with one top priority and a check-in date.name: retro description: Start-Stop-Continue retrospective identifying what to Start doing, Stop doing, and Continue doing. Use for sprint retros, personal reflection, team process reviews, or habit audits. user-invocable: true
Start-Stop-Continue Retrospective
Run a focused retrospective identifying what to Start, Stop, and Continue.
Instructions
Analyze the subject (project, period, process) and generate specific, actionable items for each category. Focus on behaviors and practices, not people.
Output Format
Subject: What period or topic are we reflecting on? Timeframe: What period does this cover?
START
New practices or behaviors to begin
| What to Start | Why | Owner | When | |--------------|-----|-------|------| | [Specific action] | [Benefit expected] | [Who] | [Start date] | | [Specific action] | [Benefit expected] | [Who] | [Start date] | | [Specific action] | [Benefit expected] | [Who] | [Start date] |
STOP
Current practices to eliminate
| What to Stop | Why | Owner | When | |--------------|-----|-------|------| | [Specific thing to stop] | [Problem it causes] | [Who] | [End date] | | [Specific thing to stop] | [Problem it causes] | [Who] | [End date] | | [Specific thing to stop] | [Problem it causes] | [Who] | [End date] |
CONTINUE
Things that are working well
| What to Continue | Why It Works | How to Protect It | |-----------------|--------------|-------------------| | [Working practice] | [Value it provides] | [How to ensure it continues] | | [Working practice] | [Value it provides] | [How to ensure it continues] | | [Working practice] | [Value it provides] | [How to ensure it continues] |
Top Priority The single most impactful change from this retro:
[Action] — because [reason]
Check-in When will we review if these changes are working?
[Date or trigger]
Guidelines
- Be specific: "Start daily standups" not "communicate more"
- Be behavioral: Focus on actions, not attitudes
- Balance: Aim for 3-5 items per category
- Celebrate Continues: Don't skip this section—recognize what's working
- Assign owners: Unowned actions don't happen
- One priority: If everything is important, nothing is
$ARGUMENTS
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/start-stop-continue-retrospective-ms47vp5s' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/start-stop-continue-retrospective-ms47vp5s/download' --output '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md.part' && mv '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md.part' '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && test -s '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/retro' && cp -R '.skill-downloads/start-stop-continue-retrospective-ms47vp5s' '.claude/skills/retro'Cursor
test -f '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && test -s '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/retro' && cp -R '.skill-downloads/start-stop-continue-retrospective-ms47vp5s' '.cursor/skills/retro'Codex
test -f '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && test -s '.skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/retro' && cp -R '.skill-downloads/start-stop-continue-retrospective-ms47vp5s' '.agents/skills/retro'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/start-stop-continue-retrospective-ms47vp5s'openskills read 'start-stop-continue-retrospective-ms47vp5s'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/start-stop-continue-retrospective-ms47vp5s/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.