agentflow-retro
Automates a retrospective process every 10 completed user stories to analyze workflow, identify friction, and generate actionable improvements for project documentation.
Install
mkdir -p .claude/skills/agentflow-retro && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14755" && unzip -o skill.zip -d .claude/skills/agentflow-retro && rm skill.zipInstalls to .claude/skills/agentflow-retro
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Run a retrospective after every 10 completed User Stories. Use when the retro counter reaches 10, when the team wants to reflect on recent work, or when continuous improvement analysis is needed.Key capabilities
- →Track completed user stories for retrospectives
- →Trigger retrospectives after 10 completed user stories
- →Review past tasks and commits for data gathering
- →Identify recurring patterns and workflow friction
- →Generate actionable items for process improvement
- →Update project rules in CLAUDE.md
How it works
This skill triggers a retrospective based on a counter of completed user stories. It guides the review of recent work to identify patterns and generate actionable items for improvement.
Inputs & outputs
When to use agentflow-retro
- →Conduct a team reflection after completing 10 user stories
- →Analyze workflow friction and cycle time issues
- →Update project rules in CLAUDE.md based on team feedback
- →Document root causes for recent bugs and quality issues
- →Identify new tooling needs and add them to the backlog
About this skill
Retrospective — Continuous Improvement
Triggered every 10 completed User Stories (tracked in project memory).
When to Run
- Retro counter reaches 10 completed User Stories
- Either party requests: "Let's do a retro"
- After a significant incident or quality issue
Counter tracks US completions only — spikes, bugs, and tooling tasks don't count.
Retro Template
## Retro -- [date] -- after story N
### What worked well
-
### Friction / slowdowns
-
### Bugfix quality (were root causes documented?)
-
### Memory + tooling gaps
-
### Inner loop robustness
-
### Quality gate effectiveness
-
### Actionable items
- [ ] (add to BACKLOG#Ideation or update project rules)
Process
- Gather data — review DONE-Today and archives since last retro
- Walk each section — be specific, reference actual tasks/commits
- Identify patterns — what keeps recurring?
- Generate actionable items — each must be concrete and assignable:
- Process improvements -> update project CLAUDE.md rules
- Tool gaps -> add to BACKLOG#Ideation
- Anti-patterns -> add to KNOWN_PATTERNS.md
- Reset counter — set
retro_stories_since_last: 0in project memory
Scope
The retro covers:
- Workflow friction and cycle time
- Bugfixing approach quality (were root causes documented?)
- Memory file usefulness
- Inner/outer loop robustness
- Tooling gaps
- Quality gate effectiveness
Output
- Actionable items added to BACKLOG#Ideation
- Rule updates applied to project CLAUDE.md
- New anti-patterns added to KNOWN_PATTERNS.md
- Counter reset in project memory
When not to use it
- →When the retro counter has not reached 10 completed user stories
- →When the team does not want to reflect on recent work
- →When continuous improvement analysis is not needed
Limitations
- →Retro counter tracks US completions only
- →Spikes, bugs, and tooling tasks do not count towards the retro counter
- →The retro covers specific areas like workflow friction and tooling gaps
How it compares
This skill automates the triggering and structuring of retrospectives based on a predefined metric, providing a consistent process compared to ad-hoc team reflections.
Compared to similar skills
agentflow-retro side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agentflow-retro (this skill) | 0 | 5mo | No flags | Beginner |
| archon | 9 | 9mo | Review | Intermediate |
| linear | 10 | 2mo | No flags | Beginner |
| zapier-workflows | 11 | 8mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by cordsjon
View all by cordsjon →You might also like
archon
coleam00
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing projects/tasks, or querying indexed knowledge. Provides RAG-powered semantic search, website crawling, document upload, hierarchical project/task management, and document versioning. Always try Archon first for external documentation and knowledge retrieval before using other sources.
linear
lobehub
Linear issue management guide. Use when working with Linear issues, creating issues, updating status, or adding comments. Triggers on Linear issue references (LOBE-xxx), issue tracking, or project management tasks. Requires Linear MCP tools to be available.
zapier-workflows
davila7
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
attio-skill-generator
kesslerio
Generate use-case-specific Attio workflow skills from templates. Use when creating new skills for lead qualification, deal management, customer onboarding, or custom Attio workflows.
github-manage
matteocervelli
Manage operations concerning GitHub on behalf of user
cto-engineering-metrics
rinaldofesta
Expert methodology for defining, tracking, and interpreting engineering performance metrics including DORA, team health, productivity, and executive reporting.