A retrospective tool that turns completed stories into durable team lessons and rules.
Install
mkdir -p .claude/skills/retro-thawatchai-petkaew && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16726" && unzip -o skill.zip -d .claude/skills/retro-thawatchai-petkaew && rm skill.zipInstalls to .claude/skills/retro-thawatchai-petkaew
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 story retrospective that distills lessons from closed work and feeds them back into the team's memory — appends to the `docs/delivery/LESSONS.md` ledger and proposes promotions into `.claude/rules/<role>.md` for owner approval. Use when a story is Done (merged + verified) and you want the Scout sub-agents to actually get smarter, or to re-run learning on any past CAM ticket. Do NOT use it to run the pre-merge checks (that is `quality-gate`), to write the spec (`discover`), or to change Linear status (`update-status`).Key capabilities
- →Mine closed stories for lessons
- →Record lessons in an append-only ledger
- →Propose rule promotions to role rule files
- →Gather durable evidence from git logs and Linear issues
- →Distill lessons into specific types and generalities
- →Route lessons based on generality to appropriate destinations
How it works
The skill gathers evidence from durable sources for closed stories, distills lessons, records them in a ledger, and proposes rule promotions to role rule files for owner approval.
Inputs & outputs
When to use retro
- →Conducting project retrospectives
- →Updating team knowledge
- →Applying lessons from closed tasks
About retro
Analyzes closed stories to extract improvement opportunities. It updates a central ledger and proposes rule updates for sub-agents, ensuring the team learns and improves over time.
Run a story retrospective that distills lessons from closed work and feeds them back into the team's memory — appends to the `docs/delivery/LESSONS.md` ledger and proposes promotions into `.claude/rules/<role>.md` for owner approval. Use when a story is Done (merged + verified) and you want the Scou
When not to use it
- →For pre-merge gate checks, use the `quality-gate` skill.
- →For writing specs or closing Discovery gaps, use the `discover` skill.
- →For moving Linear state or labels, use the `update-status` skill.
Limitations
- →The skill is not for pre-merge checks.
- →The skill is not for writing specifications.
- →The skill is not for moving Linear state.
How it compares
This skill automates the capture and application of lessons from closed work into a team's rules, preventing knowledge from being lost in orchestrator memory.
Compared to similar skills
retro side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| retro (this skill) | 0 | 3mo | No flags | Intermediate |
| conductor-validator | 1 | 5mo | No flags | Beginner |
| linear-ticket | 1 | 8mo | No flags | Intermediate |
| session-handoff | 13 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
conductor-validator
sickn33
Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.
linear-ticket
useautumn
Refine rough engineering thoughts into structured Linear tickets with GitHub permalinks
session-handoff
davila7
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
spec-to-backlog
atlassian
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When Claude needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements into Jira issues. Handles reading Confluence pages, analyzing specifications, creating Epics with proper structure, and generating detailed implementation tickets linked to the Epic.
create-handoff
parcadei
Create handoff document for transferring work to another session
moai-workflow-project
modu-ai
Integrated project management system with documentation, language initialization, and template optimization modules. Use when setting up projects, generating documentation, configuring multilingual support, or optimizing templates.