alienfast/retro
skills/retro/SKILL.md
Analyze completed Linear cycles for retrospectives. Identifies velocity trends, scope creep, and patterns to improve future planning.
testing
Updated Apr 15, 2026
$ install --global
skillsauthnpx skillsauth add alienfast/claude retroInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 6:08 PM4.5s1 file scanned
SKILL.md
- name:
- retro
- description:
- Analyze completed Linear cycles for retrospectives. Identifies velocity trends, scope creep, and patterns to improve future planning.
Retro Skill - Sprint Retrospective
You are an expert at analyzing completed sprints and generating actionable retrospective insights.
When to Use
Use this skill when:
- A sprint/cycle has ended
- Preparing for a retrospective meeting
- Analyzing team performance trends
Process
-
Gather Cycle Data
linear cycles analyze --team ENG --count 3 linear cycles get CYCLE-ID -
Analyze Completion
- Planned vs actual completion
- Scope changes during cycle
- Carry-over items
-
Identify Patterns
- Estimation accuracy
- Blocker frequency
- Category distribution
-
Generate Insights
Analysis Areas
Velocity & Completion
- Points planned vs completed
- Issue count planned vs completed
- Completion rate trend
Scope Management
- Issues added mid-cycle
- Issues removed/deferred
- Scope creep percentage
Blockers & Dependencies
- Issues that were blocked
- Average time blocked
- Dependency-related delays
Workload Distribution
- Points per team member
- Completion rate by assignee
- Bottleneck identification
Output Format
RETROSPECTIVE: Cycle 23
════════════════════════════════════════
SUMMARY
────────────────────────────────────────
Planned: 40 points (12 issues)
Completed: 34 points (10 issues)
Completion Rate: 85%
SCOPE CHANGES
────────────────────────────────────────
Added mid-cycle: 3 issues (8 pts)
Removed: 1 issue (2 pts)
Carried over: 2 issues (6 pts)
Scope creep: 15%
WHAT WENT WELL
────────────────────────────────────────
+ Auth refactor completed ahead of schedule
+ Zero critical bugs in production
+ Good collaboration on API work
WHAT COULD IMPROVE
────────────────────────────────────────
- 2 issues blocked for 3+ days (ENG-201, ENG-203)
- Underestimated ENG-205 (3pts planned, 8pts actual)
- Late scope additions disrupted focus
TRENDS (3 cycles)
────────────────────────────────────────
Velocity: 34 → 32 → 34 (stable)
Completion: 85% → 88% → 85% (stable)
Scope creep: 12% → 8% → 15% (increasing)
ACTION ITEMS
────────────────────────────────────────
1. Add buffer for complex API work
2. Daily standup check on blockers
3. Scope freeze after day 2
Commands Used
# Analyze recent cycles
linear cycles analyze --team ENG --count 3
# Get specific cycle details
linear cycles get CYCLE-23
# List cycle issues
linear issues list --team ENG --cycle CYCLE-23
# Check what was blocked
linear deps --team ENG
Discussion Questions
Generate discussion prompts for the team:
- Wins: What should we celebrate?
- Blockers: What slowed us down?
- Process: What would we do differently?
- Tools: Are there tools/automation to add?
- Communication: Where did we lose sync?
Best Practices
- Be data-driven - Base insights on actual metrics
- Focus on process - Not individual performance
- Actionable items - Every insight should have a follow-up
- Track over time - Compare to previous retros
Related Skills
alienfast/reap-worktrees
data-ai
VerifiedTrustedCommunity
Inspect and reclaim leftover /start wt worktrees. Shows which worktrees under .claude/worktrees/ are eligible for cleanup (PR merged, branch merged, or Linear issue Canceled/Done) and which are preserved (active or abandoned-for-resumption), and can reap the eligible ones now. Use when the user says 'reap worktrees', 'clean up worktrees', 'what worktrees are leftover', 'prune worktrees', or invokes /reap-worktrees.
SKILL.mdUpdated Jun 12, 2026
alienfast/merge-queue
testing
VerifiedTrustedCommunity
Inspect and drain the local deferred-merge queue. Shows worktree merges that /finish deferred (transient block — e.g. the main checkout was on the source branch with WIP) and that a local launchd drainer retries until they land. Use when the user says 'merge queue', 'what merges are pending', 'drain the merge queue', or invokes /merge-queue.
SKILL.mdUpdated Jun 11, 2026
alienfast/full
testing
VerifiedTrustedCommunity
End-to-end Linear issue macro — runs /start then /finish in sequence, gated on the /quality-review verdict. Worktree mode is opt-in via the `wt` token, mirroring /start. Pauses only for plan approval and the deferred-items filing decision; otherwise autonomous. Use when the user says 'full PL-XX', 'ship PL-XX end-to-end', or invokes /full.
SKILL.mdUpdated May 28, 2026
alienfast/quality-review
development
VerifiedTrustedCommunity
Adversarial implementation review with triage and fix loop. Hard-gates on `pnpm check`, delegates to the quality-reviewer agent for categorized findings (Critical/High/Medium/Nice-to-Have/Approved), then triages and fixes findings via the developer agent. Loops until a re-review surfaces no new Critical/High/Medium findings (convergence), with a soft ceiling of 5 cycles before asking the user how to proceed; option 3 of that prompt terminates with verdict `escalated-to-architect`. Use when the user says 'review my work', 'check this implementation', 'adversarial review', 'quality review', or invokes /quality-review.
SKILL.mdUpdated Apr 29, 2026