skills/reviews-retros-reflection/SKILL.md
Facilitates structured team reflection through retrospectives, post-mortems, after-action reviews, and weekly/quarterly reviews, producing root cause analysis and SMART action items with psychological safety. Use when conducting sprint retrospectives, project post-mortems, weekly reviews, quarterly reflections, after-action reviews (AARs), or when user mentions "retro", "retrospective", "what went well", "lessons learned", "reflection", or "how can we improve".
npx skillsauth add lyndonkl/claude reviews-retros-reflectionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Copy this checklist and track your progress:
Retrospective Progress:
- [ ] Step 1: Set the stage (context, psychological safety)
- [ ] Step 2: Gather data (what happened)
- [ ] Step 3: Generate insights (why it happened)
- [ ] Step 4: Decide actions (what to change)
- [ ] Step 5: Close and follow up (commit, track)
Step 1: Set the stage
Define period/scope, review previous action items, establish psychological safety (Prime Directive: "everyone did best job given knowledge/skills/resources/context"). For quick reviews → Use resources/template.md. For complex team retros → Study resources/methodology.md.
Step 2: Gather data
Collect facts about period: metrics (velocity, bugs, incidents), events (launches, blockers, decisions), sentiment (team energy, morale). See Retrospective Formats for collection methods.
Step 3: Generate insights
Identify patterns, root causes, surprises. Ask "why?" to move from symptoms to causes. Use resources/methodology.md for root cause techniques (5 Whys, fishbone diagrams, timeline analysis).
Step 4: Decide actions
Vote on most impactful improvements (dot voting, SMART criteria). Define 1-3 SMART actions (Specific, Measurable, Assigned owner, Realistic, Time-bound). See Common Patterns for action quality criteria.
Step 5: Close and follow up
Commit to actions, schedule check-in, thank participants. Track action completion rate (target: >80% completion before next retro). Self-check using resources/evaluators/rubric_reviews_retros_reflection.json before closing. Minimum standard: Average score ≥ 3.5.
Start/Stop/Continue (Simple, Balanced):
Mad/Sad/Glad (Emotion-Focused):
4Ls (Comprehensive):
Sailboat/Speedboat (Metaphor-Based):
Timeline (Chronological):
Pattern 1: Sprint Retrospective (Agile)
Pattern 2: Project Post-Mortem
Pattern 3: Weekly Team Review
Pattern 4: Incident Retrospective
Psychological safety:
Quality standards:
Common pitfalls to avoid:
Resources:
resources/evaluators/rubric_reviews_retros_reflection.json5-Stage Process: Set Stage → Gather Data → Generate Insights → Decide Actions → Close
Top Formats:
Action Quality: SMART criteria + <5 total + >80% completion rate
Psychological Safety: Prime Directive + Blameless + Confidential
testing
Cluster a conference's event records into a small set of coarse themes with finer sub-clusters, an explicit outlier bucket, and soft (multi-membership) affinities — using the hybrid embed-then-label pipeline (embed abstracts, reduce, density-cluster, then LLM-label the clusters) when embedding libraries are available, and an LLM-reasoned hierarchical fallback when they are not. Embeddings do the grouping; the LLM only names the groups. Conference-agnostic. Use when turning structured event records into a navigable theme map for preference elicitation and scheduling, when you need 6-8 reasonable themes rather than 20 muddy ones, or when overlapping talks must belong to more than one theme. Trigger keywords - theme clustering, cluster talks, embed then label, soft membership, outlier talks, conference themes, topic map.
development
Build a personal conference schedule as a constraint-optimization problem — hard constraints (no time overlap, room-to-room travel time, capacity/registration, the attendee's own must-attends and blackouts) plus a user-owned weighted objective trading interest against breadth, pacing (maximize contiguous free time), and serendipity. Surfaces unbreakable conflicts (two high-value overlapping talks the model cannot rank) as decisions for the human rather than silently picking, and reports what each choice traded away. Conference-agnostic. Use to turn a preference profile plus a theme map into a day-by-day plan, to resolve overlapping sessions, or to balance a packed vs paced schedule. Trigger keywords - schedule optimization, conference schedule, constraint optimization, overlapping talks, contiguous free time, conflict surfacing, packed vs paced.
development
Parse a heterogeneous conference program (markdown, HTML, PDF-derived text, or JSON) into normalized event records with per-field confidence scores and independent classification axes (topic, depth, format, prerequisites, recorded, capacity). Detects the program's format before extracting, treats every inferred field as uncertain (present vs inferred vs missing), and flags thin or missing abstracts so downstream enrichment can target them. Conference-agnostic. Use when ingesting a conference or event schedule into a structured store, normalizing a talk/session list, or extracting per-session metadata with calibrated confidence. Trigger keywords - program ingestion, parse schedule, session extraction, event records, conference program, talk metadata, per-field confidence.
development
Build a personalized preference profile from a small number of well-chosen, cluster-grounded questions instead of a long survey. Represents the person's interests as an uncertainty region over the theme map, picks the single highest-information-gain choice-based question (contrasting real talks from different clusters), balances exploiting known interests against exploring uncertain ones, deliberately injects outlier probes to fight selection bias, and stops as soon as the schedule would be stable. Also elicits the user-owned objective weights and hard constraints. Interactive — runs where it can actually ask the person. Conference-agnostic. Use to turn a theme map into a preference profile, to decide what to ask a conference attendee, or to elicit scheduling priorities. Trigger keywords - preference elicitation, ask few questions, information gain, choice-based questions, selection bias probe, objective weights, attendee preferences.