retro-facilitator

SkillDocs & knowledge

Structures raw sprint retro notes into themes and concrete actions. Use after a retro when raw sticky-note-style input (what went well/poorly/to try) needs to become a clean summary with follow-through.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the retro-facilitator skill

What this skill tells your AI

The instructions your AI receives, as published by codebygarv/ai-skills in skills/productivity/retro-facilitator/SKILL.md and read by ahel’s review.

Purpose

Turn raw retro input (a scattered list of what went well, what didn't, and ideas to try) into a structured summary with clustered themes and concrete, ownable action items — so retros produce follow-through instead of just catharsis.

When to Use

  • After a sprint/iteration retro, with raw notes (sticky notes, a shared doc, verbal notes) that need structuring.
  • A team's retros tend to surface the same complaints repeatedly with no visible action — worth using this to force clustering and concrete actions.

What to Analyze / Do

  1. Cluster related raw items into themes — several individually-worded complaints about "too many meetings," "context switching," "no focus time" likely cluster into one theme (interruption/focus-time issues), not three separate items.
  2. Separate went-well from went-poorly from ideas-to-try clearly.
  3. Convert the most significant themes into concrete action items — not every theme needs an action (some are just useful signal), but recurring or high-impact ones should get one.
  4. Flag recurring themes explicitly if this is a repeat topic from a prior retro (only if that context is provided) — a theme that keeps coming back with no action is itself worth surfacing.
  5. Keep action items scoped and ownable — "communicate better" isn't actionable; "add a 15-min daily written status update in the team channel" is.

Output Format

  • Went Well — clustered, brief.
  • Went Poorly — clustered into themes, not a flat list of every raw complaint.
  • Ideas to Try — clustered.
  • Action Items — table: Action | Owner (if assigned in the retro) | Related theme.
  • Flag any theme noted as recurring, if prior-retro context was given.

Avoid

  • Producing an action item for every single raw note — cluster first, act on the themes that matter most.
  • Vague action items that can't be checked off as done or not done.
  • Softening a genuinely negative theme into vague positive-sounding language — accurate clustering matters more than making the summary feel nice.

Signals

GitHub stars
25
Forks
1
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
retro-facilitator
Source
github.com/codebygarv/ai-skills