Session retrospective and skill audit. Use when "/reflect", "session review", "retrospective", "what went wrong", "lessons learned", "what should we remember", or "what can we improve".
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Reflect
## Success Criteria
- Every mistake/friction point cites the specific moment and its impact
- Improvements are actionable, prioritized, and <= 10 items
- Each skill audit proposes measurable changes (not vague suggestions)
- User is asked which items to persist to memory
## Process
### 1. Session Review
Scan the full conversation. For each finding, cite the specific exchange (quote or paraphrase) and its impact.
| Category | Signal |
|----------|--------|
| **Mistakes** | Wrong outputs, incorrect assumptions, hallucinated facts |
| **Friction** | Repeated clarifications, verbose responses, misread intent |
| **Wasted effort** | Work discarded, wrong approaches tried first |
| **Wins** | Approaches worth repeating, smooth interactions |
Skip one-time typos, external tool failures, and issues outside agent control.
### 2. Improvements
Numbered list of **concrete improvements**, ranked by impact. Each item: one sentence, imperative, actionable. Cap at 10.
Ask: *"Which of these should I remember for future chats?"*
Save approved items to memory files via the auto memory system.
### 3. Skill Audit (if skills were used)
For each skill invoked during the session:
…
The line at the top of this page pins the label git:20260227.215f429, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_o4cbxkjyfhudaqsw
GET https://markdownregistry.com/api/v1/resolve?ref=iliaal/whetstone/reflect
GET https://markdownregistry.com/api/v1/blob/deec149fff733f2985d0568f9b88881f0e4f2f438be8225435a549d2da3c0ef3
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
iliaal/whetstone · .agents/skills/audit-plugin/SKILL.md · Audit Whetstone skills, agents, and commands when asked for a plugin quality or consistency audit.
iliaal/whetstone · .agents/skills/diagnose-negatives/SKILL.md · Investigate negative session feedback for a Whetstone skill when asked to diagnose its failures.
iliaal/whetstone · .agents/skills/eval-skills/SKILL.md · Evaluate Whetstone skills from session evidence when asked to compare procedure-following results or optimization…
iliaal/whetstone · .agents/skills/skillopt/SKILL.md · Prepare or run Whetstone SkillOpt optimization when asked to optimize a process skill using SkillOpt.
iliaal/whetstone · .agents/skills/sync-from-repos/SKILL.md · Compare Whetstone with reference repositories when asked to sync cross-repository improvements.
iliaal/whetstone · .agents/skills/write-skill/SKILL.md · Author a new Whetstone plugin skill when asked to write a skill without upstream skills.sh sources.
cursor/plugins · pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
cursor/plugins · harness/pstack/claude-code/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
nightly-labs/openbot · marketplace/production-catalog/bundles/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
michael-denyer/pstack-claude · plugins/pstack/skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
backnotprop/pstack · skills/reflect/SKILL.md · Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit…
bradygaster/squad · packages/squad-cli/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
bradygaster/squad · packages/squad-sdk/templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
bradygaster/squad · .squad-templates/skills/reflect/SKILL.md · Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating…
