/ralph-reflect
View and manage agent loop reflections and episodic memory
$ npx -y skills add jmagly/aiwg --skill ralph-reflect --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/ralph-reflect
Context preview
The summary Claude sees to decide when to auto-load this skill.
View and manage agent loop reflections and episodic memory
SKILL.md
ralph-reflect.SKILL.mdnamespace: aiwg
name: ralph-reflect
platforms: [all]
description: View and manage agent loop reflections and episodic memory
commandHint:
category: ralph
Al Reflect Command
View, search, and manage reflections from agent loop iterations.
Instructions
Manage the Reflexion episodic memory stored in `.aiwg/ralph/reflections/`:
Subcommand: show
Display reflections for a specific loop or the most recent loop.
1. Load reflections from `.aiwg/ralph/reflections/loops/` 2. Display each reflection with:
- Trial number, timestamp
- Outcome (success/failure/partial)
- Reflection text
- Strategy change
Subcommand: patterns
Show recurring patterns across all loops.
1. Load `.aiwg/ralph/reflections/patterns/` 2. Display patterns by frequency 3. Show success rate for each pattern 4. Highlight patterns applicable to current context
Subcommand: clear
Archive and clear reflection history.
1. Archive current reflections to timestamped directory 2. Reset loops and patterns directories 3. Preserve index.yaml
Arguments
- `show [loop-id]` - Show reflections for loop (default: latest)
- `patterns` - Show learned patterns
- `clear` - Archive and clear reflections
- `--format [yaml|markdown|summary]` - Output format (default: markdown)
- `--last [n]` - Show only last n reflections
- `--loop [id]` - Filter by loop ID
References
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/reflection-memory.json - Reflection schema
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/reflection-memory-guide.md - Guide
- @.aiwg/research/findings/REF-021-reflexion.md - Research foundation
Storage Routing (#934, #967)
This skill's persistence flows through `resolveStorage('reflections')`. On the default `fs` backend reflections live at `.aiwg/reflections/`. To redirect into Obsidian, Logseq, Fortemi, or another backend without changing this skill, configure `roots.reflections` or `backends.reflections` in `.aiwg/storage.config` (#934).
When this skill needs to read/write reflections from a Bash step, prefer the storage-routed CLI:
aiwg reflections list --prefix sessions/
aiwg reflections get sessions/2026-04-28.md
echo "# reflection" | aiwg reflections put sessions/2026-04-28.md
echo '{"event":"reflect","summary":"..."}' | aiwg reflections append-log sessions/log.jsonlThe legacy direct-fs paths continue to work on the default `fs` backend — byte-identical to what the adapter writes — but only the adapter route honors `storage.config` redirection.
Read more
namespace: aiwg name: ralph-reflect platforms: [all] description: View and manage agent loop reflections and episodic memory commandHint: category: ralph
Al Reflect Command
View, search, and manage reflections from agent loop iterations.
Instructions
Manage the Reflexion episodic memory stored in `.aiwg/ralph/reflections/`:
Subcommand: show
Display reflections for a specific loop or the most recent loop.
1. Load reflections from `.aiwg/ralph/reflections/loops/` 2. Display each reflection with:
- Trial number, timestamp
- Outcome (success/failure/partial)
- Reflection text
- Strategy change
Subcommand: patterns
Show recurring patterns across all loops.
1. Load `.aiwg/ralph/reflections/patterns/` 2. Display patterns by frequency 3. Show success rate for each pattern 4. Highlight patterns applicable to current context
Subcommand: clear
Archive and clear reflection history.
1. Archive current reflections to timestamped directory 2. Reset loops and patterns directories 3. Preserve index.yaml
Arguments
- `show [loop-id]` - Show reflections for loop (default: latest)
- `patterns` - Show learned patterns
- `clear` - Archive and clear reflections
- `--format [yaml|markdown|summary]` - Output format (default: markdown)
- `--last [n]` - Show only last n reflections
- `--loop [id]` - Filter by loop ID
References
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/reflection-memory.json - Reflection schema
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/reflection-memory-guide.md - Guide
- @.aiwg/research/findings/REF-021-reflexion.md - Research foundation
Storage Routing (#934, #967)
This skill's persistence flows through `resolveStorage('reflections')`. On the default `fs` backend reflections live at `.aiwg/reflections/`. To redirect into Obsidian, Logseq, Fortemi, or another backend without changing this skill, configure `roots.reflections` or `backends.reflections` in `.aiwg/storage.config` (#934).
When this skill needs to read/write reflections from a Bash step, prefer the storage-routed CLI:
aiwg reflections list --prefix sessions/
aiwg reflections get sessions/2026-04-28.md
echo "# reflection" | aiwg reflections put sessions/2026-04-28.md
echo '{"event":"reflect","summary":"..."}' | aiwg reflections append-log sessions/log.jsonlThe legacy direct-fs paths continue to work on the default `fs` backend — byte-identical to what the adapter writes — but only the adapter route honors `storage.config` redirection.
Multi-agent AI framework for Claude Code, Copilot, Cursor, Warp, and 6 more platforms 200+ agents, 109+ CLI commands, 400+ deployable agent/skill/command/rule artifacts, 8 core frameworks, 32 addons, and a 40-plugin Claude Code marketplace.
Repo: jmagly/aiwg
Other skills on aiwg.
- /agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Open skill - /agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Open skill - /auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Open skill - /cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Open skill - /debug-memory
Query and manage the executable feedback debug memory
Open skill - /execute-feedback
Execute tests on generated code and iterate until passing
Open skill

