reflection-injection
Inject relevant past reflections into agent context at iteration start so agents learn from prior mistakes without repeating them
What this skill does
# reflection-injection
Automatically inject relevant past reflections into agent context when starting new iterations or retrying after failures.
## Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "inject reflection" → explicit reflection injection shorthand
- "add metacognition" → metacognitive step insertion
## Purpose
This skill implements the Reflexion episodic memory injection pattern. Before each iteration, it loads relevant past reflections and injects them into the agent's context, enabling learning from past mistakes without repeating them.
## Behavior
When triggered, this skill:
1. **Load reflection history**:
- Read `.aiwg/ralph/reflections/loops/` for current loop reflections
- Read `.aiwg/ralph/reflections/patterns/` for cross-loop patterns
- Apply sliding window: k=5 most recent reflections
2. **Filter for relevance**:
- Match reflections by task type similarity
- Match by error type if retrying after failure
- Match by file/module if working on specific code
3. **Format for injection**:
- Convert reflections to natural language summary
- Use @$AIWG_ROOT/agentic/code/addons/ralph/templates/self-reflection-prompt.md template
- Prepend to agent context
4. **Track usage**:
- Record which reflections were injected
- Track whether injected reflections led to success
- Update pattern effectiveness scores
## Activation Conditions
```yaml
activation:
always_active_for:
- ralph-loop-orchestrator
- ralph-verifier
triggered_by:
- ralph_iteration_start
- agent_retry_after_failure
- explicit_user_request
skip_when:
- no_reflection_history: true
- first_iteration_of_first_loop: true
```
## Integration
This skill uses:
- `project-awareness`: Context for relevance filtering
- Agent Loop Orchestrator: Provides iteration state
- Reflection memory at `.aiwg/ralph/reflections/`
## References
- @$AIWG_ROOT/agentic/code/addons/ralph/schemas/reflection-memory.json - Schema
- @$AIWG_ROOT/agentic/code/addons/ralph/docs/reflection-memory-guide.md - Guide
- @$AIWG_ROOT/agentic/code/addons/ralph/templates/self-reflection-prompt.md - Prompt template
- @.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:
```bash
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.jsonl
```
The 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.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.