Menu
Analyzes sessions using ACE framework to generate prompt improvement suggestions focused on durable patterns.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Persistent memory system with .memory.md, compaction, and cross-project sync
Database technology selection and architecture - choose between SQL vs NoSQL, PostgreSQL vs MySQL vs MongoDB, scaling strategies, migration planning. Use for database DECISIONS. For PostgreSQL implementation use postgresql skill.
Analyze feature flows for completeness, preconditions, and branch coverage using reusable flow-analyzer tools.
Automated post-phase validation workflow for GSD phases with deterministic gates and HITL controls.
Full workflow orchestration with config-driven routing and phase-based execution
Complete OpenCode knowledge base with live documentation access. Use for questions about OpenCode CLI, skills, plugins, tools, agents, SDK, or configuration. Automatically searches official docs via Context7 API with local fallback.
| name | ace-analysis |
| description | Analyzes sessions using ACE framework to generate prompt improvement suggestions focused on durable patterns. |
| license | MIT |
| compatibility | opencode |
| metadata | {"author":"OpenCode Community","version":"1.0.0"} |
Analyzes AI agent sessions using ACE (Agentic Context Engineering) framework.
Evaluate session quality and generate improvement suggestions for prompts, skills, and commands.
/ace-reflect commandPreferred: om-session plugin tools
session-list → get recent sessions
session-read → get messages from session
Fallback: OpenCode CLI
opencode session list -n 10 --format json
Last resort: Direct context analysis (current conversation)
| Mode | Flag | Scope |
|---|---|---|
| Default | (none) | Text analysis, 2-3 findings |
| Verbose | --verbose | Deeper analysis, more findings |
| Technical | --technical | Include IDs, timestamps, tool stats |
| Full | --full | Complete analysis with all metadata |
Focus on patterns, not individual mistakes:
Use scoring rubric from references/scoring-rubric.md:
| Criterium | Weight | Focus |
|---|---|---|
| Completeness | 5 | All requested tasks completed |
| Accuracy | 5 | Correct solutions, no hallucinations |
| Efficiency | 5 | Minimal iterations, good tool usage |
| Clarity | 5 | Clear communication, good structure |
| Relevance | 5 | On-topic, no unnecessary tangents |
Max Score: 25
Use template from references/report-template.md:
Return formal report for presentation to user.
references/report-template.md - Report structurereferences/scoring-rubric.md - Detailed scoring criteria| Situation | Action |
|---|---|
| No session data | Analyze current context directly |
| Plugin unavailable | Use CLI fallback |
| Subagent spawn fails | Analyze in current context |
features:
ace:
enabled: true
max_subagent_depth: 2
auto_apply_suggestions: false