メニュー
Cross-AI plan convergence - replan until review concerns are resolved.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | gsd-plan-review-convergence |
| description | Cross-AI plan convergence - replan until review concerns are resolved. |
Flow: Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check unresolved HIGH + actionable non-HIGH → Skill("gsd-plan-phase --reviews") → Agent→Skill("gsd-review") → ... → Converge or escalate
Replaces gsd-plan-phase's internal gsd-plan-checker with external AI reviewers (codex, gemini, etc.). Plan-phase runs inline (bare Skill at depth 0) so it can spawn gsd-planner/gsd-plan-checker at depth 1. Review runs inside an isolated Agent (gsd-review is a Bash leaf — no sub-agents needed). Orchestrator only does loop control.
Orchestrator role: Parse arguments, validate phase, run plan-phase inline (Skill at depth 0), spawn an Agent for gsd-review, check unresolved HIGH and actionable non-HIGH counts, stall detection, escalation gate.
<execution_context> @/home/aming/.config/opencode/gsd-core/workflows/plan-review-convergence.md @/home/aming/.config/opencode/gsd-core/references/revision-loop.md @/home/aming/.config/opencode/gsd-core/references/gates.md @/home/aming/.config/opencode/gsd-core/references/agent-contracts.md </execution_context>
<runtime_note>
Copilot (VS Code): Use vscode_askquestions wherever this workflow calls question. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. Do not skip questioning steps because question appears unavailable; use vscode_askquestions instead.
</runtime_note>
Flags:
--codex — Use Codex CLI as reviewer (default if no reviewer specified)--gemini — Use Gemini CLI as reviewer--claude — Use the agent CLI as reviewer (separate session)--opencode — Use OpenCode as reviewer--ollama — Use local Ollama server as reviewer (OpenAI-compatible, default host http://localhost:11434; configure model via review.models.ollama)--lm-studio — Use local LM Studio server as reviewer (OpenAI-compatible, default host http://localhost:1234; configure model via review.models.lm_studio)--llama-cpp — Use local llama.cpp server as reviewer (OpenAI-compatible, default host http://localhost:8080; configure model via review.models.llama_cpp)--all — Use all available CLIs and running local model servers--max-cycles N — Maximum replan→review cycles (default: 3)Feature gate: This command requires workflow.plan_review_convergence=true. Enable with:
gsd config-set workflow.plan_review_convergence true
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use this skill when the user wants direct operations on an Obsidian vault: read or edit notes and daily notes, search vault contents, count or list notes, manage tasks, move or rename files, find orphaned notes or broken links, inspect frontmatter/properties, manage sync or file history, query Bases, manage bookmarks, script the CLI, or run JavaScript against the Obsidian API. Trigger when the request implies "go into my vault and do X"; the user wants action on vault data, not an explanation. Skip pure conceptual or GUI-help questions such as settings navigation, theme/plugin installation, sync troubleshooting, Dataview syntax, keyboard shortcuts, or parsing vault files with unrelated external scripts.
Captures corrections, failures, missing capabilities, and reusable discoveries in agent so future work improves. Use this skill whenever a command, tool, or API fails unexpectedly; the user corrects the agent; the agent realizes its knowledge is outdated or wrong; a missing capability is exposed; or a better recurring approach is discovered. Record the result under .agents/learnings/, review related entries before major tasks, and promote durable workflow rules into AGENTS.md when they should change future behavior.
Generate tests for a completed phase based on UAT criteria and implementation
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit