msd-core/skills/gsd-plan-review-convergence/SKILL.md at 697cbb1f05b47a3ea2461ba1d98f0fecf7d1045e

Files

Tom Boucher da4a86d8c1 feat(#1596 ): ship GSD skills via .claude-plugin/plugin.json

Phase B-provide of epic #1258. Adds a build-generated skills/ dir +
a skills manifest field so plugin-installed GSD exposes gsd-core:<skill>
the native Claude Code way. Closes the gap where plugin-only installs
lacked the skill surface because bin/install.js never ran.

- scripts/gen-plugin-skills.cjs: build step converting commands/gsd/*.md
  to skills/gsd-<stem>/SKILL.md via convertClaudeCommandToClaudeSkill
- .claude-plugin/plugin.json: add "skills": "./skills/"
- package.json: add skills to files, gen:plugin-skills to build chain
- tests/issue-766-plugin-manifest.test.cjs: Section H conformance
  (manifest field + dir + frontmatter + count parity) + C2 skills symlink
- docs/adr/766-*.md: dated amendment adding skills surface row
- .changeset/rapid-bears-hum.md: type Added
- skills/: 69 generated gsd-<stem>/SKILL.md files (build-committed)

Closes #1596

2026-06-22 18:07:35 -04:00

3.3 KiB

Raw Blame History

name, description, argument-hint, allowed-tools

name

description

argument-hint

allowed-tools

gsd-plan-review-convergence

Cross-AI plan convergence - replan until review concerns are resolved.

<phase> [--codex] [--gemini] [--claude] [--opencode] [--ollama] [--lm-studio] [--llama-cpp] [--text] [--ws <name>] [--all] [--max-cycles N]

Read

Write

Bash

Glob

Grep

Agent

Skill

AskUserQuestion

Cross-AI plan convergence loop — an outer revision gate around gsd-review and gsd-planner. Repeatedly: review plans with external AI CLIs → if HIGH or actionable non-HIGH concerns remain → replan with --reviews feedback → re-review. Stops when no unresolved HIGH concerns or actionable MEDIUM/LOW findings remain outside PLAN.md, or when max cycles is reached.

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> @$HOME/.claude/gsd-core/workflows/plan-review-convergence.md @$HOME/.claude/gsd-core/references/revision-loop.md @$HOME/.claude/gsd-core/references/gates.md @$HOME/.claude/gsd-core/references/agent-contracts.md </execution_context>

<runtime_note> Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. Do not skip questioning steps because AskUserQuestion appears unavailable; use vscode_askquestions instead. </runtime_note>

Phase number: extracted from $ARGUMENTS (required)

Flags:

--codex — Use Codex CLI as reviewer (default if no reviewer specified)
--gemini — Use Gemini CLI as reviewer
--claude — Use Claude 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

Execute end-to-end. Preserve all workflow gates (pre-flight, revision loop, stall detection, escalation).

3.3 KiB Raw Blame History

3.3 KiB

Raw Blame History