Skill0 repo starsupdated yesterday

mindforge-review

The mindforge-review skill invokes external AI command-line interfaces (Gemini, Claude, Codex) to independently evaluate phase plans and produces a structured REVIEWS.md file containing per-reviewer feedback. Use this skill when you need cross-AI validation of planning phases before proceeding, optionally feeding the compiled reviews back into planning refinement via the /mindforge-plan-phase --reviews flag.

View source Repository: MindForge

Install in Claude Code

Copy

git clone --depth 1 https://github.com/sairam0424/MindForge /tmp/mindforge-review && cp -r /tmp/mindforge-review/.agent/skills/mindforge-review ~/.claude/skills/mindforge-review

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

<objective>
Invoke external AI CLIs (Gemini, the agent, Codex) to independently review phase plans.
Produces a structured REVIEWS.md with per-reviewer feedback that can be fed back into
planning via /mindforge-plan-phase --reviews.

**Flow:** Detect CLIs → Build review prompt → Invoke each CLI → Collect responses → Write REVIEWS.md
</objective>

<execution_context>
@.agent/workflows/mindforge-review.md
</execution_context>

<context>
Phase number: extracted from $ARGUMENTS (required)

**Flags:**
- `--gemini` — Include Gemini CLI review
- `--claude` — Include the agent CLI review (uses separate session)
- `--codex` — Include Codex CLI review
- `--all` — Include all available CLIs
</context>

<process>
Execute the review workflow from @.agent/workflows/mindforge-review.md end-to-end.
</process>