Formalswarm Verdict — Development skill for Claude Code
Read the last FormalSwarm outcome and decide whether it may be applied.
How to install Formalswarm Verdict
Installs to ~/.claude/skills/fashionmascherine-svg-formalswarm-formalswarm-verdict/SKILL.md
mkdir -p ~/.claude/skills/fashionmascherine-svg-formalswarm-formalswarm-verdict && curl -fsSL https://raw.githubusercontent.com/fashionmascherine-svg/formalswarm/HEAD/commands/formalswarm-verdict.md -o ~/.claude/skills/fashionmascherine-svg-formalswarm-formalswarm-verdict/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Formalswarm Verdict does
description: Read the last FormalSwarm outcome and decide whether it may be applied
FormalSwarm — read the verdict
Find the newest `outcome.json` (under `.formalswarm/scratch/`) and report it without embellishment:
| Report | From |
|---|---|
| outcome | global_verdict.outcome: CONFIRM / REVISE / INCONCLUSIVE |
| reason | global_verdict.reason |
| warnings | global_verdict.warnings — quote every one |
| objections | objection_count (accepted / rejected / unanswered / t |
Alternatives in Development
- Outcome — /outcome - Record the Result of an Application 36.6k ★
- Outcome Roadmap — Transform output roadmaps into outcome-focused strategic plans 7.8k ★
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Verbose Status
Show whether a Genesis agent's APPLIED-EXPERTISE declarations are DISPLAYED (verbose on) or recorded quietly (
Docsmith Render Triage
Triage a docsmith render failure: read the captured error, decide whether it's a content bug (the source docum
Verify Render
Download a rendered Poppify reel, run ffprobe + frame extract, surface a verdict on whether the render matches
Auto Continue
You are the auto-continue gate for Omux's Main Agent. The Main Agent has just finished a turn and is about to
Self Evolution Triage
Decide whether a trace should stop, distill memory, revise a command, or revise a skill.
Tastecheckpass
Decide whether finished frontend work can ship, with evidence
Related Agents
Security Triage
Independently evaluate a single security finding to decide whether it is a real, exploitable vulnerability or
Skill Applied Judge
Use this agent at session-end Phase 3.6.6 (#645 L3) to judge — from the session transcript tail — whether each
Robin
Read-only, skeptical evidence auditor for a Superloopy criterion. Use to judge whether Superloopy's determinis