Command Claude Code
Phase 4 of auditing-green-mirage: Cross-test suite-level analysis.
not rated 10 2d ago A 15 tokens
original MIT
Command Claude Code
Phase 5-6 of auditing-green-mirage: Findings report generation and output.
not rated 10 2d ago A 17 tokens
original MIT
Command Claude Code
Audit mode for code-review: multi-pass deep-dive with zero-tolerance posture, API hallucination detection, and risk assessment.
not rated 10 2d ago A 25 tokens
original MIT
Command Claude Code
Feedback mode for code-review: Process received review feedback with categorization, decision rationale, and response templates.
not rated 10 2d ago A 20 tokens
original MIT
Command Claude Code
Give mode for code-review: Review someone else's code with multi-pass analysis and structured recommendations.
not rated 10 2d ago A 17 tokens
original MIT
Command Claude Code
Tarot integration for code-review: Roundtable dialogue with archetype personas for all review modes.
not rated 10 2d ago A 18 tokens
original MIT
create-issue
31Command Claude Code
Create a GitHub issue with proper template discovery and population.
not rated 10 2d ago A 11 tokens
original MIT
create-pr
32Command Claude Code
Create a pull request with proper template discovery and population.
not rated 10 2d ago A 10 tokens
original MIT
Command Claude Code
Operator-invoked rule bookkeeping for canonical ## Rules sections produced by /crystallize. Use when accumulated rules need consolidation (overlap merge, redundancy collapse, deprecated-tool retirement). Triggers: '/crystallize-consolidate ', 'consolidate the rules section', 'merge overlapping rules in this file'. NOT…
not rated 10 2d ago A 105 tokens
original MIT
Command Claude Code
Adversarial review of a crystallized document against its original. Use when crystallize.md invokes pre-delivery verification. Receives original + crystallized documents; returns PASS or FAIL with findings.
not rated 10 2d ago A 39 tokens
original MIT
crystallize
35Command Claude Code
Transform verbose SOPs into high-performance agentic prompts via principled compression. Use when user says "/crystallize", "compress this prompt", "make this more agentic".
not rated 10 2d ago A 36 tokens
original MIT
Command Claude Code
Extract, triage, and verify code items for dead code. Part of dead-code- family. Run after /dead-code-setup.
not rated 10 2d ago A 28 tokens
original MIT
Command Claude Code
Implement dead code deletions with user approval. Part of dead-code- family.
not rated 10 2d ago A 16 tokens
original MIT
Command Claude Code
Generate dead code findings report with implementation plan. Part of dead-code- family.
not rated 10 2d ago A 16 tokens
original MIT
Command Claude Code
Git safety and scope selection for dead code analysis. Part of dead-code- family.
not rated 10 2d ago A 17 tokens
original MIT
Command Claude Code
Decompose text into atomic, independently verifiable claims using FActScore-style analysis. For text and documentation claims only; code claims use inline verification.
not rated 10 2d ago A 30 tokens
original MIT
Command Claude Code
Phase 2 of the dedupe skill family. Narrows candidate pairs through an 8-stage pipeline and dispatches per-pair classifier subagents. Run after /dedupe-setup.
not rated 10 2d ago A 43 tokens
original MIT
dedupe-apply
42Command Claude Code needs its repo
Phase 4 of the dedupe skill family. Applies operator-approved EXTRACT findings with HTML-comment-fenced JSON journaling and supports deterministic rollback. Run after /dedupe-report.
not rated 10 2d ago A 41 tokens
original MIT
Command Claude Code needs its repo
Phase 3 of the dedupe skill family. Aggregates verdicts into a human-readable report and drives per-finding disposition approval. Read-only; no file mutations.
not rated 10 2d ago A 38 tokens
original MIT
dedupe-setup
44Command Claude Code
Phase 1 of the dedupe skill family. Resolves seed paths, applies the block-segmentation protocol, and emits the blocks manifest. Run before /dedupe-analyze.
not rated 10 2d ago A 42 tokens
original MIT
Command Claude Code
Phase 0 of deep-research: Structured interview and Research Brief generation. Transforms raw research requests into research-ready briefs with disambiguation, assumption extraction, and scope boundaries.
not rated 10 2d ago A 36 tokens
original MIT
Command Claude Code
Phase 2 of deep-research: Triplet search engine with plateau detection and micro-report generation.
not rated 10 2d ago A 19 tokens
original MIT
Command Claude Code
Phase 1 of deep-research: Thread decomposition, source strategy, and convergence criteria.
not rated 10 2d ago A 17 tokens
original MIT
Command Claude Code
Generate assessment frameworks (dimensions, severity levels, verdicts, finding schemas) for evaluative skills and commands. Use when creating skills/commands that produce evaluative output, or when user says '/design-assessment'.
not rated 10 2d ago A 43 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: