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 yesterday A 43 tokens
original MIT
10Stars on the repository
188Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
dedupe-apply
26Command 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 yesterday 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 yesterday A 38 tokens
original MIT
dedupe-setup
28Command 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 yesterday 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 yesterday 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 yesterday A 19 tokens
original MIT
Command Claude Code
Phase 1 of deep-research: Thread decomposition, source strategy, and convergence criteria.
not rated 10 yesterday 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 yesterday A 43 tokens
original MIT
Command Claude Code
Structured design exploration that evaluates approaches and trade-offs before implementation. Explores requirements and design through interactive or synthesis modes.
not rated 10 yesterday A 23 tokens
original MIT
docs-audit
34Command Claude Code
Phase 1 of documenting-projects: Project analysis for documentation planning. Triggers: '/docs-audit', invoked by documenting-projects orchestrator.
not rated 10 yesterday A 30 tokens
original MIT
docs-plan
35Command Claude Code
Phase 2 of documenting-projects: TOC generation, tone assignment, and build config. Triggers: '/docs-plan', invoked by documenting-projects orchestrator.
not rated 10 yesterday A 34 tokens
original MIT
docs-review
36Command Claude Code
Phase 4 of documenting-projects: Quality gate with 8 measurable criteria and iteration. Triggers: '/docs-review', invoked by documenting-projects orchestrator.
not rated 10 yesterday A 33 tokens
original MIT
docs-write
37Command Claude Code
Phase 3 of documenting-projects: Generate documentation with adaptive tone per section. Triggers: '/docs-write', invoked by documenting-projects orchestrator.
not rated 10 yesterday A 31 tokens
original MIT
Command Claude Code
Phases 6-7 of estimating-tickets. PERT three-point estimation per ticket + Brooks's Law resource scaling.
not rated 10 yesterday A 25 tokens
original MIT
Command Claude Code
Phases 4-5 of estimating-tickets. Multi-agent consensus pointing per ticket + AI productivity multiplier.
not rated 10 yesterday A 22 tokens
original MIT
Command Claude Code
Phase 8 of estimating-tickets. Produce the final structured estimation report.
not rated 10 yesterday A 15 tokens
original MIT
Command Claude Code
Phase 1-3 of estimating-tickets. Ingest the test card, validate external-domain constraints, build a structural repo map, decompose into tickets tagged by repo.
not rated 10 yesterday A 35 tokens
original MIT
execute-plan
42Command Claude Code
Execute implementation plans with structured review checkpoints. Use when you have a plan document and want faithful, evidence-based execution.
not rated 10 yesterday A 23 tokens
original MIT
Command Claude Code
Execute a single work packet: verify dependencies, run TDD task loop through three gates, write completion marker.
not rated 10 yesterday A 22 tokens
original MIT
Command Claude Code
Phases 2-3 of fact-checking: Claim Extraction and Triage.
not rated 10 yesterday A 16 tokens
original MIT
Command Claude Code
Phases 6-7 of fact-checking: Report Generation and Learning.
not rated 10 yesterday A 15 tokens
original MIT
Command Claude Code
Phases 4-5 of fact-checking: Parallel Verification and Verdicts.
not rated 10 yesterday A 16 tokens
original MIT
Command Claude Code
Phase 0 of develop: Configuration wizard, escape hatches, preferences, continuation detection.
not rated 10 yesterday A 17 tokens
original MIT
Command Claude Code
Phase 2 of develop: Create and review design document.
not rated 10 yesterday A 11 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: