stellarshenson/claude-code-plugins
Agent
Hostile red-team reviewer that tries to BREAK a change rather than approve it. The caller names one expert lens - architect, bug-hunter, qa-engineer, analyst, data-scientist, methodologist, ux-designer, tui, devops, popular-science, slop-hunter or ai-engineer - and the reviewer argues from it, returning a verdict line…
stellarshenson/claude-code-plugins
Command
Generate the baseline concern catalogue and scorecard from the devil persona - step 2 of the workflow.
stellarshenson/claude-code-plugins
Command
One improvement cycle - decide approach, apply changes, version, re-score, rename with residual - step 3 of the workflow.
stellarshenson/claude-code-plugins
Command
Build the devil's-advocate persona and harvest the fact repository for a target document - step 1 of the workflow.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Generate baseline devil's advocate evaluation. Produces concern catalogue with risk scores and scorecard. Requires setup to have been run first (devilsadvocate.md and factrepository.md must exist).
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Bridge between evaluate and iterate. Asks user how to address devil's concerns - user suggestions, auto-apply recommended options, or planning mode. Now integrated into iterate's Step 1 - use /devils-advocate:iterate directly.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Improve document based on devil's concerns, create versioned file, re-score, rename with residual. Clear 4-step workflow - improve, version, score, rename. Re-scores in place when user made changes outside Claude.
stellarshenson/claude-code-plugins
Skill Claude CodeCodex
Set up devil's advocate persona and fact repository for a target document. Use when starting a new critical analysis. Builds the devil persona (role, biases, triggers) and harvests verified facts from source materials.
stellarshenson/claude-code-plugins
Plugin Claude Code
Structured document processing: source grounding (lexical + semantic + NLI entailment), Bayesian calibration, uniformization, PDF manipulation, and validation. Process input documents into verified, quality-controlled outputs.
stellarshenson/claude-code-plugins
Command
Ground claims against source material with the grounding CLI - single claim, one document, or many via sourcemap.yaml.
stellarshenson/claude-code-plugins
Command
PDF toolkit - extract text/tables, create/merge/split, fill and flatten forms, OCR scanned PDFs, batch-process.
stellarshenson/claude-code-plugins
Command
Build a structured deliverable from input documents - analyze, draft, verify, uniformize, deliver.