Documentation Wizard
codexAudits documentation against verified code interfaces and generates evidence-backed drift reports.
1 skill
Global research assistant plugin for statistical, scientific, implementation, and robustness review of analysis repositories.
Plugin research-partner in nicholas-camarda/codex-personal-plugins. Commands read from the repo's manifest — 1 month ago.
assess-literature-supportUse when method choices need literature and practical support assessed against the actual scientific question, data, and implementation.
design-robustness-testsUse when an analysis needs tests that catch scientifically meaningful implementation, estimand, data, or artifact regressions.
inspect-analysis-artifactsUse when analysis inputs, outputs, code paths, runtime artifacts, and published outputs must be reconstructed before review.
research-partnerUse when a research analysis, manuscript claim, repository, or pipeline needs a data-first multi-lane review grounded in local artifacts.
review-documentation-consistencyUse when manuscripts, READMEs, methods prose, or operational docs must be checked against live code, schemas, and paths.
review-implementation-validityUse when code must be checked against the claimed method, target estimand, generated outputs, and repository workflow.
review-scientific-interpretationUse when claims, interpretation, bias, or generalizability must be reviewed against the actual cohort, design, and measurements.
review-statistical-validityUse when statistical methods must be checked against the actual design, data structure, outcome, and claimed question.
synthesize-reviewUse when specialist lane outputs need to be merged into one ranked final review with evidence and disagreements preserved.
Audits documentation against verified code interfaces and generates evidence-backed drift reports.
1 skill
Audits canonical workspace layout, reports rewrite candidates, and performs backup-first verified moves.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.