A conversational package manager for Claude Code skills — search, install, update and remove skills from the CCPM registry without typing CLI commands.
Verifies factual claims in your documents against authoritative sources and applies corrections only after your approval.
Teaches Claude to read, merge, split, extract tables from, OCR and generate PDFs with Python and CLI tools.
An adversarial review skill that forces Claude into three hostile reviewer personas so 'LGTM' is never an option.
A prompt-engineering skill that detects your target AI tool and returns one paste-ready prompt tuned to that tool's quirks.
Runs a blameless after-action review of an incident, launch, or finished project and outputs a full report with timeline, root cause, and owned action items.
Runs a structured, blameless postmortem or retrospective on an incident, launch, or finished project and produces a report with timeline, root cause, and owned action items.
Reviews a diff or file purely for what can be deleted or simplified — over-engineering, speculative abstractions, and reinvented stdlib.
Runs a forensic, evidence-cited scan of any text across nine AI-tell categories and returns a 0–27 score with a verdict and fixes.
Searches your cmem.ai persistent memory with a cheap-to-expensive, three-pass method to recover context from past sessions.
Official skill that drafts internal communications — 3P updates, newsletters, FAQs, incident and leadership reports — using your company's preferred formats.
Triages the 37signals 38-question decision guide down to 6–8 load-bearing questions, forces a clear call, and archives the rationale with a revisit date.
Pick from 10 curated color/font themes — or generate a custom one — and apply it consistently across slides, docs, and HTML pages.
Forces a collaborative requirements interview, 2–3 alternative designs, and a committed spec document before any code is written.
Reads your 401k paperwork and converts fund fees, match fine print, and vesting rules into concrete dollars-over-time math.
Builds a complete 360-degree feedback survey instrument, or turns raw reviewer notes into a structured feedback report.
Converts a raw git log into grouped, user-facing release notes with a headline and migration note.
Detects your project's stack and auto-configures lint, typecheck, test and format quality gates plus a Claude settings file.
A safety net that preserves your task state and key files across Claude Code context compaction cycles.
Installs, switches, and debugs the Claude Code statusline with one script, two layouts, and a four-layer self-verification health check.