Six-phase CLAUDE.md cleanup for a file that has grown too large. Phase 0 deletes what the repository itself answers. Phase A rotates old dated records into monthly archives with an index and a navigation header. Phase B consolidates recurring failure patterns into a Known Patterns section with current instance counts.…
Package and publish one local agent Skill, or audit and release a Registry-driven public Skill portfolio, as polished installable GitHub packages. Use when the user gives a SKILL.md, Skill directory, or multi-Skill repository and asks to open-source, publish, release, share, validate, detect drift, synchronize…
A file-based handoff process for two agents named Sol and Grok to implement and review coding tasks across separate conversations. It uses shared project files to record the next actor, task details, implementation notes, and review results.
A system for recording runtime failures as structured “noise cards,” which are saved notes about unexpected behavior and its cause. Unresolved cards can later be turned into regression tests, tests that prevent the same failure from returning.
Persistent knowledge base for Claude Code projects using the LLM Wiki methodology by Andrej Karpathy. Bootstraps a structured wiki (markdown files with cross-references) and configures Claude Code to maintain it automatically across sessions. Integrates with Obsidian via MCP for graph view and visual navigation. Use…
A strict legal auditor for the Algerian Law 18-07 & Law 25-11 amendments on personal data protection, image publication rules (ANPDP Délibération 04/2026), and data sovereignty.
Read and write wiremark, the text-based wireframe DSL rendered from fenced wireframe code blocks and .wiremark files. Use when creating, editing, or interpreting wireframes, screen sketches, screen flows, or low-fidelity UI mockups in markdown documents.
Refactor any skill by extracting deterministic operations into a Python script and slimming the SKILL.md to only AI judgment parts. Use when user says /codify, codify a skill, or optimize a skill.
Audit and optimize OpenAI Codex context locally, compile model and subagent profiles, detect capability drift, create redacted lockfiles, inspect model-visible prompt structure, and render honest token, credit, quota, or API-cost receipts. Use when the user explicitly invokes CtxWise or asks to run its installed CLI…
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize…
Use the sidecarsync CLI to read, update, and synchronize Sidecar notes or state in repos with .sidecar configurations. Covers peer selection, standalone repos, per-file rules, and fork recovery.
Two-phase normalize flow: extract hardcoded strings from source code into .contentrain/ (Phase 1) and patch source files with content references (Phase 2). Use when normalizing, extracting content, or replacing hardcoded strings.
A local knowledge search tool for finding project decisions, documents, and relationships between people, concepts, events, and other project items across previous sessions.
Recommends which Claude model and effort level to fit a task, using cost of error as the deciding signal. Use when asked which Claude model or effort to use, or a task feels over or underpowered.
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
Before you execute a drafted plan/spec/design doc, run a multi-agent adversarial cross-review to surface the flaws that cause downstream rework, aggregating "evidenced, cross-family-verified" objections into a verdict. Use when the user asks to "review this plan/spec", "can this approach be executed", "poke holes /…
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: