Drop-in thinking-partner personality layer for Claude Code, Cursor, ChatGPT, and 20+ AI agent runtimes. MIT. Plaintext. Persistent memory. Framework-grounded. Calibration-disciplined.
This repository also configures its own agents. See what wick tells them →
Skill Claude Code
Detect when a task is being repeated often enough to be worth automating, then propose the right automation — a PROGRAM (deterministic script) or a SKILL (reusable judgment procedure). Analyzes the current session, the memory/ record, or an observation log; classifies program-vs-skill; estimates payoff; drafts the…
Skill Claude Code
Force base-rate thinking before a probability estimate. Identify reference class, historical rate, and adjust from there — not from intuition. Use before /calibrate or whenever you catch yourself or someone else estimating a probability from vibes.
Skill Claude Code
Extract structured fields from a source — paper, web page, API doc, or UI screenshot — and save a queryable record to memory/catalog/. Domain-agnostic. Use to build a personal index of things you'll want to find again, compare side-by-side, or reference in later decisions. Complements wick-research (which finds) and…
Skill Claude Code
Produce a one-paragraph narrative summary of a CHANGELOG.md version entry — suitable for release announcements, blog posts, or social copy. Preserves technical specifics (file paths, command names, counts) rather than vaguifying them. Defaults to the latest version; optionally takes a version like "v1.0.0". Refuses to…
Skill Claude Code
Review code or a pull request through Wick's 5 operational gates. Provides severity-classified feedback distinguishing required from nice-to-have. Use when reviewing PRs, before committing substantial changes, or for adversarial pressure on your own work.
Skill Claude Code
Reflective pass over memory/ files — flag duplicates, stale facts, conflicts, and consolidation candidates. Proposes edits, never applies without confirmation. Use monthly or when /audit flags drift.
Skill Claude Code
Make a Wick agent fully portable between machines — consolidate a host's auto-memory into the Wick memory/ layer, disable the shadow portably, and relativize all paths and tooling. Guided, gated, archive-don't-delete. Use when moving an agent to a new machine, or to converge a single-machine agent onto one governed…
Skill Claude Code
Adversarial critique of a plan, design, or decision — produce the 5 sharpest criticisms a hostile-smart opponent would raise. Complement to /steelman. Use before committing to a major decision or when you suspect you're too attached to a plan.
Skill Claude Code
Structured research on a topic — applies CRAAP test, source hierarchy (Tier 1-4), steel manning, and base-rate reasoning. Tags findings with confidence level. Use when closing memory/curiosity.md entries or before major decisions depending on external data.
Skill Claude Code
Security-focused code review — OWASP Top 10, secret leaks, auth flaws, injection, crypto misuse, dependency risk, and agentic-specific threats (prompt injection, memory poisoning). Use before production ship or after security-sensitive changes.
Skill Claude Code
Review code for reduction — find what can be removed, simplified, or deduplicated. Proposes fixes but never applies without confirmation. Use after finishing features, when files feel bloated, or when you suspect duplication.
Skill Claude Code
Summarize long content — document, paper, thread, or conversation — into a faithful TL;DR with key claims, action items, and flagged omissions. Use on long articles, meeting notes, papers, or prior-conversation compression.
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: