clankbrain

Scans a real codebase and writes coding-conventions.md from what it actually finds — variable style, SQL patterns, error handling, INSERT strategy, naming. Run once on any new project to bootstrap the convention system. Triggers on "scan conventions", "generate conventions", "bootstrap conventions", "extract conventions from code", "what are the conventions".

Security audit — checks auth, SQL injection, exposed endpoints, and sensitive data. Triggers on "security check", "is this secure", "check for vulnerabilities", "check auth", "audit security", "security audit".

Use when switching environments, updating config values, or verifying URLs/settings. Triggers on "check environment", "switch to production", "update URLs", "check config", "is this prod-ready".

Use when verifying a feature works, after making changes, or before shipping. Triggers on "verify this works", "test this", "does this work", "run the checklist", "before I ship", "check this end to end".

Use when cleaning up, simplifying, or restructuring existing code without changing behavior. Triggers on "refactor", "clean up", "simplify this", "this is getting messy", "too long", "hard to read", "extract this".

Use when the user wants to review a file for bugs, antipatterns, or quality issues. Triggers on "review", "check for issues", "look for problems", "audit", "before I ship".

Use when the user reports a LOGIC bug — wrong behavior, incorrect output, or a feature not working as designed. Triggers on "fix the bug where", "it's broken", "not sending", "not saving", "wrong result", "something broke".

Commits to a bold design direction before writing a single line of CSS. Generates a complete design system — palette, font pairing, style direction, and UX rules. Triggers on "build a landing page", "design this UI", "create a component", "design system for", "new page design", "frontend design".

Scans recently changed files against a growing library of known error patterns, flags violations before they ship. After any bug fix, extracts the root cause as a new permanent rule. Trigger on "guard check", "scan for issues", "check conventions", "did I miss anything", "scan my changes".

Tactical rules for making interfaces look intentional and polished. Specific, actionable fixes for the most common visual problems. Triggers on "my UI looks off", "fix the design", "visual hierarchy", "polish the UI", "refactoring ui".

Developer sharpening exercise — user writes the implementation first, Claude reviews and compares. Keeps independent coding ability sharp. Triggers on "/shadow-code", "shadow mode", "I'll write it first", "let me try first".

Create a new reusable skill from scratch. Triggers on "create a skill", "new skill", "make a skill called", "add a skill for", "/skill-creator".

Reads STATUS.md, todo.md, and recent memory to identify what was in progress, then proposes and executes the specific next step. Use when resuming work after a break, or say "smart resume" / "pick up where we left off" / "what were we working on" / "what's next".

Evaluates interface usability using Nielsen's 10 heuristics + Krug's principles. Returns a severity-scored list of issues. Triggers on "audit this for usability", "heuristic review", "UX issues", "usability check", "ux heuristics".

Confirms the Clankbrain install worked. Run this right after setup or anytime you suspect something is broken. Triggers on "kit health", "is the kit installed", "kit check", "did install work", "verify kit", "health check kit".

A 5-minute interactive walkthrough of Clankbrain. Shows the user the magic — memory, lessons, regret log, plans — by demonstrating each one in real time. Triggers on "tour", "show me how this works", "walkthrough", "first time", "new user", "show me the magic".

Four Big Risks product validation. Two modes: evaluate (score an existing product Red/Yellow/Green) or create (validate idea + generate working prototypes + full project scaffolding). Triggers on: /product-risk, evaluate this product, validate this idea, new product, is this worth building, product risk check, run the four risks, score this product, check the risks, rate this idea, should I build this, what are the risks, risk assessment, check for product-risk, how risky is this.

Run 2-3 prototype variants of a UX decision in parallel instead of iterating sequentially. Cagan calls this the "freshest observation" enabled by AI tooling. Triggers on "should it be X or Y", "two approaches", "I'm torn between", "try both", "parallel prototypes", "compare designs", "A/B this".

Force a one-line hypothesis before any prototype iteration. Prevents "learning theater" — building things that demo well but don't reduce risk. Triggers on "iterate on the prototype", "let me try", "tweak the design", "change the [color/layout/copy]", "what if we", or any prototype edit in build-to-learn mode.

Structured debugging flow for any bug or unexpected behavior. Follows reproduce → isolate → hypothesize → fix → verify → log. Ends by updating error-lookup.md so the same bug never costs time again. Triggers on "debug session", "can't figure out why", "weird behavior", "something's wrong with", "why is X not working", "help me debug".

Scan this project's error history and codebase to propose project-specific guards for guard-patterns.md. Generic guards ship with the kit — this skill creates the ones that prevent YOUR recurring mistakes. Trigger phrases: "generate guards", "add guards", "create project guards", "what guards should I add", "guards from my errors".

Natural language memory search. Use when the user asks "what did we decide about X", "do we know anything about X", "have we dealt with X before", or "/recall X". Faster than search-memory — single grep pass, no parallel agents.

Invalidate or remove a memory entry. Use when the user says "forget that", "that memory is wrong", "remove the X memory", "/forget X". Marks the file as invalidated rather than deleting — preserves history.

Reads recent session context, infers what you were working on, and proposes the specific next action. Use when resuming after a break, or say "act" / "what should we do next" / "pick up where we left off". Executes immediately on confirmation.

Deep cross-memory search using parallel subagents. Use when asked broad conceptual questions like "what do we know about X", "have we solved X before", "find anything about X" — questions that could live in multiple memory files. Simple lookups (single known file) still use --search directly.

Switch Claude's tool access mode for the session. Modes limit which tools Claude will use — useful for reviewing code without risk of edits, or ensuring no shell commands run. Triggers on "Mode develop", "Mode review", "Mode safe", "Mode deploy", "/mode", "switch to review mode", "read only mode", "safe mode".

Structured planning session for a new feature or change. Creates a dedicated plan file, drafts options with build cost/friction/payoff ratings, tracks the decision live. Triggers on "plan [feature]", "I want to build X", "design X", "plan mode", "thinking about building".

Language-agnostic code review. Checks correctness, security, and consistency with project conventions. Triggers on "review this", "review [file]", "check this code", "code review".

Analyzes the project codebase and builds a detailed code-map.md organized by feature flow. Shows entry point → routing → logic → DB for every major feature. Run once to bootstrap navigation; re-run after major structural changes. Triggers on "map the codebase", "build code map", "create code map", "map my project", "analyze codebase structure", "create a roadmap of the code", "where does everything live".

Enforce safe PowerShell string patterns before writing or editing any .ps1 file, or before passing PowerShell via the Bash tool. Triggers on "write a powershell script", "edit the .ps1", "run powershell", "powershell command", or any task that produces PowerShell content.