Explorar skills

Find, install, and configure an MCP server for a specific service. Handles discovery, installation, and verification.

Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the main context.

Convert a YouTube video transcript into Claude Code skills. Extracts tips, evaluates against selection criteria, and generates SKILL.md files with full transparency.

Post AI Thinking — unbiased solution space explorer. Strips inherited human heuristics, enumerates ALL possible approaches, then lets the user choose. No paradigm gets priority. Auto-calibrates depth: simple problems get a quick scan (3 paradigms), architectural decisions get the full space (7 paradigms, all phases). Existing solutions are fully included — if they fit best, use them. Invoke as: /p

Product pressure test before you build. Two modes: Startup (6 YC-style forcing questions that expose demand reality, status quo, target user, narrowest wedge, observation, and future-fit) and Builder (generative brainstorming for side projects, hackathons, and open source). Produces a design doc. Invoke when the user describes a new idea, asks whether something is worth building, or wants to press

Audit any system for human usability against Nielsen's 10 heuristics. Deterministic checklist — same 10 heuristics, same severity scale, same report structure every run. Works on UI screens, CLI flows, API response patterns, user journeys, component code, or any described interface. Invoke when user says "usability audit", "UX review", "heuristic evaluation", "audit for usability", "check this for

Use when about to emit a warning, flag, or alert for a LOW-confidence issue — the alert-fatigue / signal-credibility discipline. False alarms have an asymmetric cost: after repeated low-confidence warnings, the operator stops reading the channel, and the one true warning gets ignored. Fires on choosing a log level (warn vs info vs error), inflating a PR title/commit to "CRITICAL", marking speculat

Use when about to extract maximum present value from a RENEWABLE source in a way that degrades the source itself — the kill-the-source / unsustainable-extraction anti-pattern. Fires when about to max out an API rate limit or quota to ship one task faster (risks the access), flood the operator with low-priority pings (burns attention/trust budget), sacrifice maintainability for one task's throughpu

Use when, just after abandoning or failing at something, you catch yourself concluding "that wasn't worth reaching anyway" — the post-mortem self-deception / motivated-reasoning anti-pattern. Fires when writing a post-mortem after a failure or rollback, recording a lesson after a retreat, or when an operator/agent's stated reason for quitting smells like comfort rather than analysis. The tell: a g

Scan the codebase for AI-generated slop in comments and docstrings — temporal markers, self-referential AI framing, narrative WHAT-comments, marketing padding — and propose tightened rewrites, routing claim-bearing docstrings that need a code-grounded rewrite to its sibling /techne:reslop. Use when the user wants to audit pending changes or the whole codebase for verbose, low-value commentary left

Audit a plan's design decisions — library, framework, pattern, and architecture choices in IMPL.md / ROADMAP.md — for missing `# research(YYYY-MM):` provenance, then web-search to ground them. Use when you want architectural choices verified against current best practice before they harden into code, rather than resting on training-cutoff recall. Catches committed decisions stated as fact but neve

Run an observed live dev session — Claude drives an interactive REPL in a named tmux session, the human spectates read-only via `tmux attach -r`. Use when the user wants to play through, debug, or explore a service's REPL together. Trigger phrases include "let's do a live smoke", "run a theoros session", "I want to spectate while you drive the CLI", "start an observed dev run". Reads per-repo fact