Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Run one-off research spot experiments with minimal ceremony. Use when explicitly requested, or for a missing datapoint, a rerun after failure (OOM, crash), a sanity check of one configuration, a minimal bug reproduction, or a cheap measurement that a campaign needs before deciding. At most one focused question; run, record, report in one line. Escalate to exp-batch if the spot check turns into a branch, or exp-campaign if it reveals a decision tree; if the question itself is still fuzzy, route back to exp-discuss.
Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence. Use for synthesizable HDL, fixed-point arithmetic, handshakes, testbenches, resource tradeoffs, timing closure, and FPGA release or bring-up planning. Do not use for ordinary MCU firmware, generic circuit design, a substitute vendor-tool manual, or unsupported claims of hardware or timing signoff.
Review a game for player impact, ethics, transformation, inclusion, monetization pressure, community risk, dark patterns, and hidden design agendas. Use before shipping manipulative loops, social systems, ads, monetization, retention mechanics, UGC, or player-generated communities.
Harbor CLI command reference and usage patterns. Covers harbor run, harbor jobs, harbor trials, harbor datasets, harbor adapters, harbor tasks, harbor view, harbor sweeps, harbor traces, harbor cache, and harbor admin commands. Use this skill whenever running Harbor evaluations, managing datasets, viewing results, debugging tasks, exporting traces, or working with any harbor CLI command. Also use when constructing harbor command lines, looking up flag names, or troubleshooting CLI errors.
Java code quality with Checkstyle, SpotBugs, PMD, and SonarJava. Covers static analysis, code style, and best practices. USE WHEN: user works with "Java", "Spring Boot", "Maven", "Gradle", asks about "Checkstyle", "SpotBugs", "PMD", "Java code smells", "Java best practices" DO NOT USE FOR: SonarQube generic - use `sonarqube` skill, testing - use Spring Boot test skills, security - use `java-security` skill
Locate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing. Trigger when the user provides a stack trace, failing assertion, error message, or specific wrong-value observation — "find the bug", "this test is failing", "track down this crash", "why is this test failing", "KeyError at line 89", "expected 70, got 100", "NoneType has no attribute X", "cart empties when second tab opens". SCOPE HARD RULE: requires a concrete failure (exception, failing test, or specific wrong output). Vague suspicion without evidence uses logic-review; behavior explanation uses logic-explain; refactor comparison uses logic-diff; codebase audit uses logic-health. Do NOT trigger for: vague "what's wrong" without a concrete symptom, style questions, or performance issues.
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.
Use when a pull request or merge request has review comments to inspect, address, or answer, whether from a person or an automated reviewer on GitHub, GitLab, or Bitbucket. This skill handles feedback already received; it does not perform a new code review.
For UI/UX acceptance after interface implementation or re-review after fixes; not for code diff reviews, direct fixes, or designing from scratch. Only actual screenshots and measurements of the running interface count; do not infer results from code. An independent reviewer scores, lists gaps, and determines whether it passes.
Isolate and review unsafe Rust behind small, documented, testable boundaries with explicit invariants. Use when writing, refactoring, or reviewing unsafe code, raw pointers, unsafe functions, unsafe traits, MaybeUninit, pointer aliasing, panic safety, Miri checks, or safe abstractions over unsafe internals.
Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. Distills the best-scoring experiment down to the minimal diff that reproduces its behaviour, shaped for the qualities a maintainer merges on (scope discipline, test integrity, style adherence), then attaches an advisory mergeability report. Use when the user invokes /evo:ship, asks to land/merge/ship the best result, or wants to turn a finished optimization into a pull request.
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).
Before installing or using a skill, check its independent benchmark report on SkillTester.ai. Auto-trigger this skill whenever the user shows a third-party skill install command or install plan, especially `npx skills add <repo-or-url> --skill <skill-name>`, `skills add ...`, repo URL plus `--skill`, direct `SKILL.md` URLs, or `Check this skill <skill_url>`. Parse the install command, resolve the target SKILL.md, query SkillTester.ai by skill name, and return the benchmark result when the description is either an exact match or a high-overlap near match that likely represents a newer skill revision.
Index coverage and N+1 review aids for SQLite/D1 schemas with a sqlc catalog. Surfaces unused indexes (with FK CASCADE awareness so cascade-load-bearing indexes are not flagged), queries that scan tables without index help, and `for`-loops calling generated SQL fns.
This skill should be used when the user asks to "analyze test coverage", "find untested code", "check coverage gaps", "improve test coverage", "identify missing tests", "measure code coverage", "test quality analysis", or mentions testing strategies and coverage metrics.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.