Collects the syntax rules and failure modes that trip up PowerShell scripting on Windows -- operator grouping, ASCII-only output, null guards, JSON depth, and error-handling structure. It pairs each pitfall with the corrected form so scripts run reliably under Set-StrictMode. Use it when authoring or debugging…
Designs production prompts for LLM-powered features — clear instructions, role/system prompts, few-shot examples, structured output schemas, delimiter structuring, and reasoning strategy. Use when building or debugging an LLM feature (extraction, classification, generation, agents), when output is inconsistent or…
Guides Python design decisions -- framework choice, async-vs-sync, typing strategy, project layout, and error handling -- by reasoning from the project's needs rather than copying snippets. It explains when async helps, when Pydantic earns its place, and how to keep logic out of the view layer. Use it when writing…
Guides an engineer or agent through ingesting code-review feedback and revising well — triaging comments into must-fix, nit, and question, replying to each without defensiveness, grouping related changes, pushing back with evidence when warranted, and re-requesting review. Use when a pull request has review comments…
Organizes adversary-simulation work around the MITRE ATT&CK lifecycle -- recon, access, escalation, evasion, lateral movement, and impact -- with the goal of exposing detection gaps. It pairs each phase with objectives and emphasizes scope, minimal impact, and reporting. Use it when scoping a penetration test, running…
Covers production Rust on the 2024 edition -- ownership and lifetimes, async with Tokio, the trait and type system, performance work, and safe handling of unsafe and FFI. It leans on current ecosystem crates (axum, tower, sqlx, serde, thiserror) and idiomatic error handling. Use it when building Rust services or…
Core search-engine optimization guidance spanning the E-E-A-T quality signals, Core Web Vitals, technical foundations like sitemaps and canonicals, on-page content and meta elements, schema markup, and ranking priorities. Use it when optimizing pages for search, writing title and meta tags, strengthening trust…
Frames production server operations as decisions -- which process manager to run, what to monitor and alert on, how to handle logs, and when to scale up versus out. It reasons from symptoms and goals rather than reciting commands, and includes a triage order for incidents. Use it when keeping a service running…
Cuts away accidental complexity from working code by deleting dead branches, collapsing needless layers of indirection, un-nesting control flow, and reducing parameter lists, all while keeping observable behavior identical. Applies when a file feels over-built, more abstract than its single use justifies, or harder to…
Turns a recurring, multi-step way of working into a packaged, reusable SKILL.md that any agent can later discover and follow. Fits when the same kind of request has come up several times, when a procedure has enough stable steps to be worth recording, or when someone explicitly asks to capture a workflow as a skill.…
Drives a feature through three approved artifacts — requirements, design, then tasks — before any code is written, enforcing a left-to-right gate so design is settled before implementation. Use when starting a non-trivial feature, a multi-file change, or anything ambiguous, fuzzy, or risky. Maps the workflow onto…
Provides a disciplined, evidence-first method for tracking down stubborn defects, moving from reliable reproduction to isolation, then to a proven root cause, and finally to a verified fix. Suited to bugs that resist quick guesses, intermittent or environment-specific failures, and regressions where the cause is not…
Captures the way Tailwind CSS v4 is meant to be used, where configuration lives in CSS through the @theme directive, the Rust-based engine compiles utilities, and tokens surface as CSS custom properties. Useful when setting up or migrating a v4 project, defining a design-token system, reaching for container queries…
A taste filter for marketing-style web work (landing pages, portfolios, and redesigns) that fights generic, machine-generated "design" output. The agent reads the brief first, commits to a deliberate direction, and ships interfaces that look authored rather than templated. It reaches for genuine design systems when…
Lays out test-driven development as a repeating loop, where a failing test is written first, the smallest code that satisfies it comes next, and a cleanup pass follows once the test is green. Applies when building a new feature, fixing a bug by first capturing it as a failing test, or working through logic intricate…
Guidance for building dependable test suites, covering the test pyramid, the arrange-act-assert structure, when to pick unit versus integration versus end-to-end tests, mocking strategy, test organization and naming, and test-data techniques. Use it when writing or reviewing tests, choosing a testing approach or…
Runs parallel work in isolated git worktree checkouts that share one repository, then merges results back. Use when several agents or tasks would otherwise collide in a single working tree, when a hotfix is needed mid-feature without stashing, or when comparing two branches side by side. Covers adding, listing…
Establishes that a code change actually behaves correctly by running it and observing real output, rather than concluding it works from reading the source or trusting that it compiles. Applies right after writing a feature, fixing a bug, or refactoring, and whenever someone asks whether a change works, to test it, or…
A structured method for security review that combines an attacker mindset with the OWASP Top 10 (2025), supply-chain risk, attack-surface mapping, exploit-aware risk ranking, and code-pattern and secret analysis. Use it when scanning a project for vulnerabilities, checking OWASP alignment, assessing dependency and…
Audits front-end UI code against an external, regularly updated set of web interface guidelines covering accessibility, usability, and interaction quality, then reports each issue in a compact file-and-line format. Fits when reviewing existing UI for best-practice compliance, checking accessibility, or auditing UX…
An approach to testing web applications end to end, covering route and endpoint discovery, the web testing pyramid, Playwright practice, visual regression, API coverage, test layout, and CI integration. Use it when writing Playwright E2E tests, auditing a web app for untested routes, exercising user flows, or wiring…
Initialize and sync the AIM project workspace context.
★not rated 1 3mo agoA8 tokens
originalMIT
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: