Debugging
Find and fix bugs, error analysis
documentation-manager
by jordanhubbard
A detail-oriented technical writer who keeps project documentation accurate,
decision-maker
by jordanhubbard
An analytical agent who resolves decision beads when other agents reach
engineering-manager
by jordanhubbard
A strategic, systems-thinking engineering leader who ensures project
remediation-specialist
by jordanhubbard
A meta-level debugging specialist who analyzes stuck agents, identifies systemic blockers, and implements fixes. Acts as Loom's self-healing mechanism.
project-manager
by jordanhubbard
An organized coordinator who tracks project progress, manages releases,
persona-name
by jordanhubbard
Brief description of what this persona does and when to use it (1-3 sentences, max 500 chars).
Project Guidelines Skill (Example)
by x-cmd
tdd-workflow/ - Test-driven development methodology
sec-audit-remediate
by parhumm
Generate security fixes from detect-dev findings with regression tests. Use when remediating security vulnerabilities.
frontend-patterns
by x-cmd
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
detect-writing
by parhumm
Writing system extraction with NNg tone dimensions, UI copy classification, and i18n maturity. Use when auditing content systems.
flow-status
by benkruger
"Show current SDLC phase, PR link, timing, and what comes next. Reads .flow-states/<branch>.json. Use any time you want to know where you are in the workflow."
ansible-debug
by sigridjineth
Use when playbooks fail with UNREACHABLE, permission denied, MODULE FAILURE, or undefined variable errors. Use when SSH connections fail or sudo password is missing.
managing-tech-debt
by liqiongyu
"Manage technical debt by producing a Tech Debt Management Pack (debt register, scoring/prioritization, refactor vs rewrite decision memo, incremental paydown plan, migration/rollback plan, metrics, and stakeholder cadence). Use for tech debt, refactoring, legacy modernization, and migrations."
ai-evals
by liqiongyu
"Create an AI Evals Pack (eval PRD, test set, rubric, judge plan, results + iteration loop). Use for LLM evaluation, benchmarks, rubrics, error analysis/open coding, and ship/no-ship quality gates for AI features."
flutter-review-request
by vp-k
Use when completing tasks, implementing major features, or before merging to verify Flutter code meets requirements
fastify-best-practise
by TheCodePace
Apply Fastify best practices when creating servers, plugins, routes, schemas, hooks, configuration, decorators, error handling, testing, and TypeScript integration. Use when writing or reviewing Fastify code, setting up a new Fastify project, or asking "How should I structure my Fastify app?"
better-stimulus
by obie
Apply Better Stimulus best practices for writing maintainable, reusable StimulusJS controllers following SOLID principles
mermaid-gen
by ajoslin
Generate syntactically correct Mermaid diagrams for technical documentation
bug-investigation
by nokonoko1203
Systematically investigate user-reported bugs and issues, generating detailed reports with root cause analysis, recommended fixes, symptom details, flow diagrams, error message mappings, code analysis, and prioritized fix proposals.
humanize-writing
by jpeggdev
Remove signs of AI-generated writing from text. Use when the user mentions 'sounds like AI,' 'too robotic,' 'humanize this,' 'make it sound human,' 'de-AI this,' 'sounds like ChatGPT,' 'make it natural,' or 'doesn't sound like a person wrote it.' Detects and fixes AI writing patterns including inflated significance, promotional language, formulaic structure, AI vocabulary, superficial analyses, vague attributions, hedging, robotic rhythm, em dash and boldface overuse, chatbot artifacts, and missing personality. Based on Wikipedia's "Signs of AI writing" guide and editorial best practices.
sveltekit-data-flow
by spences10
SvelteKit data flow guidance. Use for load functions, form actions, server/client data, and invalidation. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error(), invalidateAll().
sveltekit-structure
by spences10
SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.
svelte-template-directives
by spences10
Svelte template directives ({@attach}, {@html}, {@render}, {@const}, {@debug}). Use for DOM manipulation, third-party libs, tooltips, canvas, dynamic HTML. @attach replaces use: actions.
ai-testing
by CaliLuke
Guidelines for writing effective, robust, and maintainable tests. Use when writing unit tests, integration tests, debugging test failures, or setting up test doubles. Covers test design, assertions, fakes vs mocks, and debugging strategies.