Top Agent Skills

Expert en revue de code (PR reviews, patterns, anti-patterns, security, performance, readability)

Trata o saneamento e a organizacao do processo (CPC 357): resolucao das questoes processuais pendentes, fixacao dos pontos controvertidos, delimitacao das questoes de direito relevantes, distribuicao do onus da prova (357 II c/c 373 §1 — distribuicao dinamica) e definicao das provas a produzir e da audiencia de instrucao. Cobre o saneamento compartilhado (357 §3) e o pedido de esclarecimento/ajuste em 5 dias (357 §1). Use quando o operador disser saneamento, decisao de saneamento, pontos controvertidos, organizacao do processo, distribuicao do onus da prova, ou houver despacho saneador a impugnar/cumprir.

Define o estilo juridico das pecas civeis do plugin — peticoes iniciais, contestacoes, replicas, recursos, manifestacoes, razoes. Use sempre que outra skill for redigir um texto civel, para garantir tom, estrutura, enderecamento e terminologia processual corretos. Acionada internamente pelas skills de redacao.

Redige a replica do autor e cobre as providencias preliminares (CPC 350-353): manifestacao sobre as preliminares e os documentos juntados com a contestacao, e impugnacao dos fatos impeditivos/modificativos/extintivos alegados pelo reu (350 — prazo 15 dias). Trata tambem a hipotese das materias do 337 (351). Use quando o operador disser replica, manifestacao sobre contestacao, impugnar a contestacao, providencias preliminares, o reu juntou documentos, ou houver prazo para o autor falar apos a defesa.

Redige acao de reparacao de danos por responsabilidade civil — ato ilicito (CC 186) e abuso de direito (CC 187), dever de indenizar (CC 927) com responsabilidade objetiva pela atividade de risco (927 par. unico), extensao do dano e reducao equitativa (CC 944 + par. unico), perdas e danos / lucros cessantes / juros de mora (CC 402-405), danos por homicidio, lesao a saude e ofensa a honra (CC 948-954), distinguindo dano material x moral x estetico x lucros cessantes x perda de chance, pelo rito comum (CPC 319) com tutela se cabivel. Use quando o operador disser quero indenizacao, danos morais, fui lesado, acao indenizatoria, reparacao de danos.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Use this skill when the user asks about DOT audits, FMCSA compliance reviews, new entrant safety audits (NESA), focused investigations, what auditors actually ask for, audit document checklists, common audit failures, the audit ratings (Satisfactory / Conditional / Unsatisfactory), or how to prepare for an upcoming audit. Cite 49 CFR 385.

Use this skill when the user asks about CMV oilfield operations — the 24-hour restart exemption (49 CFR 395.1(d)), oilfield-specific HOS rules, hot oil hauling, specialty equipment (winch trucks, kill trucks, frac sand haulers, water haulers), Texas Railroad Commission permitting, oilfield insurance specifics, and how oilfield operations differ from standard OTR trucking. Cite 49 CFR 395.1(d).

Use this skill when the user asks the cost of pulling a Motor Vehicle Record (MVR) in a specific state, or wants to compare MVR fees across multiple states, or is budgeting annual compliance costs for a multi-state fleet. Reference the canonical fee table below; flag that fees change (re-verify with state DMV before annual budget planning).

Use when a carrier asks about electric trucks — Tesla Semi, Freightliner eCascadia, Volvo VNR Electric, Peterbilt 579EV, range, charging, total cost of ownership, regulatory pushes (CARB ACT, ACF), incentives, infrastructure, depot vs en-route charging, and which routes/applications are EV-ready today.

Use this skill when the user asks about Driver Qualification Files (DQF) — what must be in a DQ file under 49 CFR 391, retention periods, what's required pre-hire vs ongoing, document expiration tracking, audit-readiness for driver files, common DQF deficiencies that auditors find, or how to handle missing documents on existing drivers. Always cite the specific subsection of 49 CFR 391.

Use this skill when a driver is returning to safety-sensitive duty after a positive test or refusal. Covers the SAP clearance, RTD test requirements (observed collection), and Clearinghouse update sequence.

Use this skill when the user asks what emergency equipment a CMV must carry under 49 CFR 393.95 — reflectorized triangles, flares, fire extinguishers, spare fuses, exceptions for buses/passenger CMVs, where to mount/store equipment, and what roadside inspectors check. Cite 49 CFR 393.95 + 393.97.

Use this skill when a driver holds CDLs in multiple states or has resided in multiple states. Covers what MVRs to pull, federal recordkeeping requirements, and state-specific issues.

Use this skill to determine whether you need interstate FMCSA authority or just intrastate state authority. Covers the federal/state divide.

Query Codecov for flaky-test signal, failure history, and coverage data via the codecov-api wrapper. Use when asked about flaky tests, intermittent test failures, why a test is failing, coverage on a PR/file/branch, or whenever browser access to Codecov is blocked by the login wall.

Audit, write, or revise CONTRIBUTING.md, including the decision of whether one is warranted. Use when creating contribution guidance, editing existing CONTRIBUTING, or when a README points to missing/thin contribution docs. Applies the nayafia/contributing-template framework.

File a new GitHub issue in the checked-out repo — search first for duplicates/adjacent issues to update or reference, detect the repo's issue template if any, then compose title/body/labels/milestone matching house style. Use when asked to file, create, open, report, or track an issue.

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Convert Markdown files to HTML similar to `marked.js`, `pandoc`, `gomarkdown/markdown`, or similar tools; or writing custom script to convert markdown to html and/or working on web template systems like `jekyll/jekyll`, `gohugoio/hugo`, or similar web templating systems that utilize markdown documents, converting them to html. Use when asked to "convert markdown to html", "transform md to html", "render markdown", "generate html from markdown", or when working with .md files and/or web a templating system that converts markdown to HTML output. Supports CLI and Node.js workflows with GFM, CommonMark, and standard Markdown flavors.

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

Uses BMI-specific cutoffs to interpret peak GH values during stimulation testing. Use when interpreting GH stimulation test results; triggers include GH stimulation test requiring BMI-adjusted interpretation.

Recommends using mineralocorticoid receptor antagonists rather than epithelial sodium-channel inhibitors for medical treatment of primary aldosteronism. Use when a clinician asks whether to use an MRA or ENaC inhibitor for medical treatment of PA.

Determines whether to perform adrenal venous sampling (AVS) to lateralize aldosterone excess in patients with confirmed primary aldosteronism (PA) who are being evaluated for surgical treatment. Indicated when surgery is feasible and desired by the patient, or when subtype workup is planned for a surgical candidate, especially in those younger than 35 years with spontaneous hypokalemia, marked aldosterone excess, and unilateral adrenal lesions on CT.

Monitor free T4 and adjust levothyroxine after starting antiepileptic drugs in central hypothyroidism

Perform digital rectal examination (DRE) in all men before initiating testosterone therapy to exclude prostate abnormalities or support suspicion of hypogonadism when prostate volume is reduced. Triggered when a clinician considers starting testosterone and questions whether a prostate exam is needed first or whether to check the prostate before prescribing TTh.

Interprets the aldosterone-to-renin ratio using active renin concentration (ARC) to screen for primary aldosteronism. Triggered when a clinician has PAC and ARC results and asks 'How do I interpret this ARR using active renin concentration?'

Recommends low-dose GH replacement in patients with cured acromegaly and documented GHD in the absence of known contraindications. Triggers include managing a cured acromegaly patient with documented growth hormone deficiency.

Diagnose monogenic and syndromic obesity in children and adolescents using a structured step-by-step algorithm. Use this skill whenever a clinician suspects a genetic cause of obesity, asks about leptin deficiency, MC4R mutation, POMC deficiency, PCSK1 deficiency, leptin receptor deficiency, Bardet-Biedl syndrome, Prader-Willi syndrome, Alström syndrome, or any case of early-onset severe obesity with hyperphagia. Also trigger for questions about targeted pharmacotherapy including setmelanotide or metreleptin, or when to order a genomic obesity panel. Cross-references the NHS Genomic Test Finder skill to surface the relevant R-code once a diagnosis is reached.

In patients with primary aldosteronism receiving mineralocorticoid receptor antagonist therapy, the guideline recommends titrating the MRA dose upward to raise renin when blood pressure remains uncontrolled and renin is suppressed. Consider this step when hypertension is not at goal despite MRA therapy and plasma renin activity (or direct renin concentration) is low.

Manage diabetes insipidus with desmopressin

Recommends confirmatory testing with corticotropin stimulation test in patients presenting with clinical symptoms or signs suggesting PAI (e.g., fatigue, hypotension, hyponatremia, hyperpigmentation) when the patient's condition permits safe testing. Use when a clinician identifies suggestive features and circumstances allow outpatient stimulation testing without imminent need for emergency glucocorticoids.

Determines whether to recommend adrenalectomy or mineralocorticoid receptor antagonists for primary aldosteronism based on PA subtype and patient/surgical factors. Triggered after subtype confirmation when clinicians ask “Should this patient have surgery or medical treatment?” or discuss treatment options with the patient.

Suggests oral contraceptives over injectable contraceptives for women with BMI ≥27 kg/m2 with comorbidities or BMI ≥30 kg/m2 seeking contraception, provided they are well‑informed and oral contraceptives are not contraindicated. Triggers include clinician questions such as “Which contraceptive method is less likely to cause weight gain in this obese patient?” or “Should I recommend oral pills instead of depot injection for this patient with BMI 29 and hypertension?”.

This skill identifies adult childhood cancer survivors with isolated growth hormone deficiency and prior hypothalamic‑pituitary axis radiation exposure who require retesting to confirm persistence of GHD. Triggers include clinician questions such as “Should I retest for GHD in this adult survivor with childhood GHD and radiation history?” or “Is repeat GHD evaluation indicated in this patient?”

Decide whether a newly-diagnosed multiple myeloma (NDMM) patient is eligible for high-dose melphalan + autologous stem cell transplantation (ASCT) as part of front-line therapy, using the EHA-ESMO 2021 criteria. Trigger when a clinician asks "is this myeloma patient fit for transplant", "ASCT eligibility for myeloma", "transplant-eligible NDMM", "should I refer for stem cell transplant", "high-dose melphalan candidate", or any decision about whether a newly-diagnosed myeloma patient should go to upfront ASCT.

Determines whether to recommend unilateral laparoscopic adrenalectomy or medical therapy with a mineralocorticoid receptor antagonist for patients with confirmed unilateral PA (aldosterone-producing adenoma or unilateral adrenal hyperplasia). Triggered when discussing treatment options after confirming unilateral PA in a hypertensive patient with hypokalemia or resistant hypertension.

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.

Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", "update the spec", or "break this into stories".

DEPRECATED — consolidated into bmad-prd update intent - this skill will be removed in v7 in favor of `bmad-prd`.

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.

Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"

Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel.

Adversarial code review using parallel review layers and structured triage. Use when the user says "run code review" or "review this code"

Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".

Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]"

DEPRECATED — consolidated into bmad-prd validate intent - this skill will be removed in v7 in favor of `bmad-prd`.

Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'.

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

Plans, creates, and validates BMad modules. Use when the user requests to 'ideate module', 'plan a module', 'create module', 'build a module', or 'validate module'.

Generate typed SDK bindings (Pydantic v2 models, TypeScript types) from the Bloodbank JSON Schema tree at `bloodbank/schemas/bloodbank/v1/**` (Draft 2020-12). Uses `datamodel-code-generator` and `json-schema-to-typescript` — NOT the deprecated hand-rolled Holyfields generators. Use when generating event-contract bindings for a Bloodbank consumer, importing typed CloudEvents envelopes into another project, or scaffolding a `bloodbank-contracts` SDK package. Trigger keywords — "bloodbank SDK", "bloodbank contracts", "Pydantic from bloodbank schemas", "TypeScript types for bloodbank events", "bloodbank.v1.* types", "event contract bindings", "datamodel-code-generator", "json-schema-to-typescript", "regenerate SDK", "CloudEvents bindings". Do NOT use for schema authoring (edit `bloodbank/schemas/` directly per `docs/event-naming.md` §12), runtime envelope validation (use `BLOODBANK_HOOK_VALIDATE=1`), schema-tree consistency (`mise run smoketest:schemas`), or generic JSON Schema codegen unrelated to Bloodbank.