
pm-latam
Working life in Brazil and Mexico: termination pay, annual tax returns, and final settlements, covered.
- version
- 1.0.0
- GitHub stars
- 1.6K
What it does
- Adds 4 skills:
br-rescisao-clt,br-irpf-prep,mx-finiquito-liquidacion, andmx-declaracion-anual-prepfor employment and tax questions - Covers CLT termination pay, FGTS and unemployment insurance effects, and the Brazilian annual income tax return (IRPF)
- Estimates Mexican finiquito on any separation and liquidación on unjustified dismissal, based on the daily wage
- Designed for workers, employers, and HR teams in Brazil and Mexico checking settlements and annual filings
Working life in Brazil and Mexico: CLT termination pay, the Brazilian annual income tax return, Mexican finiquito and liquidación, and the Mexican annual tax return
Add marketplace
/plugin marketplace add mohitagw15856/pm-claude-skillsRun it inside Claude Code once, then install the plugin below.
Install
/plugin install pm-latam@pm-claude-skillsRun it inside Claude Code after adding the marketplace.
Files
Discovered from sourceIRPF Prep (Brazil)
The Brazilian annual return is mostly an exercise in matching: what the taxpayer declares must agree with what employers, banks, clinics and landlords have already reported. Returns are held for review when those numbers differ. This skill organises the documents, chooses the model and builds the worksheet. Thresholds, caps and dates change every year and must be checked on the tax authority's official pages.
What This Skill Produces
- A verdict on whether filing is required, with the trigger
- A document checklist by source
- A comparison of the complete and simplified models using the user's figures
- A deductions worksheet with the evidence needed for each item
- An assets and debts template
- A pre-submission check against the usual causes of review
Required Inputs
Ask for these if not provided:
- The calendar year being declared
- Income by type: salary, self-employment, rent, pension, capital gains, exempt income
- Dependants and alimony paid or received
- Health, education and private pension spending
- Assets at the start and end of the year: property, vehicles, bank and investment balances
- Debts
- Whether a pre-filled return is available through the government login
- Sales of property or shares during the year
Framework
- Who must file. Triggers include taxable income above the annual threshold, exempt income above a higher threshold, assets above a set value, capital gains or stock market transactions, and rural activity above a limit. Verify each for the year.
- Documents. Income statements (informes de rendimentos) from every employer, bank and broker; receipts for health and education with the provider's tax number; private pension and social security statements; rent received or paid; property and vehicle documents; last year's return.
- Pre-filled return. Use it as a starting point and check every line; the taxpayer remains responsible.
- Complete or simplified. The simplified model replaces all deductions with a percentage of taxable income up to a cap. The complete model itemises. Compare totals.
- Deductions in the complete model. Dependants (fixed amount each), education (capped per person), health (no cap, strict evidence), official social security, private pension of the right type up to a share of taxable income, court-ordered alimony, and the self-employed cash book.
- Assets and debts. Declared at acquisition cost, not market value, with the standard description for each. Balances at 31 December of both years.
- Monthly obligations. Income from individuals or abroad may have required monthly payment during the year; check whether it was paid.
- Review triggers (malha fina). Income omitted, a dependant claimed twice or with their own income left out, health costs without matching provider reports, figures that differ from the income statements, and asset growth that income does not explain.
- After filing. Keep the receipt, track the refund lots or pay the balance, and correct with a rectifying return if an error appears.
Output Format
Preparação do IRPF: ano-calendário [year]
Obrigado a declarar? [yes / no / voluntary] because [trigger]. Prazo: [date to verify].
Documentos
| Documento | Fonte | Recebido? |
|---|
Completa x simplificada
| Completa | Simplificada | |
|---|---|---|
| Rendimentos tributáveis | ||
| Deduções | ||
| Base de cálculo |
Deduções
| Tipo | Beneficiário | Valor | Limite a verificar | Comprovante |
|---|
Bens e dívidas
| Item | Descrição padrão | 31/12 anterior | 31/12 do ano |
|---|
Antes de transmitir
- All income statements entered exactly as issued
- Each dependant appears in one return only, with their income included
- Every health expense has a receipt with the provider's tax number
- Asset growth is consistent with declared income
- Bank details for the refund are correct
Assumptions and gaps
- [Figures estimated]
- [Documents still missing]
Apoio à preparação, não é consultoria tributária. Confira limites, prazos e regras do ano nos canais oficiais ou com um contador.
Quality Checks
- The filing trigger is named
- The model comparison uses the user's numbers
- Each deduction lists its evidence
- Assets are at cost, not market value
- No threshold, cap or date is asserted as current without a verify note
- Review triggers are checked
Anti-Patterns
- Do not state this year's thresholds from memory.
- Do not accept the pre-filled return unchecked.
- Do not claim health costs without proper receipts.
- Do not update property to market value.
- Do not ignore a dependant's own income.
Example Trigger Phrases
- "Preciso declarar imposto de renda este ano? Ganhei só salário."
- "Completa ou simplificada? Tenho dois filhos e plano de saúde."
- "Como declaro um apartamento financiado?"
- "Caí na malha fina por despesa médica. O que faço?"
Run this skill in your browser: https://mohitagw15856.github.io/pm-claude-skills/skill/br-irpf-prep.html
From the mohitagw15856/pm-claude-skills README
English · 简体中文 · 繁體中文 · 한국어 · 日本語 · Español · Português (BR)
🧠 PM Skills: Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
One request to your AI, one finished deliverable back: the PRD, the stakeholder update and the decision call, at a senior product manager's standard.
Try it right now. Install below, then paste this into your assistant:
Here are my discovery notes from six customer calls: [paste your notes].
Turn them into a one-page PRD, a risk register with owners, and a
stakeholder update I can send to leadership today.
Your assistant loads user-interview-synthesis, prd-template and stakeholder-update and returns the three documents, not advice about writing them. Not a PM? The same library covers engineers, job seekers, students, founders and 中文用户, below.
▶ Playground · ⚡ Install · 📚 All skills · 📘 Worked examples · 🏆 Best AI for your job · ❓ How do I…? · 🖼 Showcase · 🌳 Tech tree · 🇨🇳 简体中文 · 繁體中文 · 한국어 · 🆕 Changelog
Your landlord kept your deposit. You got laid off on a Tuesday. Your boss wants the PRD by Friday. Generic AI is a very confident intern. PM Skills is the senior colleague's notes: 1374 of them, one markdown file each. (PM stands for Professional. Yes, we get asked.)
PM Skills is an open-source library of 1374 Agent Skills — plain-markdown SKILL.md files that teach an AI assistant to do one professional task to a senior professional's standard, from writing a PRD to decoding a lease or running a blameless postmortem. Each skill bundles the framework, an output template, quality checks, and anti-patterns. It is MIT-licensed and works with Claude, ChatGPT, Gemini, Cursor, and Codex.
⚡ Install in 30 seconds
npx pm-claude-skills add # any tool: Cursor, Codex, Windsurf, Cline, Zed…
# In Claude Code: /plugin → search pm-skills (official Anthropic directory)
npx --registry=https://registry.npmmirror.com pm-claude-skills add # 中国大陆镜像
Then just say what you need: "Decode this job ad and tell me where I am weak." Nothing here can break your setup: a skill is a markdown file your AI reads; installing copies text files, uninstalling deletes them. Read one first. Per-tool instructions: docs/installation.md · ChatGPT and Gemini: copy from exports/ · MCP: claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp · No install at all: point any MCP client at the hosted broker https://pm-skills-mcp.pm-claude-skills.workers.dev/mcp (how it works) · Starting a team? clone a starter template for your role · No network? every release ships an offline bundle you can serve on a laptop
🔄 Keep it updated
Skills improve every week. Whichever way you installed, updating is one step.
| You installed with | Update with |
|---|---|
npx pm-claude-skills add (any tool) | Run the same command again. npx pm-claude-skills doctor lists what is installed and what is stale. |
| The Claude Code marketplace | Open /plugin, pick the pm-claude-skills marketplace and choose Update. |
| The Python package | pip install -U pm-skills |
| The MCP server | Use npx -y -p pm-claude-skills@latest pm-claude-skills-mcp in your MCP config and every start is the latest release. |
| A fork of this repository | The bundled sync-fork.yml workflow fast-forwards your main every week. See docs/fork-sync.md. |
Stuck? The FAQ answers the common questions in English, 简体中文, 繁體中文, 日本語, 한국어, Español and Português.
🌅 Claude Duet, OpenAI Dots and other proactive agents
PM Skills works with Claude Duet, Anthropic's proactive agent. Duet uses the skills in your Claude account, so every skill here can run inside it. Agents that work while you're away fail in new ways: briefs that pad, uncited claims, acting instead of drafting, saying "done" about a draft. So 21 Duet-ready skills are built for unattended use. They keep briefs short and cited, draft instead of sending, and always ask before anything is sent, posted, paid, signed or deleted.
The five skills: prepare-for-duet · standing-orders · approval-policy-designer · morning-brief-designer and interrupt-rules · agent-kill-switch-plan
Watchers for a small business: cash-watch, payroll-eve-check, signature-pipeline-watch, crm-hygiene-sweep and store-watch. They cover Stripe, Xero, QuickBooks, Gusto, DocuSign, HubSpot and Shopify. For teams: shared-agent-charter, for a Dot or a shared agent in Slack or Teams.
Get started
- Into Claude and Duet: press ⬇ Add to Claude on any skill's page, then upload the ZIP in claude.ai (Settings, Skills, Upload skill).
- A starter pack of 3 or 4 skills (founder, freelancer, shop owner, team lead, business ops) on the Duet page, or
npx pm-claude-skills add --agent claude --skills standing-orders,cash-watch,store-watch. - The whole bundle:
npx pm-claude-skills add --bundle pm-duet.
Test it safely: the injection drill has 12 planted instructions to check whether your agent reports or obeys them. The fake-apps sandbox gives invented Gmail, Stripe and Shopify data where every send or payment is refused and logged.
Honest status: every one of these skills is designed for Duet. None has been tested on Duet yet, because it's a waitlisted research preview. File a Tested on Duet report and a skill moves up a tier, with your name on it. They're written to work with Dots and Muse too: see how the three compare.
🥊 The demo
More to see: the Showcase gallery has the Playground, the tech tree, Galaxy 3D and Skill City.
🧭 How it works
More detail: the installer, the MCP server and the REST API
A skill is one plain-markdown SKILL.md file: a description that tells your assistant when to load it, plus the working framework, output template and quality checks it follows. The installer (npx pm-claude-skills add) copies the skills you choose into the config folder of the tool you use, so they load only when a request matches. The MCP server serves skills on demand to any MCP client instead, and the same package exposes a read-only REST API for n8n, Make and other automations. No runtime, no account, nothing resident: uninstalling deletes text files.
🧑🤝🧑 Pick your path
|
| Hi, I'm Nib. Pick the card that sounds most like you. Each one opens three starter skills with a prompt you can copy. |
None of these you? docs/start has all six paths, a map of every bundle by what you want to do, a four-question quiz and a five-level quest log. Mid-something big? Skill Packs start from your moment: a new baby, a layoff, a move, a loss.
🗺 What you can do
The product-management core first, then the bundles everyone borrows. Each one is a real bundle in plugins/.
The table: what each bundle gives you, what you bring, and links
| Your job this week | Bundle | What you get | What you bring |
|---|---|---|---|
| Turn research into decisions | pm-discovery | Interview guides, job stories, synthesis with quotes and prevalence | Transcripts or raw notes |
| Write the PRD and the updates | pm-essentials | PRD, meeting notes, stakeholder updates, competitive analysis | A feature brief; your goals |
| Plan the quarter | pm-planning | OKRs, RICE/MoSCoW/Kano prioritisation, roadmap narrative | A backlog and a company goal |
| Ship the sprint and the launch | pm-delivery | Sprint plans, tech specs, A/B test plans, launch checklists | Stories, capacity, dates |
| Read the numbers | pm-data | Metrics frameworks, cohort and churn analysis, dashboard briefs | Your metrics or a CSV |
| Watch the market | pm-strategy | Competitor teardowns, signal tracking, stakeholder influence maps | Competitor names and sources |
| Launch and sell it | pm-gtm | GTM plans, content calendars, email campaigns | A product and an audience |
| Keep the customers | pm-cs | Health scorecards, QBR decks, churn analysis, renewal playbooks | Account data, close notes |
| Make the hard call | pm-decisions | Typed ship-or-slip, renew-or-churn, hire-or-pass calls with probabilities | The decision's real state |
| Escape the average answer | pm-thinking | Red-teaming, five clashing minds, decision panels | A plan or question worth attacking |
| Read before you sign | pm-decoders | Leases, bills, benefits and contracts decoded with the money maths | The document itself |
| Land the next job | pm-jobsearch | JD decoding, outreach, interview prep, follow-up sequences | The JD and your CV |
| 用中文工作 | pm-china-work | 周报、述职、复盘,中国职场的写法 | 你的工作记录 |
Install any bundle: /plugin install pm-decoders@pm-claude-skills, or npx pm-claude-skills add --bundle pm-decoders. All 167 bundles with every skill and install command: docs/catalogue.md · every skill in one page: SKILLS.md · chain them: WORKFLOWS.md
🇨🇳 中文用户
用中文提问即可。 十六个面向中文用户的技能包:周报述职(pm-china-work)、考公考研(pm-china-exams)、劳动合同与补偿(pm-china-life)、外贸、制造业、合规、出海等,73 个技能有简体中文版、27 个有繁体中文版。
国内安装:npx --registry=https://registry.npmmirror.com pm-claude-skills add,镜像与离线包见 docs/CHINA.md。
新增:电商运营(pm-china-ecommerce)、创业与政策申报(pm-china-startup)、留学与海归(pm-china-study-abroad);微信小程序技能查找器、uTools 与 Quicker 插件;结果一键写回飞书文档、语雀、钉钉文档;Qwen Code、iFlow、Kimi 可直接安装:npx pm-claude-skills add --agent qwen。
试着说:"帮我写周报" · "公司要裁我,能拿多少补偿?" · "下个月公务员面试,帮我模拟一轮。"
完整中文说明(技能包全表、常见问题、国内工具与本地模型、海报与分享卡):简体中文 README · 港台用户:繁體中文 README
🆕 What's new
What each release adds, and what to try saying
| Release | What it adds | Try saying |
|---|---|---|
| v84.0.0 Regions and new models | Regional packs for the Gulf, Brazil and Mexico, Germany, and Nigeria, Kenya and South Africa; packs for nurses, farmers, shop-floor retail, sports coaches, procurement and PhD students; three more China packs with a WeChat Mini Program finder, uTools and Quicker plugins, write-back to 飞书, 语雀 and 钉钉, and installs for Qwen Code, iFlow and Kimi; one model registry on the current Claude line-up, per-skill model and effort guidance, and missions that chain typed pipelines with checkpoints and resume | "I worked in Dubai for seven years on a basic of 8,000. What is my gratuity?" · "Was bedeutet mein Arbeitszeugnis?" · "帮我写双11活动方案" |
| v83.2.0 Duet support | 21 Duet-ready skills for Claude Duet and other proactive agents: standing orders, approval policies, a kill switch, small-business watchers (cash, payroll, signatures, CRM, store), team charters, an injection drill, a fake-apps sandbox, starter packs and an Add to Claude ZIP for every skill | "Write standing orders for my Duet" · "Watch my Stripe and Xero every morning" |
| v83.0.0 For everyone, everywhere | Easy Read, Teach me, voice and mixed-language questions, local rules for your place, a skill for every form, newcomer, informal-economy, disability and after-a-disaster skills, the library offline on a Raspberry Pi, a USSD menu for any phone, right-click any file, skill apps, partner checks and an expert-graded jobs exam | "Explain this P60 to me" · "मेरा landlord deposit नहीं दे रहा" |
New in v84: local rules for the Gulf, Brazil and Mexico, Germany and Nigeria, Kenya and South Africa (with a USSD menu for any phone); bundles for nursing, farming, shop-floor retail, sports coaching, procurement and PhD work; Arabic, German and French translations in the side-by-side reader, right-to-left where the language is; one model registry with per-skill model and effort guidance (run <skill> --auto-model); and missions, which chain typed pipelines into one resumable run.
Reaching everyone (v83): read any skill in Easy Read, have it teach you instead of doing it, ask by voice in your own language (Hinglish and Taglish included), look up any form, open a skill as an app, or use it with no internet: on a Raspberry Pi, over USSD on a basic phone, or from the right-click menu with a free local model.
Everything older: CHANGELOG.md · the write-ups: docs/WHATS-NEW.md · most-wanted skills and votes: the tech tree
✅ Trust and quality
An honest summary of what is checked, measured and still unreviewed, computed from the repo on every change:
The numbers in full, with links, and how the library checks itself
- Checked on every change, in CI: structure (SkillCheck, all 1,374 skills at the L3 gate), a security audit, a near-duplicate check, a count-drift check, translation parity (201 translations in 11 languages), and a prompt-injection suite of 15 hostile documents. A change that fails any of them does not merge.
- Eval cases: 478 of the 1,374 skills carry eval cases (
evals/cases.json), and 163 have a worked example inexamples/. - Measured scores: 399 skills have blind-judged scores on the leaderboard (average 4.6/5 across the models tested); the benchmark report publishes the negative findings too. Everything unscored is unscored, not assumed good.
- Human review: of the 183 skills rated high-stakes in risk tiers, 0 have a current review by a qualified professional. The expert-review programme and its ranked queue exist for exactly this; if you hold a relevant credential, reviewing one skill is the most valuable contribution available, and it earns co-authorship, a signed certificate and the badge.
- Reported savings: none recorded yet. Tell us what a skill saved you: hours and money only, added up in public on the Wall of Wins.
- Checked by people who do the job: organisations can vouch for skills as partners, and the jobs exam has AI answers marked blind by working professionals on their own marking schemes. Both start empty and fill only with real participants.
- It rewrites itself, in public: the weakest skills are periodically rewritten by a model and kept only if a judge scores the rewrite higher; every attempt, including the losses, is in the evolution log.
- Honesty rules baked in: decoders end with a not-advice line (the severity scale), calculators name what they do not model, simulators debrief out of character. PM Skills is not a substitute for a professional.
Privacy, stated plainly: everything installable runs locally. Skills are inert markdown on your machine; the CLI, the exports and the local MCP server send nothing anywhere, and telemetry is off unless you set PM_SKILLS_TELEMETRY=1 (skill name only, never content). The two things that do leave your machine are your prompts to whichever model provider you chose, and requests to the hosted playground or hosted MCP if you opt to use them. Full statements: docs/TELEMETRY.md · report a vulnerability: SECURITY.md · licence: MIT. Verify a release: npx pm-claude-skills verify --release (signed SBOM, Sigstore provenance). Verify one skill: its SHA-256 is published in /.well-known/agent-skills.json, so running shasum -a 256 on your copy of the file should match; every exported file carries the same hash in a provenance footer. Agent-native skills are red-teamed on every change (evals/adversarial).
🙌 Community
- Show and Tell: share what a skill produced, including what it got wrong: open a Show and Tell. The best entries become showcases.
- Vote on what gets built next: the tech tree ranks open skill requests by 👍; the top three are in research.
- Roadmap: confirmed direction in ROADMAP.md, the live signals behind it in docs/roadmap.md.
- Chat: TODO, a Discord or GitHub Discussions link goes here once the maintainer enables one; until then, issues are the front door.
🤝 Contributing
The library grows a skill at a time: plant one of your own. One markdown file, one PR.
Add a skill by PR (the standard, CONTRIBUTING), request one and watch it appear on the tech tree, or claim a good first translation. 中文贡献者:Gitee Issue 也可以。
Contributors
Mohit Aggarwal 🚧 💻 🖋 🌍 📖 🚇 |
Thejesh 💻 🐛 🖋 |
Chanhyo Jung 🖋 |
Matthew Blode 🔌 |
InsightFactoryAPP 🔌 |
Martinius 🔌 |
Credits follow the all-contributors spec (.all-contributorsrc). Contributed and not listed? Open a pull request running node scripts/build-contributors.mjs --add <your-login> <type>, or ask in an issue. Translators: pick a skill from the claim board.
Star history
Star history chart for PM Skills, with markers for star milestones and major releases
If a skill saved you real money or a real mistake, star the repo: it's how others find it. Sponsors fund the playground's free runs and get naming rights, not influence: become a sponsor.
MIT. Use them, fork them, ship them at work. Skills are judgment, and judgment wants to be free.
Built by Mohit with Claude. 1374 skills · 167 bundles · 35 professions · every commit gated. The long version lives in the Showcase.
Details
- Marketplace
- mohitagw15856/pm-claude-skills
- Source
- plugins/pm-latam
- Category
- Productivity
More from mohitagw15856/pm-claude-skills
All 167- pm-layoffv1.0.0
- pm-learningv1.0.0
- pm-legalv1.2.0
- pm-lifeadminv1.0.0
- pm-livev1.0.0
- pm-localizationv1.0.0
- pm-maintainerv1.0.0
- pm-menav1.0.0
- pm-methodv1.0.0
- pm-moneyv1.0.0
- pm-musicianv1.0.0
- pm-neurodivergentv1.0.0
- pm-newcomerv1.0.0
- pm-newgenv1.0.0
- pm-nonprofitv1.0.0
- pm-nursingv1.0.0
- pm-operationsv1.4.0
- pm-operatorv1.0.0
- pm-oss-launchv1.0.0
- pm-parentsv1.0.0
- pm-peoplev1.1.0
- pm-personalv1.0.0
- pm-pharmacyv1.0.0
- pm-phdv1.0.0
Similar to pm-latam
More Productivity & Planning
code-reviewanthropics/claude-code156.1K starsAutomated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
cavemanJuliusBrussee/caveman121.1K starsTalk like caveman. Cut filler. Keep technical details explicit.
career-opscareer-ops-hq/career-ops83.4K starsOpen-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor you
ruflo-autopilotruvnet/ruflo82.2K starsAutonomous /loop-driven task completion with learning, prediction, and progress tracking
ppt-masterhugohe3/ppt-master78K starsGenerate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirem
moletw93/Mole75.4K starsDrive the Mole CLI (mo) safely: find what uses disk space, preview cleanup with --dry-run, uninstall apps, and read system health and cleanup history.