opencode-skills-collection 3.0.27 → 3.0.29

package/bundled-skills/docs/users/visual-guide.md

@@ -34,7 +34,7 @@ antigravity-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,465+ skills live here
+├── 📁 skills/                          ← 1,480+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -47,7 +47,7 @@ antigravity-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,465+ total)
+│   └── ... (1,480+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -100,7 +100,7 @@ antigravity-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,465+ SKILLS          │
+                    │  1,480+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -201,7 +201,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,465+ total)                │
+│   └── ... (1,480+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/flowhunt-skill/SKILL.md

@@ -0,0 +1,141 @@
+---
+name: flowhunt-skill
+description: "Automation discovery audit skill. Walks through a 5-question workflow intake, then audits Gmail/Calendar/Slack/task trackers to identify automation opportunities. Use when a user wants to discover what processes in their business can be automated."
+category: automation
+risk: safe
+source: community
+source_repo: heyneuron/flowhunt-skill
+source_type: community
+date_added: "2026-05-23"
+author: heyneuron
+tags: [automation, discovery, audit, gmail, calendar, slack, productivity, workflow]
+tools: [claude, codex, gemini, cursor]
+license: "MIT"
+license_source: "https://github.com/heyneuron/flowhunt-skill/blob/main/LICENSE"
+---
+
+# FlowHunt Skill — Automation Discovery Audit
+
+## Overview
+
+FlowHunt is an automation discovery audit skill. It guides agents through a structured 5-question intake to understand the user's business context, then systematically audits connected tools (Gmail, Google Calendar, Slack, task trackers, and more) to surface concrete automation opportunities ranked by impact and effort.
+
+The skill is cross-agent: it works with Claude Code, Codex CLI, Gemini CLI, OpenCode, and any agent that accepts markdown skill files.
+
+Install: `npx skills add heyneuron/flowhunt-skill`
+
+## When to Use This Skill
+
+- Use when the user asks "what can I automate in my business?"
+- Use when the user wants a workflow audit across Gmail, Calendar, Slack, or task tools
+- Use when starting an automation engagement and need structured discovery before recommending solutions
+- Use when the user says "show me automation opportunities" or "FlowHunt"
+
+## How It Works
+
+### Step 1: Intake — 5-Question Workflow Questionnaire
+
+Ask the user exactly these five questions, one at a time:
+
+1. **Role & team size** — What is your role, and how many people are on your team?
+2. **Top 3 repetitive tasks** — What are the three most repetitive tasks you or your team do every week?
+3. **Connected tools** — Which tools do you actively use? (Gmail, Google Calendar, Slack, Notion, Jira, Asana, HubSpot, etc.)
+4. **Pain point** — Which of those repetitive tasks costs you the most time or causes the most errors?
+5. **Automation goal** — Are you looking to save time, reduce errors, or hand off tasks entirely?
+
+Wait for answers before moving to the audit.
+
+### Step 2: Audit — Scan Connected Tools
+
+For each tool the user mentioned, surface automation patterns:
+
+**Gmail**
+- Auto-labeling and routing rules
+- Draft generation for recurring email types
+- Invoice / attachment extraction to Drive or Notion
+- Follow-up reminders when no reply received
+
+**Google Calendar**
+- Meeting prep summaries (agenda + attendee context) sent automatically
+- Booking link workflows with intake forms
+- Post-meeting action item extraction
+
+**Slack**
+- Daily standup collection → summary to channel or doc
+- Keyword alerts routed to the right person
+- Approval workflows with emoji reactions
+
+**Task trackers (Asana, Jira, Notion, Linear)**
+- Auto-create tasks from emails or Slack messages
+- Status update reminders
+- Weekly digest of overdue or blocked items
+
+**CRMs (HubSpot, Salesforce, Pipedrive)**
+- Lead scoring and routing rules
+- Follow-up sequences triggered by deal stage change
+- Contact enrichment on new lead creation
+
+### Step 3: Prioritization Matrix
+
+Rank each identified opportunity on a 2x2:
+
+| | Low effort | High effort |
+|---|---|---|
+| **High impact** | Do first (quick wins) | Plan carefully |
+| **Low impact** | Nice to have | Skip for now |
+
+Present the top 3 quick-win automations with:
+- What it does
+- Which tools it connects
+- Estimated time saved per week
+- Suggested implementation path (Zapier / Make / n8n / custom code)
+
+### Step 4: Output
+
+Deliver a structured Automation Opportunity Report in markdown:
+
+```
+# Automation Opportunity Report
+
+## Business Context
+[Summary from intake]
+
+## Top 3 Quick Wins
+1. [Name] — [What it does] — [Tools] — [~X hrs/week saved]
+2. ...
+3. ...
+
+## Full Opportunity List
+[All identified automations, ranked]
+
+## Recommended Next Step
+[Single clearest action the user can take today]
+```
+
+## Common Rationalizations to Reject
+
+| Excuse | Why it's wrong |
+|--------|----------------|
+| "I'll skip the intake and guess their stack" | Intake prevents wasted recommendations on tools they don't use |
+| "I'll list every possible automation" | Overwhelming output kills adoption — prioritize ruthlessly |
+| "I'll recommend complex custom code first" | Start with no-code/low-code quick wins; earn the right to build |
+
+## Red Flags
+
+- User has no clear repetitive task → dig deeper, they always exist
+- Recommending automations for tools the user didn't mention → stay scoped
+- Skipping the prioritization matrix → every opportunity looks equal without it
+
+## Limitations
+
+- This skill identifies and prioritizes automation opportunities; it does not implement the automations for the user.
+- Tool audits depend on the user's stated stack and any explicitly connected data sources; do not assume access to Gmail, Calendar, Slack, CRMs, or task trackers.
+- Time-saved estimates are directional planning aids, not guaranteed outcomes.
+
+## Verification
+
+The skill is complete when the user has:
+- [ ] Answered all 5 intake questions
+- [ ] Received a ranked list of automation opportunities
+- [ ] Identified at least one quick-win automation they can start this week
+- [ ] A clear recommended next step

package/bundled-skills/geminiignore-finops/SKILL.md

@@ -0,0 +1,173 @@
+---
+name: geminiignore-finops
+description: "Configure and optimize .geminiignore files for AI context window efficiency and token cost reduction (FinOps)."
+category: context-optimization
+risk: safe
+source: community
+source_repo: iradoweck/antigravity-awesome-skills
+source_type: community
+date_added: "2026-05-25"
+author: iradoweck
+tags: [finops, context-management, token-optimization, geminiignore]
+tools: [gemini, claude, cursor]
+license: "MIT"
+license_source: "https://github.com/iradoweck/antigravity-awesome-skills/blob/main/LICENSE"
+---
+
+# GeminiIgnore FinOps Setup & Optimization
+
+## Overview
+
+A skill to construct, refine, and maintain high-performance `.geminiignore` files across diverse tech stacks. By filtering out machine-generated code, heavy logs, package locks, and binary assets, this skill optimizes the AI agent's context window, accelerates processing speed, and reduces token consumption costs (FinOps).
+
+## When to Use This Skill
+
+- Use when initializing a new repository or workspace for pair-programming with AI agents.
+- Use when the AI context window is reaching its limits or when billing optimization (FinOps) is a priority.
+- Use when the AI agent is accidentally reading build outputs, lock files, databases, or binary media.
+
+## How It Works
+
+### Step 1: Analyze the Workspace Tech Stack
+Detect the languages, frameworks, and dependency managers present in the project (e.g., Node.js, Python, PHP, Dart/Flutter, Rust).
+
+### Step 2: Initialize or Update the `.geminiignore` File
+Create a `.geminiignore` file at the root of the active workspace. If one already exists, review it to add missing categories.
+
+### Step 3: Implement the 7 Core Rules
+Add rules divided into the following categories to filter out unnecessary machine noise while keeping human-written code visible:
+
+1. **System & Editor Noise**: Block OS temp files (`.DS_Store`, `Thumbs.db`) and user-specific IDE caches (`.idea/`, `.vscode/*`, Xcode user data).
+2. **Dependency Folders & Lock Files**: Ignore third-party package directories (`node_modules/`, `vendor/`) and giant machine-generated lock files (`package-lock.json`, `yarn.lock`, `Cargo.lock`, `composer.lock`).
+3. **Build & Target Output**: Block compiled folders (`dist/`, `build/`, `.next/`, `.nuxt/`).
+4. **Caches & Tool Metadata**: Block compiler caches (`.tsbuildinfo`, `.vite/`, `.pytest_cache/`, `.eslintcache`).
+5. **Binary & Rich Assets**: Block media types (`*.png`, `*.pdf`, `*.mp4`, `*.woff2`) to prevent triggering expensive vision/multimodal tokens.
+6. **Local Databases & Logs**: Block log files (`*.log`) and SQL dumps or local SQLite DBs (`*.sqlite`, `*.db`).
+7. **Compiled Binaries & Mobile Builds**: Block mobile package files (`*.apk`, `*.ipa`) and compiled binaries (`*.class`, `*.pyc`, `*.dll`).
+
+### Step 4: Validate Exclusions
+Verify that the AI can still see critical configuration blueprints (like `.env.example`, `package.json`, `composer.json`, `pyproject.toml`) but ignores the actual `.env` files and compilation artifacts.
+
+## Examples
+
+### Example 1: Standard Universal `.geminiignore` Template
+
+Here is a recommended baseline configuration for a multi-language project:
+
+```ini
+# ==============================================================================
+# .geminiignore - BASELINE DE FINOPS E ARQUITETURA
+# ==============================================================================
+
+# 1. SISTEMA OPERACIONAL E IDEs
+.DS_Store
+Thumbs.db
+Desktop.ini
+$RECYCLE.BIN/
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+.idea/
+*.iml
+.gradle/
+local.properties
+.history/
+
+# 2. DEPENDÊNCIAS (ECONOMIA DE TOKENS EM LOCK FILES)
+node_modules/
+package-lock.json
+yarn.lock
+pnpm-lock.yaml
+vendor/
+composer.lock
+venv/
+.venv/
+env/
+.env
+.env.*
+!.env.example
+poetry.lock
+Cargo.lock
+pubspec.lock
+
+# 3. BUILDS E EXPORTAÇÕES
+dist/
+build/
+out/
+target/
+.next/
+.nuxt/
+.output/
+bin/
+obj/
+
+# 4. CACHES DE FRAMEWORKS
+.vite/
+.parcel-cache/
+.eslintcache
+.babel-cache/
+.tsbuildinfo
+.turbo/
+.pytest_cache/
+.ruff_cache/
+storage/framework/
+storage/logs/
+
+# 5. ASSETS BINÁRIOS E MULTIMÍDIA EXTREMOS
+*.png
+*.jpg
+*.jpeg
+*.gif
+*.webp
+*.svg
+*.ico
+*.psd
+*.fig
+*.pdf
+*.zip
+*.tar.gz
+*.woff
+*.woff2
+*.ttf
+
+# 6. BANCOS DE DADOS E LOGS
+*.log
+*.db
+*.sqlite
+*.sqlite3
+*.sql
+*.sql.gz
+
+# 7. ARQUIVOS COMPILADOS
+*.apk
+*.aab
+*.ipa
+*.jar
+*.class
+*.pyc
+__pycache__/
+*.so
+*.dylib
+*.dll
+*.exe
+*.js.map
+*.css.map
+```
+
+## Best Practices
+
+- ✅ **Ignore dependency lock files**: Standard lock files (e.g., `package-lock.json`, `yarn.lock`) contain thousands of lines of redundant package resolution trees. Ignoring them is the single largest FinOps win.
+- ✅ **Keep configurations visible**: Ensure manifests like `package.json`, `composer.json`, `Cargo.toml`, and `pyproject.toml` are NEVER ignored, as the AI needs them to understand dependencies.
+- ✅ **Whitelist config examples**: Use rules like `!.env.example` alongside `.env` ignores so the AI understands configuration structure without exposing credentials.
+- ❌ **Do not ignore source code**: Avoid overly broad folder patterns like `lib/` or `app/` if they contain primary source code. Be specific (e.g., block `vendor/bundle/` but not your actual code).
+
+## Limitations
+
+- A `.geminiignore` file only affects AI tools parsing the workspace; it does not replace `.gitignore` for Git repository hosting.
+- Patterns must be formatted correctly according to gitignore-style globbing to avoid accidentally ignoring source files.
+
+## Related Skills
+
+- `@context-optimization` - Broad tactics for context window management.
+- `@clean-code` - Architectural practices for clean, human-readable codebases.

package/bundled-skills/ii-commons/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: ii-commons
+description: "Deterministic search across arXiv, PubMed/PMC, and US policy corpora with daily freshness cutoffs."
+category: research
+risk: safe
+source: community
+source_repo: Intelligent-Internet/II-Commons-Skills
+source_type: community
+date_added: "2026-05-26"
+author: Intelligent Internet
+tags: [research, arxiv, pubmed, pmc, policy, retrieval, cli, codex]
+tools: [claude, cursor, gemini, codex, antigravity]
+license: "Apache-2.0"
+license_source: "https://github.com/Intelligent-Internet/II-Commons-Skills/blob/main/LICENSE"
+---
+
+# II-Commons
+
+## Overview
+
+II-Commons provides deterministic retrieval for research agents across arXiv, PubMed/PMC, and supported US policy corpora. Use it when a task needs reproducible search, metadata lookup, full-document Markdown retrieval, or a freshness check before answering with recent evidence.
+
+The upstream project publishes a Node.js CLI as `@intelligentinternet/ii-commons` and a full agent skill at `skills/ii-commons/`.
+
+## When to Use This Skill
+
+- Use when searching arXiv, PubMed/PMC, or supported US policy corpora for evidence.
+- Use when the user asks for latest or recent research and corpus freshness matters.
+- Use when you need stable identifiers, metadata, or full-document Markdown for downstream analysis.
+- Use when comparing evidence across scientific literature and policy documents.
+
+## How It Works
+
+### Step 1: Check Corpus Freshness
+
+Run `cutoff` before freshness-sensitive searches:
+
+```bash
+npx @intelligentinternet/ii-commons cutoff
+```
+
+Report the relevant cutoff date before interpreting recent results.
+
+### Step 2: Search the Right Corpus
+
+Use exactly this command shape:
+
+```bash
+npx @intelligentinternet/ii-commons search arxiv "large language model inference" --max-results 10
+npx @intelligentinternet/ii-commons search pubmed "type 2 diabetes review" --start 20240000 --max-results 10
+npx @intelligentinternet/ii-commons search policy "state overtime rule for agricultural workers" --jurisdictions US-CA --max-results 10
+```
+
+Choose `arxiv` for preprints and technical research, `pubmed` for biomedical and clinical literature, and `policy` for supported US policy corpora.
+
+### Step 3: Retrieve Metadata or Markdown
+
+Use stable identifiers from search results:
+
+```bash
+npx @intelligentinternet/ii-commons meta "arXiv:2402.03578"
+npx @intelligentinternet/ii-commons markdown "PMCID:PMC11152602"
+```
+
+Build summaries from search results first, then request Markdown when detailed inspection or full-document grounding is needed.
+
+## Installation
+
+Run the CLI with `npx`:
+
+```bash
+npx @intelligentinternet/ii-commons --help
+```
+
+Or install globally:
+
+```bash
+npm install -g @intelligentinternet/ii-commons
+ii-commons cutoff
+```
+
+To install the full upstream agent skill, install the `skills/ii-commons/` folder from:
+
+```text
+https://github.com/Intelligent-Internet/II-Commons-Skills
+```
+
+## Best Practices
+
+- Prefer server-side date filters such as `--start` and `--end` for time-bounded arXiv and PubMed searches.
+- Preserve canonical identifiers such as `arXiv:<id>`, `PMID:<id>`, `PMCID:PMC<id>`, and `policy:<jurisdiction>:<id>`.
+- Use `cutoff` as the authoritative freshness boundary for each corpus.
+- Keep non-time filters conservative until initial search results show the right scope.
+
+## Limitations
+
+- Requires Node.js 18 or newer and outbound network access to `commons.ii.inc`.
+- Basic usage works without authentication; higher usage limits may require an API token from `https://commons.ii.inc/`.
+- Supported policy coverage is limited to the policy corpora exposed by II-Commons.
+
+## Security & Safety Notes
+
+- Do not print or expose `II_COMMONS_API_KEY` values.
+- Treat outputs as retrieval evidence, not expert review. For medical, legal, or policy-sensitive work, cite sources and preserve uncertainty.
+- Commands call an external API service; confirm network access is allowed in the user's environment before running them.
+
+## Related Skills
+
+- Use broader web-search or deep-research skills when evidence is outside arXiv, PubMed/PMC, or supported policy corpora.
+- Use citation-management skills after II-Commons has identified stable source records.