opencode-skills-collection 4.0.49 → 4.0.51

package/bundled-skills/.antigravity-install-manifest.json

@@ -1,6 +1,6 @@
 {
   "schemaVersion": 1,
-  "updatedAt": "2026-09-01T02:22:24.965Z",
+  "updatedAt": "2026-09-03T01:49:23.310Z",
   "entries": [
     "00-andruia-consultant",
     "007",
@@ -766,6 +766,7 @@
     "electron-development",
     "elixir-pro",
     "elon-musk",
+    "email-issue-fixer",
     "email-security",
     "email-sequence",
     "email-systems",

package/bundled-skills/agents-md/SKILL.md

@@ -1,130 +1,217 @@
 ---
 name: agents-md
-description: This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
+description: Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.
+category: development
 risk: critical
 source: community
+date_added: "2026-03-06"
 ---
 
-# Maintaining AGENTS.md
+# Maintain AGENTS.md from repository evidence
 
-AGENTS.md is the canonical agent-facing documentation. Keep it minimal—agents are capable and don't need hand-holding. Target under 60 lines; never exceed 100. Instruction-following quality degrades as document length increases.
+## Overview
 
-## When to Use
-- The user asks to create, update, or audit `AGENTS.md` or `CLAUDE.md`.
-- The project needs concise, high-signal agent instructions derived from the actual toolchain and repo layout.
-- Existing agent documentation is too long, duplicated, or drifting away from real project conventions.
-
-## File Setup
-
-1. Create `AGENTS.md` at project root
-2. Create symlink: `ln -s AGENTS.md CLAUDE.md`
-
-## Before Writing
-
-Analyze the project to understand what belongs in the file:
+Create or improve agent instructions that help a coding agent change the
+repository correctly without rediscovering its workflow. Base every
+repository-specific command, path, and rule on evidence in the current
+checkout.
 
-1. **Package manager** — Check for lock files (`pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`, `uv.lock`, `poetry.lock`)
-2. **Linter/formatter configs** — Look for `.eslintrc`, `biome.json`, `ruff.toml`, `.prettierrc`, etc. (don't duplicate these in AGENTS.md)
-3. **CI/build commands** — Check `Makefile`, `package.json` scripts, CI configs for canonical commands
-4. **Monorepo indicators** — Check for `pnpm-workspace.yaml`, `nx.json`, Cargo workspace, or subdirectory `package.json` files
-5. **Existing conventions** — Check for existing CONTRIBUTING.md, docs/, or README patterns
+Prefer a focused diff over a wholesale rewrite. There is no universal line
+limit, required section list, symlink layout, or commit-attribution policy;
+follow the repository's own needs and maintainer intent.
 
-## Writing Rules
-
-- **Headers + bullets** — No paragraphs
-- **Code blocks** — For commands and templates
-- **Reference, don't embed** — Point to existing docs: "See `CONTRIBUTING.md` for setup" or "Follow patterns in `src/api/routes/`"
-- **No filler** — No intros, conclusions, or pleasantries
-- **Trust capabilities** — Omit obvious context
-- **Prefer file-scoped commands** — Per-file test/lint/typecheck commands over project-wide builds
-- **Don't duplicate linters** — Code style lives in linter configs, not AGENTS.md
+## When to Use
 
-## Required Sections
+- The user asks to create, update, shorten, or audit `AGENTS.md`.
+- A monorepo needs root instructions plus narrower package-level overrides.
+- Existing agent instructions contain stale commands, duplicated policy, or
+  unsupported claims.
+- The user wants to reconcile `AGENTS.md` with `CLAUDE.md`,
+  `.github/copilot-instructions.md`, or other repository instruction files.
+
+Use `@agents-generator` instead when the task specifically calls for its
+packaged generation modes, assets, or backup workflow. Use this skill when a
+maintainer-readable, evidence-first edit is the primary goal.
+
+## How It Works
+
+### 1. Preserve existing intent
+
+Before writing, read every instruction file that applies to the target path,
+including existing `AGENTS.md` files and relevant tool-specific files such as
+`CLAUDE.md`, `GEMINI.md`, `.github/copilot-instructions.md`, and
+`.github/instructions/*.instructions.md`.
+
+- Improve an existing `AGENTS.md` in place when possible.
+- Preserve accurate maintainer-authored rules and repository-specific policy.
+- Do not replace another tool's instruction file with a symlink unless the
+  user requests it and repository evidence shows identical content is desired.
+- Do not silently choose between conflicting instructions. Follow the
+  higher-priority applicable rule, or ask when the intended policy cannot be
+  established from the repository.
+
+### 2. Build a bounded evidence map
+
+Inspect only enough of the repository to establish how work is actually done:
+
+1. Read the project overview and contribution guidance, such as `README*`,
+   `CONTRIBUTING*`, and relevant docs.
+2. Read manifests, lockfiles, workspace files, task runners, and build config
+   to identify supported tools and exact commands.
+3. Read CI workflows to learn required checks. Do not assume every CI or
+   deployment job is safe or appropriate to run locally.
+4. Inspect representative source and test files for naming, layout, and test
+   conventions.
+5. Identify generated files, migrations, vendored code, large fixtures,
+   secrets boundaries, and production-only operations.
+
+Prefer `rg --files` and `rg` for discovery when available. Track the source of
+each non-obvious command or rule so unsupported claims do not enter the final
+file.
+
+### 3. Choose the instruction scope
+
+Use the root `AGENTS.md` for repository-wide guidance. Add or revise a nested
+`AGENTS.md` only when a subtree has materially different commands,
+architecture, conventions, or safety boundaries.
+
+Keep shared rules at the root and only differences in nested files. For tools
+that implement the public AGENTS.md convention, the nearest file in the
+directory tree controls the working subtree. Do not copy the full root file
+into every package.
+
+### 4. Write high-signal guidance
+
+Choose headings that fit the repository instead of forcing a fixed template.
+Include the following only when supported by evidence:
+
+- **Repository map:** the few directories and boundaries an agent must know.
+- **Setup and commands:** exact install, development, build, lint, type-check,
+  and test commands, with the working directory when it is not obvious.
+- **Focused validation:** targeted checks for a small change and broader checks
+  required before handoff.
+- **Change rules:** generated-file ownership, migrations, schemas, APIs,
+  dependencies, and cross-package coordination.
+- **Safety boundaries:** secrets, production data, destructive commands,
+  deployments, and operations that require explicit authorization.
+- **Contribution rules:** repository-specific naming, formatting, commit, or
+  pull-request requirements that affect implementation or handoff.
+
+Write direct, testable statements. Prefer:
 
-### Package Manager
-Which tool and key commands only:
 ```markdown
-## Package Manager
-Use **pnpm**: `pnpm install`, `pnpm dev`, `pnpm test`
+- From the repository root, run `npm test -- path/to/file.test.ts` for a focused test.
 ```
 
-### File-Scoped Commands
-Per-file commands are faster and cheaper than full project builds. Always include when available:
-```markdown
-## File-Scoped Commands
-| Task | Command |
-|------|---------|
-| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |
-| Lint | `pnpm eslint path/to/file.ts` |
-| Test | `pnpm jest path/to/file.test.ts` |
-```
+over:
 
-### Commit Attribution
-Always include this section. Agents should use their own identity:
 ```markdown
-## Commit Attribution
-AI commits MUST include:
-```
-Co-Authored-By: (the agent model's name and attribution byline)
-```
-Example: `Co-Authored-By: Claude Sonnet 4 <noreply@example.com>`
+- Make sure tests pass and follow best practices.
 ```
 
-### Key Conventions
-Project-specific patterns agents must follow. Keep brief.
+Link to maintained documentation instead of copying it. Distinguish required
+checks from optional, slow, privileged, or deployment-only checks.
 
-## Optional Sections
+### 5. Validate before handoff
 
-Add only if truly needed:
-- API route patterns (show template, not explanation)
-- CLI commands (table format)
-- File naming conventions
-- Project structure hints (point to critical files, flag legacy code to avoid)
-- Monorepo overrides (subdirectory `AGENTS.md` files override root)
+1. Re-read each changed `AGENTS.md` completely.
+2. Remove contradictions, duplicate rules, placeholders, and stale claims.
+3. Confirm every mentioned file and directory exists.
+4. Cross-check commands against manifests or CI, and run safe, proportionate
+   checks when useful.
+5. If nested files changed, confirm each contains only subtree-specific rules
+   and does not conflict accidentally with the root.
+6. Review the diff as a maintainer: every added line should change an agent's
+   decision or prevent a realistic mistake.
 
-## Anti-Patterns
+Report the files changed, evidence used, checks actually run, and unresolved
+uncertainty. Never say a command was tested when it was only read from config.
 
-Omit these:
-- "Welcome to..." or "This document explains..."
-- "You should..." or "Remember to..."
-- Linter/formatter rules already in config files (`.eslintrc`, `biome.json`, `ruff.toml`)
-- Listing installed skills or plugins (agents discover these automatically)
-- Full project-wide build commands when file-scoped alternatives exist
-- Obvious instructions ("run tests", "write clean code")
-- Explanations of why (just say what)
-- Long prose paragraphs
+## Examples
 
-## Example Structure
+### Create a focused root file
 
-```markdown
-# Agent Instructions
+Evidence found:
 
-## Package Manager
-Use **pnpm**: `pnpm install`, `pnpm dev`
+- `package-lock.json` selects npm.
+- `package.json` defines `lint`, `typecheck`, and `test` scripts.
+- CI runs those three checks from the repository root.
+- `src/generated/` is produced by `npm run generate`.
 
-## Commit Attribution
-AI commits MUST include:
-```
-Co-Authored-By: (the agent model's name and attribution byline)
-```
+A useful result might include:
 
-## File-Scoped Commands
-| Task | Command |
-|------|---------|
-| Typecheck | `pnpm tsc --noEmit path/to/file.ts` |
-| Lint | `pnpm eslint path/to/file.ts` |
-| Test | `pnpm jest path/to/file.test.ts` |
+```markdown
+# Agent instructions
 
-## API Routes
-[Template code block]
+## Commands
+- Run commands from the repository root.
+- Install with `npm ci`.
+- For handoff, run `npm run lint`, `npm run typecheck`, and `npm test`.
 
-## CLI
-| Command | Description |
-|---------|-------------|
-| `pnpm cli sync` | Sync data |
+## Generated code
+- Do not edit `src/generated/` directly; update its source and run `npm run generate`.
 ```
 
+Do not add a package manager, command, or generated-file rule that the evidence
+did not establish.
+
+### Revise without erasing policy
+
+If an existing file has accurate release restrictions but a stale test
+command, change only the stale command and any directly affected explanation.
+Preserve the release restrictions, even when a shorter replacement would look
+cleaner.
+
+## Best Practices
+
+- Keep instructions concise enough to scan, but let repository complexity
+  determine length.
+- Prefer repository-specific decisions over generic engineering advice.
+- Include targeted commands when the project supports them; do not invent a
+  file-scoped invocation for a tool that only supports suite-level runs.
+- State where commands run and whether they modify files.
+- Reference formatter and linter config instead of restating every rule.
+- Make tool-specific files additive when their semantics differ; do not assume
+  all agents interpret formats or precedence identically.
+
+## Security & Safety Notes
+
+- Treat this as a state-changing skill because it may edit repository files.
+  Review the diff before handoff.
+- Never include secrets, credentials, internal URLs, personal data, or local
+  environment values in agent instructions.
+- Do not run deployment, publication, database mutation, history rewrite, or
+  other consequential commands merely to validate documentation.
+- Preserve approval gates already present in repository policy.
+- Do not upload private repository instructions to third-party services. Ask
+  for explicit consent before transmitting any repository content externally.
+
+## Common Pitfalls
+
+- **Guessing commands:** infer tools from manifests and CI, not popularity.
+- **Forcing one layout:** a symlink or a fixed section list may erase
+  tool-specific or maintainer-authored guidance.
+- **Overwriting an existing file:** make the smallest evidence-backed change.
+- **Copying the README:** include only information that changes agent behavior.
+- **Duplicating nested files:** keep shared guidance at the root and local
+  differences near the relevant code.
+- **Claiming validation that did not run:** distinguish inspection from
+  execution in the handoff.
+
 ## Limitations
-- Use this skill only when the task clearly matches the scope described above.
-- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
-- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
+
+- Repository evidence can be incomplete or contradictory; ask when a material
+  policy choice cannot be resolved safely.
+- A documented command may still require credentials, services, or operating
+  system support that are unavailable locally.
+- AGENTS.md support and precedence vary across coding tools; verify the target
+  tool when interoperability matters.
+- This skill improves instruction quality but cannot prove that every future
+  agent will follow the file correctly.
+
+## Related Skills and Tools
+
+- `@agents-generator` - packaged generation, dry-run, update, and backup modes.
+- `@folder-specific-claude-and-agents-md` - deeper guidance for scoped
+  Claude/AGENTS instruction layouts.
+- [agents.md](https://agents.md/) - public format and scope guidance.

package/bundled-skills/docs/README.md

@@ -19,6 +19,7 @@
 - [`users/kiro-integration.md`](users/kiro-integration.md)
 - [`users/visual-guide.md`](users/visual-guide.md)
 - [`users/local-config.md`](users/local-config.md)
+- [`users/skills-library-overview.md`](users/skills-library-overview.md)
 
 ## Contributors
 

package/bundled-skills/docs/integrations/jetski-cortex.md

@@ -1,9 +1,9 @@
 ---
 title: Jetski/Cortex + Gemini Integration Guide
-description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,107+ skills."
+description: "Use agentic-awesome-skills with Jetski/Cortex without hitting context-window overflow with 2,108+ skills."
 ---
 
-# Jetski/Cortex + Gemini: safe integration with 2,107+ skills
+# Jetski/Cortex + Gemini: safe integration with 2,108+ skills
 
 > **Custom-host integration:** This guide documents a low-level, direct-manifest lazy loader for Jetski/Cortex and similar hosts. For Codex or Claude Code, the recommended path is [AAS Core](../users/aas-core.md), which provides neutral, deterministic catalog retrieval and validates exact agent-selected IDs through a bounded, read-only MCP server.
 
@@ -25,7 +25,7 @@ Never do:
 - concatenate all `SKILL.md` content into a single system prompt;
 - re-inject the entire library for **every** request.
 
-With 2,107+ skills, this approach fills the context window before user messages are even added, causing truncation.
+With 2,108+ skills, this approach fills the context window before user messages are even added, causing truncation.
 
 ---
 

package/bundled-skills/docs/integrations/jetski-gemini-loader/README.md

@@ -23,7 +23,7 @@ This example shows one way to integrate **agentic-awesome-skills** with a Jetski
 - How to enforce a **maximum number of skills per turn** via `maxSkillsPerTurn`.
 - How to choose whether to **truncate or error** when too many skills are requested via `overflowBehavior`.
 
-This pattern avoids context overflow when you have 2,107+ skills installed.
+This pattern avoids context overflow when you have 2,108+ skills installed.
 
 Manifest contract references:
 

package/bundled-skills/docs/maintainers/repo-growth-seo.md

@@ -29,7 +29,7 @@ Preferred homepage:
 Preferred social preview:
 
 - lead with `AAS Core` and the profile → stack → plan flow;
-- present `2,107+ Agentic Skills` as supporting catalog evidence, not a second product;
+- present `2,108+ Agentic Skills` as supporting catalog evidence, not a second product;
 - mention Codex and Claude as the current Core agent path, with broader host compatibility as distribution support;
 - avoid dense text and tiny logos that disappear in social cards.
 

package/bundled-skills/docs/maintainers/skills-update-guide.md

@@ -72,7 +72,7 @@ The update process refreshes:
 - Canonical skills index (`skills_index.json`)
 - Compatibility mirror (`data/skills_index.json`)
 - Web app skills data (`apps\web-app\public\skills.json`)
-- All 2,107+ skills from the skills directory
+- All 2,108+ skills from the skills directory
 
 ## When to Update
 

package/bundled-skills/docs/users/aas-core.md

@@ -31,7 +31,7 @@ AAS MCP does not scan the repository and does not decide which skills are best.
 > **Release boundary:** AAS Core landed after release 14.6.0. Use an exact Core-capable release rather than an unreviewed moving tag.
 
 ```bash
-npm exec --yes --ignore-scripts --package=agentic-awesome-skills@16.5.0 -- aas mcp configure \
+npm exec --yes --ignore-scripts --package=agentic-awesome-skills@16.6.0 -- aas mcp configure \
   --host codex \
   --scope user \
   --config /absolute/path/to/codex/config.toml \

package/bundled-skills/docs/users/bundles.md

@@ -1064,4 +1064,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: June 2026 | Total Skills: 2,107+ | Total Bundles: 58_
+_Last updated: June 2026 | Total Skills: 2,108+ | Total Bundles: 58_

package/bundled-skills/docs/users/claude-code-skills.md

@@ -17,7 +17,7 @@ Configure AAS Core for Claude Code, describe the task and constraints, let Claud
 - It lets Claude search the verified local catalog without loading the full library into context.
 - It preserves Claude's exact selection without using metadata as an eligibility gate.
 - It keeps MCP discovery read-only and CLI changes approval-gated.
-- It includes 2,107+ skills instead of a narrow single-domain starter pack.
+- It includes 2,108+ skills instead of a narrow single-domain starter pack.
 - It supports the standard `.claude/skills/` path and the Claude Code plugin marketplace flow.
 - It also ships generated bundle plugins so teams can install focused packs like `Essentials` or `Security Developer` from the marketplace metadata.
 - It includes onboarding docs, bundles, and workflows so new users do not need to guess where to begin.

package/bundled-skills/docs/users/gemini-cli-skills.md

@@ -12,7 +12,7 @@ Install into the Gemini skills path, then ask Gemini to apply one skill at a tim
 
 - It installs directly into the expected Gemini skills path.
 - It includes both core software engineering skills and deeper agent/LLM-oriented skills.
-- It helps new users get started with bundles and workflows rather than forcing a cold start from 2,107+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 2,108+ files.
 - It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
 
 ## Install Gemini CLI Skills

package/bundled-skills/docs/users/kiro-integration.md

@@ -18,7 +18,7 @@ Kiro is AWS's agentic AI IDE that combines:
 
 Kiro's agentic capabilities are enhanced by skills that provide:
 
-- **Domain expertise** across 2,107+ specialized areas
+- **Domain expertise** across 2,108+ specialized areas
 - **Best practices** from Anthropic, OpenAI, Google, Microsoft, and AWS
 - **Workflow automation** for common development tasks
 - **AWS-specific patterns** for serverless, infrastructure, and cloud architecture

package/bundled-skills/docs/users/skills-library-overview.md

@@ -0,0 +1,87 @@
+# The Full Skill Library: At-a-Glance Overview
+
+Agentic Awesome Skills ships a verified catalog of **2,107 skills** in `skills/<skill-id>/SKILL.md`. This page is a curated high-level map of the whole library: how skills are organized, the main capability areas and their approximate sizes, the risk labels you will encounter, and the authoritative surfaces to browse when you need the complete, current list.
+
+The authoritative, machine-generated catalog is [`CATALOG.md`](../../CATALOG.md). This overview is a hand-maintained index; it can lag the catalog after a release, so treat `CATALOG.md` and `skills_index.json` as the source of truth for counts and exact skill lists.
+
+## How the library is organized
+
+Every skill directory contains a `SKILL.md` whose frontmatter drives discovery:
+
+| Field | Purpose |
+| --- | --- |
+| `name` | Canonical skill id, e.g. `email-issue-fixer` |
+| `description` | Short purpose and trigger summary shown in search surfaces |
+| `category` | Thin grouping used by UI/search (see notes below) |
+| `tags` | Free-form keywords for search |
+| `risk` | One of `none`, `safe`, `critical`, `offensive`, or `unknown` |
+| `source` / `source_type` | Provenance of the skill content |
+| `date_added` | When the skill entered the registry |
+
+The full registry is exposed through three consistent surfaces:
+
+- [`CATALOG.md`](../../CATALOG.md) — human-readable catalog grouped by category.
+- `skills_index.json` — the legacy compatibility manifest (documented in [`discovery-manifest.md`](discovery-manifest.md)).
+- `data/catalog.json` — structured catalog used by the catalog app and AAS Core.
+
+> The `category` field is loose and historically fragmented (hundreds of skills are unclassified). Use `tags`, full-text search, and the AAS Core `search_skills` tool instead of relying on the category field as a taxonomy.
+
+## Capability areas
+
+The table below groups the real catalog data into editorial capability areas so you can find the region of the library that matches your task. Counts are approximate and change as the catalog evolves.
+
+| Capability area | Approx. skills | What you will find |
+| --- | ---: | --- |
+| Development & code quality | 480 | General, frontend, backend, mobile and fullstack development; language-specific guidance; code review and quality patterns |
+| Other & uncategorized | 330 | Small, niche, or legacy skills without a clean category label |
+| Cloud & infrastructure | 215 | Cloud platforms, DevOps, databases, operations, and ML infrastructure |
+| AI, agents & ML | 205 | Agent workflows, orchestration, evaluation, prompt engineering, and voice agents |
+| Automation, productivity & workflow | 190 | Task automation, workflows, browser automation, productivity, and collaboration |
+| Content, writing & creative | 160 | Writing, design, graphics, media, video, and presentation skills |
+| Business, product & research | 160 | Strategy, planning, product, project management, legal, finance, research, education, and health |
+| Security & pentesting | 85 | Security engineering, offensive testing, and defensive hardening |
+| Marketing, growth & SEO | 70 | Campaigns, analytics, SEO, growth, and app-store optimization |
+| Data & document processing | 65 | Data science, engineering, spreadsheets, documents, and knowledge management |
+| Testing & reliability | 55 | Test authoring, automation, reliability, and quality engineering |
+| Meta, authoring & special | 35 | Meta skills, skill authoring, and general-purpose helper skills |
+| API & integrations | 30 | Connectors and automation built around third-party APIs |
+| Gaming & blockchain | 25 | Game development, blockchain, and cryptocurrency |
+
+## Risk labels
+
+Every skill carries a `risk:` label in its frontmatter:
+
+| Risk | Meaning |
+| --- | --- |
+| `none` | No elevated risk; plain productivity guidance |
+| `safe` | Generally safe; local or low-impact operations |
+| `critical` | Privileged, destructive, or high-impact operations (code execution, deployments, pipelines) |
+| `offensive` | Offensive security / penetration-testing content; review the security guardrails before use |
+| `unknown` | Legacy or unclassified content that predates the risk-labeling scheme |
+
+Of the current catalog, roughly **1,090 are `critical`**, **850 are `safe`**, **100 are `none`**, and **60 are `offensive`**.
+
+Read [`SECURITY_GUARDRAILS.md`](../../docs/SECURITY_GUARDRAILS.md) and the [`security-guardrails`](../../docs/contributors/security-guardrails.md) contributor guide before invoking anything marked `critical` or `offensive`.
+
+## How to find the right skill
+
+1. **Search the full catalog** — with AAS Core running, use `search_skills`/`get_skill`; see the [usage guide](usage.md).
+2. **Browse the generated catalog** — [`CATALOG.md`](../../CATALOG.md) lists every skill by category with description, risk, source, and tags.
+3. **Use bundles as editorial shortlists** — see [bundles](bundles.md) for curated packs like the Web Wizard.
+4. **Use the tool-specific guides** — [Claude Code](claude-code-skills.md), [Codex CLI](codex-cli-skills.md), [Cursor](cursor-skills.md), and [Gemini CLI](gemini-cli-skills.md) include starter picks.
+
+## Distribution surfaces
+
+The same skills reach you through several channels, all backed by the same source tree:
+
+- **Full library** — direct install of the complete catalog (`~/.agents/skills/` by default).
+- **Plugins** — root and bundle plugins for Claude Code and Codex (see [plugins](plugins.md)).
+- **AAS Core** — agent-owned, reproducible selection validated against the catalog.
+
+## Related pages
+
+- [Usage guide](usage.md) — compose and use a skill stack.
+- [AAS Core](aas-core.md) — agent-owned catalog search and selection.
+- [Discovery manifest](discovery-manifest.md) — the machine-readable `skills_index.json` contract.
+- [Bundles](bundles.md) — curated skill packs.
+- [Security skills](security-skills.md) — guidance for security-relevant skills.

package/bundled-skills/docs/users/usage.md

@@ -39,7 +39,7 @@ If you came in through a **Claude Code** or **Codex** plugin instead of AAS Core
 
 When you ran `npx agentic-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 2,107+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 2,108+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
 ✅ **Made them available** to your AI assistant
 ❌ **Did NOT enable them all automatically** (they're just sitting there, waiting)
 
@@ -231,7 +231,7 @@ Let's actually use a skill right now. Follow these steps:
 
 ## Direct-install Step 5: Pick Skills Manually
 
-Don't try to use all 2,107+ skills at once. Here's a sensible approach:
+Don't try to use all 2,108+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -362,7 +362,7 @@ Usually no, but if your AI doesn't recognize a skill:
 
 ### "Can I load all skills into the model at once?"
 
-No. Even though you have 2,107+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 2,108+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 

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

@@ -40,7 +40,7 @@ agentic-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 2,107+ skills live here
+├── 📁 skills/                          ← 2,108+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -53,7 +53,7 @@ agentic-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (2,107+ total)
+│   └── ... (2,108+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -106,7 +106,7 @@ agentic-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  2,107+ SKILLS          │
+                    │  2,108+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -207,7 +207,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (2,107+ total)                │
+│   └── ... (2,108+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/email-issue-fixer/SKILL.md

@@ -0,0 +1,115 @@
+---
+name: email-issue-fixer
+description: "Fix small email mistakes without touching the writer's voice, and strip tracking parameters from links on request. Always returns the corrected draft plus a change list."
+category: writing
+risk: safe
+source: self
+source_type: self
+date_added: "2026-09-01"
+author: whoisabhishekadhikari
+tags: [email, proofreading, grammar, links]
+---
+
+# Email Issue Fixer
+
+Fix the small mistakes that make an email look careless, without touching the writer's voice or what the email commits to. Always return the corrected draft plus a list of what changed.
+
+## When to Use
+
+- Use when the user asks to "fix my email", "check the grammar before I send", "proofread this email", or any pre-send cleanup of a draft.
+- Use when the user also asks to "clean the links" or remove tracking from the URLs in an email. Link cleaning is never automatic.
+- Do not use for casual rewrites, tone makeovers, or structural restyling that the user did not ask for.
+
+## Pass 1: correctness only
+
+Fix these:
+
+- Duplicated words ("a a", "the the") and wrong articles. Choose a/an by sound, not spelling: "an hour", "a university", "a one-time offer".
+- Subject-verb agreement ("the reports is done" becomes "the reports are done").
+- Wrong-word slips: your/you're, its/it's, than/then, affect/effect, their/there.
+- Capitalization, doubled spaces, missing or doubled punctuation.
+
+Leave these alone. They are voice, not errors:
+
+- Sentence fragments, contractions, one-line paragraphs.
+- Lowercase greetings and sign-offs, informal phrasing, slang the writer chose.
+- Repetition used for emphasis.
+
+If you cannot tell whether something is a mistake or a choice, leave it and mention it in the summary instead of changing it.
+
+Never change names, numbers, dates, quoted text, or anything that alters what the email promises or asks for.
+
+## Pass 2: links (only when the user asks)
+
+Do not touch links during a normal proofread. Clean them only when the user asks for it.
+
+When asked, remove only these unambiguous tracking keys:
+
+- `utm_source`, `utm_medium`, `utm_campaign`, `utm_term`, `utm_content`, `mc_cid`, `mc_eid`, `fbclid`, `gclid`, `igshid`, `_hsenc`, `_hsmi`
+
+Keep every other parameter. Values like `id`, `page`, `v`, `q`, or anything unfamiliar are often what makes the link work. When in doubt, keep it.
+
+Treat `ref`, `ref_src`, and similarly generic keys as ambiguous: they are sometimes attribution, sometimes application state the link needs to work. Do not strip them automatically. Only remove them when context confirms they are attribution, or ask the writer first.
+
+Do not delete whole links. Do not delete a link because it appears twice; signature links and repeated calls to action are usually deliberate.
+
+Flag rather than fix: shortened links (bit.ly and similar), unfamiliar domains, and any query string that looks like a token, session ID, or credential. Point them out and let the writer decide.
+
+If a query parameter looks like a credential, token, or session ID, do not echo its value anywhere in the output. Keep the link only by replacing the sensitive value with a placeholder such as `[REDACTED]` (for example `?auth=[REDACTED]`), list the redaction in "Changes made", and tell the writer to re-enter the real value before sending. If they prefer, advise rotating the leaked value first.
+
+## Always return
+
+- The corrected email, in the same format and layout it arrived in.
+- A "Changes made" list, one line per change.
+- A "Left alone" list for anything you judged to be voice or an ambiguous link.
+- If nothing needed fixing, say so plainly rather than inventing changes.
+
+## Never
+
+- Send, schedule, or file the email. Hand the draft back for the writer to send.
+- Repeat credentials, tokens, or personal details found inside links.
+- Rewrite for tone, length, or structure unless asked. If the user wants that, ask what direction they want first.
+
+## Examples
+
+### Articles and agreement
+
+Input:
+
+```text
+Please find attached a a copy of the report. Our sales team achieved a amazing quarter.
+```
+
+Output:
+
+```text
+Please find attached a copy of the report. Our sales team achieved an amazing quarter.
+```
+
+Changes made:
+
+- a a to a (duplicated word)
+- a amazing to an amazing (vowel sound)
+
+### Link cleaning
+
+Input:
+
+```text
+https://app.example.com/reports?utm_source=newsletter&utm_medium=email&id=123
+```
+
+Output:
+
+```text
+https://app.example.com/reports?id=123
+```
+
+Changes made:
+
+- Removed 2 tracking parameters (utm_source, utm_medium)
+- Kept id=123, which the link needs to open the right report
+
+## Limitations
+
+This reads and edits text only. It cannot judge whether the email's facts, tone, or timing are right. That stays with the writer.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-skills-collection",
-  "version": "4.0.49",
+  "version": "4.0.51",
   "description": "OpenCode CLI plugin that automatically downloads and keeps skills up to date.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/skills_index.json

@@ -1319,12 +1319,12 @@
   {
     "id": "agents-md",
     "path": "skills/agents-md",
-    "category": "ai-ml",
+    "category": "development",
     "name": "agents-md",
-    "description": "This skill should be used when the user asks to \"create AGENTS.md\", \"update AGENTS.md\", \"maintain agent docs\", \"set up CLAUDE.md\", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.",
+    "description": "Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.",
     "risk": "critical",
     "source": "community",
-    "date_added": null,
+    "date_added": "2026-03-06",
     "plugin": {
       "targets": {
         "codex": "supported",
@@ -17901,6 +17901,35 @@
       "strategy"
     ]
   },
+  {
+    "id": "email-issue-fixer",
+    "path": "skills/email-issue-fixer",
+    "category": "writing",
+    "name": "email-issue-fixer",
+    "description": "Fix small email mistakes without touching the writer's voice, and strip tracking parameters from links on request. Always returns the corrected draft plus a change list.",
+    "risk": "safe",
+    "source": "self",
+    "date_added": "2026-09-01",
+    "plugin": {
+      "targets": {
+        "codex": "supported",
+        "claude": "supported"
+      },
+      "setup": {
+        "type": "none",
+        "summary": "",
+        "docs": null
+      },
+      "reasons": []
+    },
+    "source_type": "self",
+    "tags": [
+      "email",
+      "proofreading",
+      "grammar",
+      "links"
+    ]
+  },
   {
     "id": "email-security",
     "path": "skills/email-security",