opencode-skills-collection 4.0.5 → 4.0.6

package/bundled-skills/docs/users/ai-agent-skills.md

@@ -1,24 +1,24 @@
 # AI Agent Skills
 
-If you are researching **AI agent skills** on GitHub, the useful first decision is whether you want deterministic project-level composition or manual selection from a catalog.
+If you are researching **AI agent skills** on GitHub, the useful first decision is whether you want agent-owned project selection with reproducible state or manual catalog browsing.
 
-Agentic Awesome Skills is built around **AAS Core**: Codex or Claude inspects the project, sends an explicit profile to the local AAS MCP, and receives an explainable recommendation from the verified catalog. The agent proposes `aas-stack.json`; the CLI validates it and produces an immutable preview plan before any target change.
+Agentic Awesome Skills is built around **AAS Core**: Codex or Claude inspects the project, searches and reads the complete local catalog, chooses exact skill IDs, and uses `compose_stack` to pin them in `aas-stack.json`. The CLI validates that agent-owned state and produces an immutable preview plan before any target change.
 
 The catalog, plugins, bundles, workflows, and direct installer remain supporting content and distribution surfaces. AAS does not scan the repository, call a remote model, or write project files through MCP.
 
 ## What to look for in an AI agent skill system
 
 - **Explicit input boundary**: is project analysis performed by the coding agent and passed as a reviewable profile?
-- **Deterministic recommendation**: can the same profile, policy, runtime, and catalog identity reproduce the same result?
-- **Explainability**: do recommendations include evidence, exclusions, uncovered goals, and unknowns?
+- **Agent-owned selection**: can the coding agent search and read every skill before choosing exact IDs?
+- **Reproducibility**: can the chosen IDs be pinned to a catalog identity and replayed without a metadata eligibility gate?
 - **Durable desired state**: can the approved selection be recorded independently of the agent conversation?
 - **Preview before change**: can the system validate the manifest and produce an exact plan without changing the target?
 - **Source and compatibility evidence**: are provenance, risk, host support, and distribution boundaries explicit?
 
 ## When Agentic Awesome Skills is a good fit
 
-- You use Codex or Claude and want a small, policy-controlled stack for a real project.
-- You want local search and recommendation without repository scanning or remote-model calls by AAS.
+- You use Codex or Claude and want the agent to choose a focused stack for a real project.
+- You want complete local search and inspection without repository scanning or remote-model calls by AAS.
 - You need a reviewable `aas-stack.json` and CLI validation and planning before target changes.
 - You also value a broad catalog and multiple distribution options around the Core workflow.
 
@@ -43,6 +43,6 @@ The catalog, plugins, bundles, workflows, and direct installer remain supporting
 
 ## Quick recommendation
 
-- Choose **AAS Core** if you want local, deterministic, explainable skill-stack composition from an explicit project profile to a preview plan.
+- Choose **AAS Core** if you want complete local catalog access, agent-owned selection, reproducible stack composition, and a preview plan.
 - Choose direct distribution if you already know the exact skills you want or your host does not support the Core path.
-- Choose a smaller curated repository if a fixed editorial shortlist matters more than project-specific recommendation and durable desired state.
+- Choose a smaller curated repository if a fixed editorial shortlist matters more than complete catalog access and durable desired state.

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

@@ -1,16 +1,16 @@
 # Best Claude Code Skills on GitHub
 
-If you are looking for the **best Claude Code skills on GitHub**, there is no single perfect repository for every user. The right choice depends on whether you want deterministic project-level composition, curated discovery, or official reference material.
+If you are looking for the **best Claude Code skills on GitHub**, there is no single perfect repository for every user. The right choice depends on whether you want complete catalog access with Claude-owned selection, curated discovery, or official reference material.
 
-## Best for deterministic project stacks
+## Best for agent-selected project stacks
 
 ### 1. [sickn33/agentic-awesome-skills](https://github.com/sickn33/agentic-awesome-skills)
 
-Best for teams and individual developers who want Claude to send an explicit project profile to a local, read-only MCP, receive an explainable recommendation, and produce a reviewable `aas-stack.json` before CLI validation and planning.
+Best for teams and individual developers who want Claude to inspect a project, search and read the complete catalog through a local read-only MCP, choose exact IDs, and produce a reviewable `aas-stack.json` before CLI validation and planning.
 
 Choose this if you want:
 
-- local deterministic recommendation with explicit policy and evidence;
+- complete local catalog access with Claude-owned selection;
 - durable desired state plus immutable plan preview;
 - a broad catalog, plugins, bundles, workflows, and direct distribution around Core.
 

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

@@ -1062,4 +1062,4 @@ Found a skill that should be in a bundle? Or want to create a new bundle? [Open
 
 ---
 
-_Last updated: June 2026 | Total Skills: 1,968+ | Total Bundles: 58_
+_Last updated: June 2026 | Total Skills: 1,969+ | Total Bundles: 58_

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

@@ -1,23 +1,23 @@
 # AAS Core with Claude Code
 
-For Claude Code, the recommended AAS path is **AAS Core**: a local, agent-first control plane for catalog search, deterministic stack recommendation, manifest inspection, and preview-first planning.
+For Claude Code, the recommended AAS path is **AAS Core**: a local, agent-first control plane for complete catalog search, Claude-owned skill selection, manifest inspection, and preview-first planning.
 
-The local AAS MCP is read-only. It can help Claude search and inspect the catalog or propose a minimal `aas-stack.json`, while validation, planning, and any approved changes stay in the AAS CLI lifecycle.
+The local AAS MCP is read-only. It lets Claude search and read every catalog skill, then validate and pin Claude's chosen IDs in `aas-stack.json`; planning and any approved changes stay in the AAS CLI lifecycle.
 
 Start with the [AAS Core guide](aas-core.md). The Claude plugin marketplace and direct skill installation remain supported delivery paths after you know which skills you want.
 
-> **Preview status:** Search, recommendation, manifest validation, and planning are the documented preview path. Stop after plan review; apply and recovery are not certified preview safety claims.
+> **Preview status:** Complete catalog search, agent-owned selection, manifest validation, and planning are the documented path. Stop after plan review; apply and recovery remain experimental.
 
 ## How to use Agentic Awesome Skills with Claude Code
 
-Configure AAS Core for Claude Code, describe the task and constraints, review the recommended stack, then preview the CLI plan. Core does not install or mutate through MCP. The current documented preview path stops after plan review.
+Configure AAS Core for Claude Code, describe the task and constraints, let Claude choose exact IDs from the complete catalog, then review the composed stack and preview the CLI plan. Core does not install or mutate through MCP.
 
 ## Why use this repo for Claude Code
 
 - It lets Claude search the verified local catalog without loading the full library into context.
-- It produces deterministic recommendations with inspectable factors and evidence.
+- 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 1,968+ skills instead of a narrow single-domain starter pack.
+- It includes 1,969+ 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.
@@ -63,7 +63,7 @@ test -d .claude/skills || test -d ~/.claude/skills
 With AAS Core configured:
 
 ```text
-Use AAS to recommend a minimal skill stack for this security review. Propose the aas-stack.json and preview the plan without applying it.
+Inspect this security-review project, search and read the complete AAS catalog, and choose the exact skill IDs you judge most useful. Use compose_stack with a project profile, show me the schema 2 aas-stack.json, inspect it, and preview the plan without applying it.
 ```
 
 After installing or activating a chosen skill, direct invocation still works:

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

@@ -1,27 +1,27 @@
 # AAS Core with Codex CLI
 
-For Codex, the recommended AAS path is **AAS Core**: a local, agent-first control plane that lets Codex search the verified catalog, inspect skills, and recommend a minimal stack before anything is installed.
+For Codex, the recommended AAS path is **AAS Core**: a local, agent-first control plane that lets Codex search and read every catalog skill, choose the exact IDs itself, and preserve that selection before anything is installed.
 
-The AAS MCP server is local and read-only. Codex can call `search_skills`, `get_skill`, `recommend_stack`, `inspect_stack`, and `diff_stack`; changes remain in the CLI lifecycle, where `validate` and `plan` are preview operations and `apply` requires explicit approval.
+The AAS MCP server is local and read-only. Codex can call `search_skills`, `get_skill`, `compose_stack`, `inspect_stack`, and `diff_stack`; changes remain in the CLI lifecycle, where `validate` and `plan` are preview operations and `apply` requires explicit approval.
 
 Start with the [AAS Core guide](aas-core.md). Direct skill installation and Codex plugins remain supported when you already know exactly which payload you want.
 
-> **Preview status:** Search, recommendation, manifest validation, and planning are the documented preview path. Stop after plan review; apply and recovery are not certified preview safety claims.
+> **Preview status:** Complete catalog search, agent-owned selection, manifest validation, and planning are the documented path. Stop after plan review; apply and recovery remain experimental.
 
 ## How to use Agentic Awesome Skills with Codex CLI
 
 Configure AAS Core for Codex, then describe the real task instead of manually searching a large directory. The normal flow is:
 
 1. Codex discovers the local AAS MCP tools.
-2. Codex searches the catalog and requests a deterministic recommendation for your task profile.
-3. Codex proposes a minimal `aas-stack.json` for you to review.
+2. Codex searches and reads the complete catalog, then chooses the exact skills using its project understanding.
+3. Codex calls `compose_stack` and proposes `aas-stack.json` for you to review.
 4. The AAS CLI validates the manifest and previews the exact plan.
 5. Stop after reviewing the plan unless you are deliberately participating in controlled preview development.
 
 ## Why use this repo for Codex CLI
 
-- It gives Codex native, local discovery and recommendation through MCP.
-- It keeps catalog evidence, stack intent, validation, and planning deterministic and inspectable.
+- It gives Codex native, complete local catalog discovery through MCP.
+- It keeps the agent's exact selection, project profile, validation, and planning inspectable.
 - It separates read-only agent tools from approval-gated CLI mutations.
 - It is strong for local repo work where you want to move from planning to implementation to verification without changing libraries.
 - It includes both general-purpose engineering skills and deeper specialist tracks.
@@ -62,7 +62,7 @@ test -d .codex/skills || test -d ~/.codex/skills
 With AAS Core configured:
 
 ```text
-Use AAS to recommend the smallest skill stack for designing and testing this parser change. Show me the proposed aas-stack.json and preview the plan; do not apply it.
+Inspect this parser project, search and read the complete AAS catalog, and choose the exact skill IDs you judge most useful for designing and testing the change. Use compose_stack with a project profile, show me the schema 2 aas-stack.json, inspect it, and preview the plan; do not apply it.
 ```
 
 After installing or activating a chosen skill, direct invocation still works:

package/bundled-skills/docs/users/discovery-manifest.md

@@ -2,7 +2,7 @@
 
 This page documents the legacy-compatible `skills_index.json` contract used by custom host integrations and lazy loaders.
 
-For Codex and Claude Code, use [AAS Core](aas-core.md) instead of wiring a host directly to this repository manifest. Core uses a verified local catalog and exposes bounded, read-only MCP tools for search, inspection, and recommendation. The raw manifest remains useful for integrations that do not have an AAS Core host adapter.
+For Codex and Claude Code, use [AAS Core](aas-core.md) instead of wiring a host directly to this repository manifest. Core exposes every skill in a verified local catalog through bounded, read-only MCP tools for search, inspection, and agent-owned composition. The raw manifest remains useful for integrations that do not have an AAS Core host adapter.
 
 ## Manifest contract (v1)
 

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

@@ -8,19 +8,19 @@
 
 ### What is AAS Core?
 
-AAS Core is the deterministic, versioned control plane that turns this repository's catalog into an approved project stack. Codex or Claude can inspect a repository, send an explicit profile to the local read-only AAS MCP, explain the resulting recommendation, and propose an `aas-stack.json`. The `aas` CLI then validates the manifest and previews an immutable plan.
+AAS Core is the versioned control plane that gives Codex or Claude complete local catalog access and turns the agent's exact selection into a reproducible project stack. The agent inspects the repository, searches and reads skills, chooses exact IDs, and uses `compose_stack` to propose `aas-stack.json`. The `aas` CLI then validates the manifest and previews an immutable plan.
 
 AAS Core is the product; the approved `aas-stack.json` and immutable plan are its durable artifacts. Skills and the catalog provide content and evidence, MCP and CLI are interfaces, Workbench is a review surface, and plugins, bundles, workflows, and installers provide curation or distribution around Core. Start with [AAS Core](aas-core.md).
 
 ### Is AAS Core fully certified?
 
-No. The current public claim is **AAS Agent-First Preview**: it helps Codex and Claude compose a local, explainable, reproducible skill stack. Full-catalog recommendation quality and transactional apply/recovery safety are not yet certified.
+Core supports complete local catalog search and inspection, agent-owned selection, reproducible composition, manifest validation, and plan preview. Transactional apply/recovery safety remains outside the supported claim.
 
 `stack apply` and `stack recover` are experimental, disabled by default, and are not supported preview safety claims. The recommended public flow stops after reviewing `stack validate` and `stack plan` output.
 
 ### Does AAS upload my repository or use another model?
 
-No. The agent may inspect the project using its normal local capabilities, but AAS MCP does not scan the repository. It receives an explicit allowlisted profile and runs deterministic recommendation against a bundled or verified local catalog. MCP is local stdio, read-only, offline-capable, and contains no model credentials or telemetry.
+No. The agent inspects the project using its normal local capabilities. AAS MCP only exposes the complete bundled or verified local catalog and validates agent-selected IDs; it does not scan the repository, rank skills, or enforce selection policy. MCP is local stdio, read-only, offline-capable, and contains no model credentials or telemetry.
 
 ### What are "skills" exactly?
 
@@ -29,7 +29,7 @@ Skills are specialized instruction files that teach AI assistants how to handle
 
 ### Do I need to install every skill?
 
-**No.** With AAS Core, ask the agent to recommend a small stack that matches your project, target, goals, and risk policy. On a broad direct install, all skills may be present locally while the host loads only the skills it invokes.
+**No.** With AAS Core, ask the agent to inspect the project and choose the exact skills from the complete catalog. On a broad direct install, all skills may be present locally while the host loads only the skills it invokes.
 
 Use [Starter Packs](bundles.md) as human-curated presets when you want a fixed starting point.
 
@@ -50,7 +50,7 @@ Start from:
 ### What is the difference between skills, AAS MCP, and the CLI?
 
 - **Skills** are reusable `SKILL.md` playbooks that guide an AI assistant through a workflow.
-- **AAS MCP** is the local, read-only discovery and composition interface to AAS Core. It searches and inspects the verified catalog, recommends a stack, and checks or compares manifests.
+- **AAS MCP** is the local, read-only discovery and composition interface to AAS Core. It exposes every catalog skill, reads requested content, validates agent-selected IDs, and checks or compares manifests.
 - **The `aas` CLI** manages explicit lifecycle operations such as catalog status/update, MCP configuration, stack validation, planning, and diagnostics.
 
 Other MCP servers may grant access to APIs, services, databases, or hosted systems. AAS MCP has a narrower boundary: it does not install, apply, update catalogs, scan repositories, or modify configuration through tool calls.
@@ -137,7 +137,7 @@ _Always check the Risk label and review the code._
 
 ### How do I start with AAS Core?
 
-Use the pinned `aas` binary from a release whose notes explicitly state that it includes AAS Core to preview and approve local MCP configuration for Codex or Claude. Release 14.6.0 predates Core; Core-capable packages begin with the 15.x line. Restart the host if needed, then ask the agent to recommend and explain a stack without applying it. The command template and trust boundaries are in [AAS Core](aas-core.md).
+Use the pinned `aas` binary from a release whose notes explicitly state that it includes AAS Core to preview and approve local MCP configuration for Codex or Claude. Release 14.6.0 predates Core; Core-capable packages begin with the 15.x line. Restart the host if needed, then ask the agent to search the full catalog, choose exact IDs, and compose a stack without applying it. The command template and trust boundaries are in [AAS Core](aas-core.md).
 
 The package publishes separate `agentic-awesome-skills`, `aas`, and `aas-mcp` binaries. Use the explicit `aas` binary for Core lifecycle commands; the legacy `agentic-awesome-skills` entrypoint remains the direct installer.
 
@@ -160,7 +160,7 @@ If you get a 404 from npm, use: `npx github:sickn33/agentic-awesome-skills`
 git clone https://github.com/sickn33/agentic-awesome-skills.git .agent/skills
 ```
 
-For direct skill distribution, the installer CLI performs a lighter shallow clone of the current library. Manual `git clone` remains appropriate when you want the full repository history or plan to contribute from the same checkout. For Codex or Claude users who want project-specific recommendation, start with AAS Core instead of treating a full-library install as the primary product path.
+For direct skill distribution, the installer CLI performs a lighter shallow clone of the current library. Manual `git clone` remains appropriate when you want the full repository history or plan to contribute from the same checkout. For Codex or Claude users who want project-specific agent selection with reproducible state, start with AAS Core instead of treating a full-library install as the primary product path.
 
 **Tool-specific paths:**
 
@@ -378,7 +378,7 @@ Examples:
 
 ### How do I know which skill to use?
 
-With AAS Core, describe the project outcome and constraints, then ask the agent to call `recommend_stack`. Review its coverage, evidence, exclusions, discovery candidates, and unknowns before accepting the proposed IDs.
+With AAS Core, describe the project outcome and constraints, then ask the agent to search and read the full catalog, choose exact IDs, and call `compose_stack`. Review the agent's rationale and proposed IDs before accepting the stack.
 
 For manual discovery:
 

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 1,968+ files.
+- It helps new users get started with bundles and workflows rather than forcing a cold start from 1,969+ 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/getting-started.md

@@ -1,15 +1,15 @@
 # Getting Started with AAS Core
 
-**New here? Start with AAS Core and let your agent compose a small, reviewable skill stack for the project.**
+**New here? Start with AAS Core and let your agent choose a reviewable skill stack from the complete catalog.**
 
-> **Preview status:** AAS Agent-First Preview supports local, explainable stack composition with Codex and Claude. Full-catalog recommendation quality and transactional apply/recovery safety are not yet certified.
+> **Product boundary:** Codex or Claude owns skill selection. AAS Core provides complete local catalog access, reproducible composition, validation, and plan preview; apply and recovery remain experimental.
 
 ## Start with AAS Core
 
-AAS Core is the primary product path. Codex or Claude inspects your project, calls the local read-only AAS MCP, explains a deterministic catalog recommendation, and proposes an `aas-stack.json`. You review the exact policy and skill IDs before using the `aas` CLI to validate the manifest and preview a plan.
+AAS Core is the primary product path. Codex or Claude inspects your project, searches and reads the complete catalog through the local read-only AAS MCP, chooses the exact skill IDs, and uses `compose_stack` to propose an `aas-stack.json`. You review those IDs before using the `aas` CLI to validate the manifest and preview a plan.
 
 ```text
-project -> agent -> local AAS MCP -> recommendation -> aas-stack.json
+project -> agent -> full local catalog -> agent selection -> compose_stack -> aas-stack.json
         -> human review -> validate -> plan preview
 ```
 
@@ -167,7 +167,7 @@ For Claude Code, use:
 For Codex, this repository also ships a root plugin plus bundle plugins through the repo-local metadata described in [plugins.md](plugins.md).
 
 **Q: Do I need to install every skill?**
-A: No. With AAS Core, ask the agent to recommend a small stack under an explicit policy. On the legacy direct-install path, you can install the broad library while the host reads only invoked or relevant skills. **Starter Packs** in [bundles.md](bundles.md) remain human-curated discovery aids.
+A: No. With AAS Core, ask the agent to inspect the project and choose exact IDs from the complete catalog. On the legacy direct-install path, you can install the broad library while the host reads only invoked or relevant skills. **Starter Packs** in [bundles.md](bundles.md) remain human-curated discovery aids.
 
 **Q: Can I make my own skills?**
 A: Yes! Use the **@skill-creator** skill to build your own.

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 1,968+ specialized areas
+- **Domain expertise** across 1,969+ 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/plugins.md

@@ -2,7 +2,7 @@
 
 Release `9.0.0` adds first-class plugin distributions for both **Claude Code** and **Codex**.
 
-This page explains how plugins fit beneath **AAS Core**, the recommended orchestration layer for Codex and Claude Code. Plugins and direct installs deliver skill payloads; Core helps an agent discover, recommend, inspect, validate, and plan a minimal stack before delivery.
+This page explains how plugins fit beneath **AAS Core**, the orchestration layer for Codex and Claude Code. Plugins and direct installs deliver skill payloads; Core exposes the complete catalog and validates, records, and plans the exact stack chosen by the agent.
 
 ## What a plugin is in this repo
 
@@ -139,7 +139,7 @@ Bundle-specific Codex plugins are generated alongside the root plugin so you can
 Choose **AAS Core first** if:
 
 - you want Codex or Claude Code to search and inspect the local catalog
-- you want a deterministic recommendation instead of manually browsing thousands of skills
+- you want Codex or Claude to search the complete catalog and preserve its exact selection
 - you want a reviewable `aas-stack.json` and preview plan before any change
 - you want read-only MCP discovery separated from approval-gated CLI operations
 

package/bundled-skills/docs/users/skills-vs-mcp-tools.md

@@ -3,9 +3,9 @@
 The short version is:
 
 - **Skills** are reusable `SKILL.md` playbooks that tell an AI assistant how to execute a workflow.
-- **AAS MCP** is the local, read-only interface through which an agent searches the verified AAS catalog, inspects evidence, and composes a proposed stack.
+- **AAS MCP** is the local, read-only interface through which an agent retrieves the verified AAS catalog without ranking, inspects evidence, and records its exact selected IDs in a proposed stack.
 - **Other MCP tools** connect an assistant to external systems such as APIs, databases, browsers, or hosted services.
-- **The `aas` CLI** validates durable stack intent and previews exact lifecycle operations under human control.
+- **The `aas` CLI** validates the durable project profile and agent-selected stack, then previews exact lifecycle operations under human control.
 
 These surfaces are complementary. AAS Core connects them around the approved `aas-stack.json` manifest.
 
@@ -34,12 +34,12 @@ It exposes exactly:
 
 - `search_skills`;
 - `get_skill`;
-- `recommend_stack`;
+- `compose_stack`;
 - `inspect_stack`;
 - `diff_stack`;
 - the `aas://skills/{id}` resource template.
 
-The agent inspects the project using its normal local capabilities and sends AAS an explicit, allowlisted profile. AAS MCP does not scan the repository itself. It returns structured factors, evidence, coverage, exclusions, discovery candidates, and unknowns from a bundled or verified local catalog.
+The agent inspects the project using its normal local capabilities, searches and reads the complete catalog, and chooses the exact skills. AAS MCP does not scan the repository itself, and Core does not rank or exclude candidates. Catalog metadata is informational only.
 
 AAS MCP is local stdio, process-per-session, read-only, offline-capable, and contains no model credentials or telemetry. Its tool calls do not install or remove skills, apply a stack, update catalogs, or edit host configuration.
 
@@ -61,18 +61,18 @@ The `aas` CLI is the explicit operational interface for:
 
 - catalog status and updates;
 - MCP configuration;
-- stack initialization and deterministic recommendation from an explicit profile;
+- validation and composition of an agent-selected stack;
 - manifest validation;
 - plan creation and read-only diagnostics.
 
-The durable artifact is `aas-stack.json`, which pins catalog identity, targets, intent, policy, and exact skill IDs. The agent may propose it; the user reviews it. `stack validate` checks it, and `stack plan` creates an immutable preview bound to the observed managed state and exact operations.
+The durable artifact is `aas-stack.json`, which pins catalog identity, targets, the project profile, and exact skill IDs. The agent proposes it; the user reviews it. It has no Core selection policy. `stack validate` checks it, and `stack plan` creates an immutable preview bound to the observed managed state and exact operations.
 
 `stack apply` and `stack recover` exist only for controlled preview development. They are experimental, disabled by default, and are not supported or certified preview safety claims.
 
 ## The easiest mental model
 
 - **Skills provide the operating guidance.**
-- **AAS MCP helps the agent select and explain the right guidance.**
+- **AAS MCP gives the agent complete catalog access and records the selection the agent makes.**
 - **`aas-stack.json` records what the user approved.**
 - **The CLI validates and previews the lifecycle.**
 - **Other MCP servers provide access to outside systems.**
@@ -83,7 +83,7 @@ Start with **AAS Core** when:
 
 - you use Codex or Claude with local MCP support;
 - you want the agent to compose a small stack from project evidence;
-- you need explicit risk/source/setup policy and a reproducible manifest;
+- you need complete catalog access and a reproducible manifest of the agent's exact selection;
 - you want a reviewable plan before any skill changes.
 
 Start with a **direct skill or specialized plugin** when:
@@ -96,7 +96,7 @@ Add **other MCP tools** when the work needs live access to APIs, services, datab
 
 ## Preview limits
 
-AAS Agent-First Preview helps Codex and Claude compose a local, explainable, reproducible skill stack. It does not claim certified full-catalog recommendation quality or transactional apply/recovery safety. Missing evidence is reported as `unknown`, and AAS may leave a goal uncovered rather than present a weak recommendation as certainty.
+AAS Core helps Codex and Claude search and read the complete local catalog, choose exact skill IDs, and preserve them in a reproducible stack. Metadata may be reported as unknown, but it is informational and never blocks selection or use. Apply and recovery remain experimental.
 
 ## Good next reads
 

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

@@ -1,19 +1,31 @@
 # Usage Guide: Compose and Use an AAS Skill Stack
 
-> **Recommended path:** let Codex or Claude use AAS Core to compose a small, policy-controlled stack. Direct installs and manual skill invocation remain supported alternatives.
+> **Recommended path:** let Codex or Claude inspect the project, search and read the complete AAS catalog, and choose the exact skills. AAS Core records and validates that agent-owned selection.
 
 ## Primary workflow: agent-first composition
 
-After configuring the local AAS MCP, ask your agent to inspect the repository and recommend a stack for the outcome you want:
+After configuring the local AAS MCP, ask your agent to inspect the repository and choose a stack for the outcome you want:
 
 ```text
-Inspect this repository and use the AAS MCP tools to recommend a small skill stack.
-Explain evidence, exclusions, and unknowns; propose an aas-stack.json; do not apply it.
+Inspect this repository and enumerate its primary capability areas. For each
+capability, search the complete AAS catalog, paginate or refine the query, and
+compare multiple plausible candidates with get_skill when available. Select at
+least one non-redundant valid skill per capability, explicitly report catalog
+gaps, and evaluate architecture/runtime, languages/frameworks, domain behavior,
+data/storage, integrations, testing/quality, security/privacy, UX/accessibility,
+deployment/operations, and maintenance workflow. Mark dimensions not applicable
+instead of silently omitting them. Do not stop at the first few matches or
+optimize for the smallest stack. Core has no semantic policy favoring a small
+stack; each manifest has a technical maximum of 128 selected skills. Only then
+use compose_stack with a project profile, inspect the schema 2 manifest returned
+in memory, and do not apply it.
 ```
 
-The agent should use `search_skills`, `get_skill`, and `recommend_stack`, then check the complete proposal with `inspect_stack` and correct every reported issue before presenting it. Review the resulting `aas-stack.json`, validate it with `aas stack validate`, and use `aas stack plan` to preview the exact operations without materializing skills or managed state in the target.
+The agent must use `search_skills` and `get_skill` across the complete catalog, build a capability-to-skill coverage map, continue searching while a primary capability remains uncovered, choose the exact IDs itself, call `compose_stack`, then check the in-memory proposal with `inspect_stack` before presenting it. All 1,968 current catalog skills remain individually searchable, readable, and selectable. A client or the CLI can persist the reviewed `aas-stack.json`; an audit-enabled flow can then call `export_selection_evidence`, validate it with `inspect_selection_evidence`, and atomically publish the manifest and separate `aas-selection-evidence.json` sidecar in an `artifact-dir`. Use `aas stack plan` to preview the exact operations without materializing skills or managed state in the target.
 
-The recommendation is deterministic and local. AAS MCP does not inspect the repository itself, install skills, update catalogs, or change configuration. See [AAS Core](aas-core.md) for setup, the exact tool boundary, CLI commands, and preview limitations.
+Selection evidence contains the raw `search_skills` queries observed during the MCP session. Do not place secrets, credentials, private source text, or personal data in catalog queries.
+
+Selection belongs to the coding agent. AAS MCP does not inspect the repository itself, rank or exclude skills, install skills, update catalogs, or change configuration. See [AAS Core](aas-core.md) for setup, the exact tool boundary, CLI commands, and preview limitations.
 
 `stack apply` and `stack recover` are experimental, disabled by default, and are not supported or certified preview safety claims.
 
@@ -21,13 +33,13 @@ The recommendation is deterministic and local. AAS MCP does not inspect the repo
 
 ## Alternative workflow: direct skill installation
 
-If you came in through a **Claude Code** or **Codex** plugin instead of AAS Core or a full library install, invoke individual skills in prompts. Plugins ship a fixed plugin-safe subset; AAS Core instead composes a project stack from the verified catalog and records it in `aas-stack.json`. See [plugins.md](plugins.md) for the distribution model.
+If you came in through a **Claude Code** or **Codex** plugin instead of AAS Core or a full library install, invoke individual skills in prompts. Plugins ship a fixed plugin-safe subset; AAS Core instead validates and records the exact stack the agent selected from the verified catalog in `aas-stack.json`. See [plugins.md](plugins.md) for the distribution model.
 
 ### What direct distribution provides
 
 When you ran `npx agentic-awesome-skills` or cloned the repository, you:
 
-✅ **Downloaded 1,968+ skill files** to your computer (default: `~/.agents/skills/`; or a custom path like `~/.agent/skills/` if you used `--path`)
+✅ **Downloaded 1,969+ 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)
 
@@ -219,7 +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 1,968+ skills at once. Here's a sensible approach:
+Don't try to use all 1,969+ skills at once. Here's a sensible approach:
 
 If you want a tool-specific starting point before choosing skills, use:
 
@@ -350,7 +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 1,968+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
+No. Even though you have 1,969+ skills installed locally, you should **not** concatenate every `SKILL.md` into a single system prompt or context block.
 
 The intended pattern is:
 
@@ -404,7 +416,7 @@ Use @skill-creator to help me build a custom skill for [your task]
 For the Core-first path:
 
 1. Configure the local MCP with the [AAS Core guide](aas-core.md).
-2. Ask the agent to recommend and explain a small stack.
+2. Ask the agent to search the complete catalog, choose exact IDs, and explain its selection.
 3. Review `aas-stack.json`, validate it, and preview the plan.
 
 For direct/manual use:

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

@@ -10,22 +10,22 @@ This guide shows the primary AAS Core workflow and the supporting catalog and di
 PROJECT
    │ inspected by Codex or Claude, not by AAS
    ▼
-EXPLICIT PROJECT PROFILE
+AGENT SEARCHES + READS COMPLETE LOCAL CATALOG
    │
    ▼
-AAS MCP ── search · inspect · recommend
+CODEX OR CLAUDE CHOOSES EXACT SKILL IDS
    │
    ▼
-AAS CORE + LOCAL VERIFIED CATALOG
-   │ evidence · exclusions · coverage · unknowns
+compose_stack ── validates · pins · never recommends
+   │
    ▼
-AGENT PROPOSES aas-stack.json
+AGENT PROPOSES aas-stack.json (no selection policy)
    │
    ├────────► WORKBENCH (optional browser-local review)
    ▼
 CLI VALIDATE ──► CLI PLAN ──► HUMAN REVIEW
 
-Supported preview path: stop after plan review.
+Supported path: stop after plan review.
 Apply and recovery remain experimental.
 ```
 
@@ -40,7 +40,7 @@ agentic-awesome-skills/
 ├── 📄 CONTRIBUTING.md                  ← Contributor workflow
 ├── 📄 CATALOG.md                       ← Full generated catalog
 │
-├── 📁 skills/                          ← 1,968+ skills live here
+├── 📁 skills/                          ← 1,969+ skills live here
 │   │
 │   ├── 📁 brainstorming/
 │   │   └── 📄 SKILL.md                 ← Skill definition
@@ -53,7 +53,7 @@ agentic-awesome-skills/
 │   │   └── 📁 2d-games/
 │   │       └── 📄 SKILL.md             ← Nested skills also supported
 │   │
-│   └── ... (1,968+ total)
+│   └── ... (1,969+ total)
 │
 ├── 📁 apps/
 │   └── 📁 web-app/                     ← Interactive browser
@@ -106,7 +106,7 @@ agentic-awesome-skills/
 
 ```
                     ┌─────────────────────────┐
-                    │  1,968+ SKILLS          │
+                    │  1,969+ SKILLS          │
                     └────────────┬────────────┘
                                  │
         ┌────────────────────────┼────────────────────────┐
@@ -207,7 +207,7 @@ If you want a workspace-style manual install instead, cloning into `.agent/skill
 │   ├── 📁 brainstorming/                 │
 │   ├── 📁 stripe-integration/            │
 │   ├── 📁 react-best-practices/          │
-│   └── ... (1,968+ total)                │
+│   └── ... (1,969+ total)                │
 └─────────────────────────────────────────┘
 ```
 

package/bundled-skills/docs/vietnamese/AAS_CORE.vi.md

@@ -1,27 +1,27 @@
 # AAS Core
 
-**AAS Core** là lớp điều khiển cục bộ, ưu tiên agent được khuyến nghị cho Agentic Awesome Skills. Core cho phép Codex hoặc Claude Code tìm kiếm và kiểm tra catalog cục bộ đã xác minh, tạo đề xuất stack tối thiểu theo quy tắc xác định, rồi trình bày `aas-stack.json` và kế hoạch CLI để người dùng xem trước khi có bất kỳ thay đổi nào.
+**AAS Core** là lớp điều khiển cục bộ, ưu tiên agent được khuyến nghị cho Agentic Awesome Skills. Core cho phép Codex hoặc Claude Code tìm kiếm và đọc catalog cục bộ đã xác minh, tự chọn chính xác các ID skill, rồi lưu lựa chọn đó trong `aas-stack.json` để người dùng xem trước trước khi có bất kỳ thay đổi nào. Core không xếp hạng hay đề xuất skill.
 
 > **Ranh giới phát hành:** Gói npm 14.6.0 đã phát hành trước AAS Core và không thể dùng để bootstrap Core. Các gói hỗ trợ Core bắt đầu từ dòng 15.x; chỉ dùng một phiên bản chính xác có release notes tuyên bố rõ rằng nó bao gồm AAS Core.
 
 ## Luồng sử dụng
 
 1. Dùng AAS CLI chính thức để cấu hình MCP stdio cục bộ cho Codex hoặc Claude Code.
-2. Cho phép agent gọi `search_skills`, `get_skill` và `recommend_stack`; chỉ dùng `inspect_stack` hoặc `diff_stack` khi cần.
-3. Xem lại tệp `aas-stack.json` do agent đề xuất.
+2. Cho phép agent gọi `search_skills` và `get_skill`, tự đánh giá kết quả theo ngữ nghĩa, rồi gọi `compose_stack` với `profile` và các ID đã chọn; dùng `inspect_stack` để xác minh và `diff_stack` khi cần so sánh.
+3. Xem lại tệp `aas-stack.json` schema 2 chứa `profile` và đúng thứ tự ID do agent chọn.
 4. Dùng AAS CLI để xác thực manifest và xem trước kế hoạch chính xác.
 5. Dừng lại sau khi xem kế hoạch; chỉ nghiên cứu các giai đoạn sau nếu bạn chủ động tham gia phát triển preview có kiểm soát.
 
 ## Ranh giới tin cậy
 
 - AAS MCP chạy cục bộ và chỉ đọc; MCP không cài đặt, xóa, áp dụng hay cập nhật nội dung.
-- Đề xuất dựa trên quy tắc xác định và bằng chứng trong catalog, không dựa trên một lệnh gọi mô hình ẩn khác.
+- Kết quả tìm kiếm đầy đủ, phân trang và có thứ tự catalog ổn định; chúng không chứa điểm số hay thứ hạng. Codex hoặc Claude Code tự đánh giá và chọn skill.
 - `validate` và `plan` là luồng preview hiện được ghi nhận. `apply` và `recover` bị tắt theo mặc định và chưa phải là cam kết an toàn đã được chứng nhận.
 - Danh tính catalog và runtime được xác minh cục bộ. Theo mặc định, dữ liệu dự án không được gửi tới dịch vụ AAS.
 
 ## Quan hệ với plugin và cài đặt trực tiếp
 
-AAS Core là lớp điều phối và ra quyết định. Plugin, plugin chuyên biệt và bản cài đặt thư viện đầy đủ vẫn là các cách phân phối nội dung skill. Với Codex và Claude Code, nên dùng Core để xác định stack tối thiểu trước, rồi mới chọn cách phân phối phù hợp.
+AAS Core là lớp truy cập catalog, ghi nhận lựa chọn và xác thực; Codex hoặc Claude Code ra quyết định ngữ nghĩa. Plugin, plugin chuyên biệt và bản cài đặt thư viện đầy đủ vẫn là các cách phân phối nội dung skill. Với Codex và Claude Code, nên dùng Core để lưu stack do agent chọn trước, rồi mới chọn cách phân phối phù hợp.
 
 Các công cụ chưa có adapter AAS Core vẫn có thể dùng cách cài đặt trực tiếp, plugin hoặc tích hợp manifest tùy chỉnh.
 

package/bundled-skills/docs/vietnamese/README.vi.md

@@ -2,7 +2,7 @@
 
 > **Ghép stack kỹ năng cục bộ, xác định cho coding agent: từ hồ sơ dự án tường minh đến kế hoạch có thể xem lại trước mọi thay đổi trên target.**
 
-Codex hoặc Claude tự kiểm tra dự án; AAS không quét repository. Agent gửi một hồ sơ tường minh tới AAS MCP cục bộ, chỉ đọc. AAS Core đánh giá hồ sơ và policy dựa trên catalog cục bộ đã xác minh, rồi agent đề xuất `aas-stack.json`; CLI xác thực manifest và tạo kế hoạch preview bất biến trước khi thay đổi kỹ năng.
+Codex hoặc Claude tự kiểm tra dự án; AAS không quét repository. Agent tìm kiếm catalog cục bộ đầy đủ theo thứ tự ổn định, tự đánh giá kết quả không có điểm số hay xếp hạng, rồi gửi `profile` cùng chính xác các ID đã chọn tới `compose_stack`. AAS Core ghi nhận lựa chọn trong `aas-stack.json` schema 2; CLI xác thực manifest và tạo kế hoạch preview bất biến trước khi thay đổi kỹ năng.
 
 > **Ranh giới phát hành:** Gói npm 14.6.0 đã phát hành trước AAS Core và không thể dùng để bootstrap Core. Các gói hỗ trợ Core bắt đầu từ dòng 15.x; chỉ dùng một phiên bản chính xác có release notes tuyên bố rõ rằng nó bao gồm Core. Luồng preview được hỗ trợ dừng sau khi xem kế hoạch; `apply` và `recover` vẫn mang tính thử nghiệm. [Tìm hiểu AAS Core](AAS_CORE.vi.md).
 
@@ -15,7 +15,7 @@ Codex hoặc Claude tự kiểm tra dự án; AAS không quét repository. Agent
 [![OpenCode](https://img.shields.io/badge/OpenCode-CLI-gray)](https://github.com/opencode-ai/opencode)
 [![Antigravity](https://img.shields.io/badge/Antigravity-DeepMind-red)](https://github.com/sickn33/agentic-awesome-skills)
 
-Catalog gồm **1,967+ kỹ năng `SKILL.md`**, plugin chuyên biệt, bundle, workflow và installer trực tiếp vẫn rất quan trọng. Chúng là lớp nội dung, tuyển chọn, phân phối và tương thích xung quanh AAS Core, không phải sản phẩm chính cạnh tranh với Core:
+Catalog gồm **1,968+ kỹ năng `SKILL.md`**, plugin chuyên biệt, bundle, workflow và installer trực tiếp vẫn rất quan trọng. Chúng là lớp nội dung, tuyển chọn, phân phối và tương thích xung quanh AAS Core, không phải sản phẩm chính cạnh tranh với Core:
 
 - 🟣 **Claude Code** (Anthropic CLI)
 - 🔵 **Gemini CLI** (Google DeepMind)