# Ase Arch Discover > > - **Type:** Skill - **Install:** `agentstack add skill-rse-ase-ase-arch-discover` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [rse](https://agentstack.voostack.com/s/rse) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [rse](https://github.com/rse) - **Source:** https://github.com/rse/ase/tree/master/plugin/skills/ase-arch-discover - **Website:** https://ase.tools ## Install ```sh agentstack add skill-rse-ase-ase-arch-discover ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md Discover Components $ARGUMENTS *Discover* additional, *third-party components* (libraries/frameworks) for the technology stack to *provide* the *needed functionality* . 1. 1. Derive the needed from the , but keep the functionality description very *brief* but still *precise*. 2. If is not clear, not precise, or not specific enough, let the *user interactively choose* the intended functionality. In the following, you *MUST* *NOT* use your built-in tool! Instead, you *MUST* just show a custom dialog according to the expanded `custom-dialog` definition. You *MUST* closely follow this definition: Functionality: Which functionality should the components provide? : (grounded candidate functionality 1) : (grounded candidate functionality 2) : (grounded candidate functionality 3) : (grounded candidate functionality 4) Then use the and its corresponding grounded candidate functionality to adjust accordingly. 3. Display the determined final functionality with just the following : **FUNCTIONALITY**: 2. 1. Determine the used technology stack: 1. If a file `package.json` is found in the top-level directory of the project and contains an entry `typescript` under `dependencies` or `devDependencies`, then TypeScript. 2. Else, if a file `package.json` is found in the top-level directory of the project, then JavaScript. 3. Else, if a file `build.gradle.kts` or `settings.gradle.kts` is found in the top-level directory, then Kotlin. 4. Else, if a file `build.gradle` is found in the top-level directory and is applying `kotlin`, `org.jetbrains.kotlin.jvm`, `kotlin-android`, or `kotlin-multiplatform` plugins, then Kotlin. 5. Else, if a file `pom.xml` is found in the top-level directory and contains `kotlin-maven-plugin` or `kotlin-stdlib` dependencies, then Kotlin. 6. Else, if a file `pom.xml` or `build.gradle` is found in the top-level directory of the project, then Java. 7. Else, use Unknown. 2. Display the determined final technology stack with just the following : **TECHNOLOGY STACK**: 3. 1. If is "Unknown", the technology stack could not be determined and no component discovery backend is available. Inform the user with just the following and then *STOP* the entire flow (do not perform any further steps): **RESULT**: technology stack could not be determined -- component discovery is only supported for JavaScript, TypeScript, Java, and Kotlin projects. 2. From and , derive essential keywords (L=1-M), which allow you to search for suitable components. 3. Determine the *candidate pool size* as twice the (i.e. = 2 × ). Each discovery source below may fetch up to candidates so that the later ranking and trimming (which alone is governed by ) has a meaningful set to choose from. In the to be discovered candidate set of components (K=1-C, where C is the merged and deduplicated candidate count), remember the component name as , the official package name as , the latest version as , the stars as , the created date as , the last updated date as , the total number of downloads in the last month as . 4. If is "JavaScript" or "TypeScript": 1. Based on the essential keywords (L=1-M), use the `ase-meta-search` skill in a subagent to *generally* discover an initial set of a maximum of *NPM packages* and at least their real name and their unique package names . 2. Use the shell command `npm search --json --searchlimit "" [...] ""` to *specifically* discover an additional set of a maximum of *NPM packages* and at least their unique package names , based on the essential keywords (L=1-M). Merge the results into the already existing result set, but deduplicate entries. 5. If is "Java" or "Kotlin": 1. Based on the essential keywords (L=1-M), use the `ase-meta-search` skill in a subagent to *generally* discover an initial set of a maximum of *Maven packages* and at least their real name and their unique Maven coordinates of the form `groupId:artifactId`. 2. Use the shell command `curl -s 'https://search.maven.org/solrsearch/select?q=+[...]+&rows=&wt=json'` to *specifically* discover an additional set of a maximum of *Maven packages* and at least their unique Maven coordinates (i.e. `:` from each result document's `g` and `a` fields), based on the essential keywords (L=1-M). Merge the results into the already existing result set, but deduplicate entries by Maven coordinate. 6. Call the `ase_component_info(stack: "", components: [ "", ..., "" ])` tool of the `ase` MCP server *once* for the entire candidate set of discovered packages. The tool dispatches internally on and fetches all metadata in maximum parallel and returns an array of objects `{ name, version, created, updated, repository, stars, downloads, rank }`. For each component (K=1-C) read from its corresponding entry: from `version`, from `updated`, from `created`, from `repository`, from `stars` (numeric or `N.A.`), from `downloads` (numeric or `N.A.`) and from `rank` (numeric). 7. Sort, in descending order, the discovered candidate components (K=1-C) by their `rank` field and trim the result list to just a maximum of total components, which establishes the final retained set (K=1-N, where N is at most ). All subsequent steps operate solely on this retained set. 8. For each component (K=1-N), research and then decide which *one* of *USP* (Unique Selling Point -- what makes it unique), *Crux* (what you should notice), or *Gotcha* (what you should not stumble over) is its single most distinguishing perspective, and remember this as an (K=1-N) formatted like `: ` where is one of `USP`, `Crux`, or `Gotcha` and is a 1-6 word hint. Do not output anything. 4. 1. Display the determined, individual components as a Markdown *table* with just the following and do not output anything else: **COMPONENT HINTS**: | ⚑ *Component* | ▣ *Package* | ⚖ *Hint* | | :------------ | :------------- | :-------- | | **** | `` | | [...] | **** | `` | | 2. Display the discovered components as a Markdown *table* with just the following : **COMPONENT RANKING**: | ⚑ *Component* | ▣ *Package* | ❖ *Version* | ↓ *Downloads* | ⎈ *Stars* | ⏲ *Updated* | ☆ *Created* | | :------------ | :------------- | -----------: | -----------------: | -------------: | :--------------- | :----------- | | **** | `` | | **** | **** | **** | | [...] | **** | `` | | **** | **** | **** | | ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [rse](https://github.com/rse) - **Source:** [rse/ase](https://github.com/rse/ase) - **License:** Apache-2.0 - **Homepage:** https://ase.tools Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-rse-ase-ase-arch-discover - Seller: https://agentstack.voostack.com/s/rse - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.