plugins-copilot/java-toolkit/skills/jar-explore/SKILL.md
List, search, and read files inside JARs (META-INF, .properties, XML, manifests, resources). Use instead of raw `unzip`, `jar tf`, or `jar xf`. For class search and decompilation, use the maven-indexer MCP server bundled with this plugin.
npx skillsauth add st0nefish/claude-toolkit jar-exploreInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use the plugin's bundled jar-explore tool for reading raw JAR contents
rather than unzip, jar tf, or jar xf. Do not construct plugin-root
Bash paths manually; if the current Copilot CLI session cannot resolve
the installed plugin path, say so plainly instead of guessing.
For class search and decompilation, use the maven-indexer MCP server
bundled with this plugin (run /java-toolkit:java-toolkit start first if
the Docker stack isn't running):
search_classesget_class_details (type: "source")search_artifactssearch_implementationsThis tool covers what the MCP server doesn't: listing raw entries, regex search within a JAR, and reading arbitrary non-class files.
The tool exposes three subcommands:
<jar> — list every entry in the JAR.<jar> <pattern> — list entries matching a case-insensitive
extended regex (e.g. ClassName, META-INF.*\.properties).<jar> <entry> — print the entry's contents to stdout (no
extraction to disk). Use for META-INF/MANIFEST.MF,
META-INF/spring.factories, application.properties, or any embedded
source file.search_artifacts) or the project build output.list <jar> or search <jar> <pattern>.read <jar> <entry>.development
Start work from your description — explore the codebase and plan
data-ai
Multi-phase, multi-agent feature workflow: spec → plan → refine → divide → execute → review. Invoke when the user escalates a session-start/session-issue flow to orchestration, or asks to run a non-trivial feature (multiple files, design ambiguity, cross-cutting concerns, correctness-critical paths) through the full multi-agent workflow. For small fixes, prefer session-start.
tools
Browse open issues, pick one, and start work on it
tools
Interact with GitHub and Gitea issue trackers and CI systems. List and show issues, file bugs, comment on issues or PRs, list and show pull requests, and fetch CI run logs — all from any repo context without leaving the session.