Android Debugging
rcosteira79/android-skills
Android and KMP debugging techniques for crashes, ANRs, memory leaks, R8 traces, Gradle failures and Compose recomposition, built on finding the root cause first.
Agent skill
Slay the Amethyst Feedback Diagnosis
Reads Slay the Amethyst diagnostics bundles to decide whether a problem comes from the launcher, a mod or the device, citing exact files and lines.
Install Slay the Amethyst Feedback Diagnosis
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .claude/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .claude/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosisType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .agents/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .agents/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .cursor/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .cursor/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ModinMobileSTS/SlayTheAmethystModded.git --path .opencode/skills/sts-feedback-diagnosis--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .gemini/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .gemini/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .github/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .github/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ModinMobileSTS/SlayTheAmethystModded sts-feedback-diagnosis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ModinMobileSTS/SlayTheAmethystModded.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/sts-feedback-diagnosis .opencode/skills/sts-feedback-diagnosis && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sts-feedback-diagnosis" agent skill from https://github.com/ModinMobileSTS/SlayTheAmethystModded/tree/main/.opencode/skills/sts-feedback-diagnosis into .opencode/skills/sts-feedback-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sts-feedback-diagnosis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sts-feedback-diagnosis- GitHub stars
- 406
- Token cost
- ~2.6k tokens
- SKILL.md length
- 961 words
- Files
- 4 (incl. scripts, references)
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Reads Slay the Amethyst diagnostics bundles to decide whether a problem comes from the launcher, a mod or the device, citing exact files and lines.
- Works in 8 steps: Treat the package as evidence for one… → Run python… → Identify the bundle kind first → …
- Inspecting a feedback or crash package sent by a player
- SKILL.md covers Quick Start, Workflow, Project-Specific Clues and Resources
- Runs Python scripts from its folder; calls python and rg
What it does
The skill analyzes diagnostics bundles from the Slay the Amethyst launcher: feedback reports, crash reports, JVM log exports and performance logs, supplied as zip files or extracted sts folders. It treats the package as evidence for one report, runs a script that summarizes the structure for both the current and a legacy layout, and first identifies which kind of bundle it has.
Reading order starts with the user's issue body and request JSON, then the latest log and its summary, the crash summary, signal dump and process exit trace, and the launcher settings and device info before any blame is assigned. The agent extracts the user's claim first, treats generated log summaries as helpers only because they can miss performance problems, and ends with a verdict of launcher, mod, device or driver, mixed or undetermined.
When your agent uses it
- Inspecting a feedback or crash package sent by a player
- Deciding whether a crash comes from the launcher, a mod or the device
- Reading launcher settings and device info alongside the logs
- Writing an evidence-backed diagnosis with a concrete next step
Example prompts
- “Diagnose this feedback report zip and tell me whether the launcher, a mod or the device caused the crash.”
- “Look at sts-crash-report-example.zip and cite the log lines that matter.”
- “Check the launcher settings and device info before assigning blame for this slowdown.”
Requirements
- Python to run inspect_feedback_report.py
- A diagnostics bundle zip or an extracted sts folder
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Treat the package as evidence for one report, not as a generic log dump.
- Run python scripts/inspect_feedback_report.py for a structural summary. It resolves both the current layout and the legacy sts/jvm_logs/…
- Identify the bundle kind first
- Read sts/feedback/issue_body.md first when present, and use sts/feedback/request.json for structured values.
- Inspect sts/logs/latest.log. It is the most recent run. Archived sts/logs/jvm_log_*.log are older runs, newest first, up to 5 slots.
- Use sts/crash/summary.txt, sts/logs/last_signal_dump.txt, and sts/logs/process_exit_trace.txt for crash/native-exit evidence.
- Use sts/info/launcher_settings.txt and sts/info/device_info.txt before assigning blame; many problems are driven by renderer…
- End with a verdict: launcher, mod, device/driver, mixed, or undetermined, citing exact files and lines.
What it can do on your machine
Read from SKILL.md and the folder at commit cc0f053. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonrg
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Slay the Amethyst Feedback Diagnosis loads about 2.6k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 181 tokens; SKILL.md has 961 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 961 words (~2,596 tokens).
- name
- sts-feedback-diagnosis
Files
SKILL.md and 3 other files (scripts, references) in .opencode/skills/sts-feedback-diagnosis of ModinMobileSTS/SlayTheAmethystModded.
- SKILL.md
- agents/openai.yaml
- references/bundle-and-triage.md
- scripts/inspect_feedback_report.py
Open the folder on GitHubat commit cc0f053
Compare with similar skills
Slay the Amethyst Feedback Diagnosis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Slay the Amethyst Feedback Diagnosis this skillModinMobileSTS/SlayTheAmethystModded | 406 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Android Debuggingrcosteira79/android-skills | 153 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Mobile App Debuggingsecondsky/claude-skills | 227 | — | ~513 | Automated safety check: Pass | MIT | |
| Maui AI DebuggingRedth/Maui.Gtk | 101 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Magicnet Device DebuggingLIghtJUNction/MagicNet | 186 | — | ~2.9k | Automated safety check: Notes | MIT | |
| Inspect Network TrafficHedvigInsurance/android | 154 | — | ~756 | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Mobile App Debugging
secondsky/claude-skills
Mobile app debugging for iOS, Android, cross-platform frameworks.
Maui AI Debugging
Redth/Maui.Gtk
End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent.
Magicnet Device Debugging
LIghtJUNction/MagicNet
Debug and verify MagicNet on a real Android root device. An agent skill from LIghtJUNction/MagicNet.
Inspect Network Traffic
HedvigInsurance/android
Read the HTTP and GraphQL calls a debug build of the Android app made, with request and response bodies, status codes, timings and errors, over adb.
AppsFlyer Unity Bridge Debugging
AppsFlyerSDK/appsflyer-unity-plugin
Traces a failing call or callback between C# and the native Android or iOS wrappers of the AppsFlyer Unity plugin to find the first broken link.
More from ModinMobileSTS/SlayTheAmethystModded
Android Mobile UI Design
ModinMobileSTS/SlayTheAmethystModded
Designs and reviews Android screens with attention to touch ergonomics, adaptive layouts, accessibility, state handling and an implementation handoff.
Compose Performance Audit
ModinMobileSTS/SlayTheAmethystModded
Audits Jetpack Compose screens for performance problems, from recomposition scope and stability to lazy list keys and effects, and proposes minimal fixes with ways to verify them.
Jetpack Compose Patterns
ModinMobileSTS/SlayTheAmethystModded
Applies practical Jetpack Compose patterns to Android UI code: state hoisting, one-way data flow, side effects, modifiers, theming and testable composables.
Related
Works with
Categories
Questions about Slay the Amethyst Feedback Diagnosis
What does Slay the Amethyst Feedback Diagnosis do?
Reads Slay the Amethyst diagnostics bundles to decide whether a problem comes from the launcher, a mod or the device, citing exact files and lines. The skill analyzes diagnostics bundles from the Slay the Amethyst launcher: feedback reports, crash reports, JVM log exports and performance logs, supplied as zip files or extracted sts folders. It treats the package as evidence for one report, runs a script that summarizes the structure for both the current and a legacy layout, and first identifies which kind of bundle it has.
When should I use Slay the Amethyst Feedback Diagnosis?
Slay the Amethyst Feedback Diagnosis fits situations like: inspecting a feedback or crash package sent by a player; deciding whether a crash comes from the launcher, a mod or the device; reading launcher settings and device info alongside the logs; writing an evidence-backed diagnosis with a concrete next step.
How do I install Slay the Amethyst Feedback Diagnosis in Claude Code?
Run `npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a claude-code`. Or copy the skill folder (.opencode/skills/sts-feedback-diagnosis in ModinMobileSTS/SlayTheAmethystModded) into .claude/skills/sts-feedback-diagnosis in your project. Claude Code loads it when a task matches its description.
How do I install Slay the Amethyst Feedback Diagnosis in Codex?
Run `npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a codex`. Or copy the skill folder (.opencode/skills/sts-feedback-diagnosis in ModinMobileSTS/SlayTheAmethystModded) into .agents/skills/sts-feedback-diagnosis in your project. Codex loads it when a task matches its description.
Can I use Slay the Amethyst Feedback Diagnosis in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ModinMobileSTS/SlayTheAmethystModded --skill sts-feedback-diagnosis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sts-feedback-diagnosis, .gemini/skills/sts-feedback-diagnosis, .github/skills/sts-feedback-diagnosis and .opencode/skills/sts-feedback-diagnosis in your project.
What does Slay the Amethyst Feedback Diagnosis need to run?
Going by SKILL.md and its folder, Slay the Amethyst Feedback Diagnosis needs Python for the scripts in its folder and the command-line tools its instructions call (python and rg). Our summary lists: Python to run inspect_feedback_report.py; A diagnostics bundle zip or an extracted sts folder.
Does Slay the Amethyst Feedback Diagnosis access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Slay the Amethyst Feedback Diagnosis safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Slay the Amethyst Feedback Diagnosis use?
Slay the Amethyst Feedback Diagnosis has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Slay the Amethyst Feedback Diagnosis use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.
What are the alternatives to Slay the Amethyst Feedback Diagnosis?
Skills that share tags, products or a category with Slay the Amethyst Feedback Diagnosis: Android Debugging (rcosteira79/android-skills, 153 stars), Mobile App Debugging (secondsky/claude-skills, 227 stars), Maui AI Debugging (Redth/Maui.Gtk, 101 stars) and Magicnet Device Debugging (LIghtJUNction/MagicNet, 186 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Slay the Amethyst Feedback Diagnosis?
ModinMobileSTS (a GitHub organization) maintains it in ModinMobileSTS/SlayTheAmethystModded, which has 406 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 8, 2026.
Source: ModinMobileSTS/SlayTheAmethystModded on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.