CI Failure Triage and Repair
Chachamaru127/claude-code-harness
Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.
A skill your agent uses to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix.
Install Analyze CI Failure
$ npx skills add MartinStyk/apk-analyzer --skill analyze-ci-failure -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install MartinStyk/apk-analyzer analyze-ci-failure --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/MartinStyk/apk-analyzer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .claude/skills/analyze-ci-failure && 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 "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .claude/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failureType 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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install MartinStyk/apk-analyzer analyze-ci-failure --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MartinStyk/apk-analyzer.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .agents/skills/analyze-ci-failure && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .agents/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install MartinStyk/apk-analyzer analyze-ci-failure --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MartinStyk/apk-analyzer.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .cursor/skills/analyze-ci-failure && 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 "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .cursor/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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/MartinStyk/apk-analyzer.git --path .claude/skills/analyze-ci-failure--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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install MartinStyk/apk-analyzer analyze-ci-failure --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MartinStyk/apk-analyzer.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .gemini/skills/analyze-ci-failure && 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 "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .gemini/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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 MartinStyk/apk-analyzer analyze-ci-failureInstalls 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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/MartinStyk/apk-analyzer.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .github/skills/analyze-ci-failure && 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 "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .github/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install MartinStyk/apk-analyzer analyze-ci-failure --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/MartinStyk/apk-analyzer.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/analyze-ci-failure .opencode/skills/analyze-ci-failure && 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 "analyze-ci-failure" agent skill from https://github.com/MartinStyk/apk-analyzer/tree/develop/.claude/skills/analyze-ci-failure into .opencode/skills/analyze-ci-failure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "analyze-ci-failure", 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
analyze-ci-failure- GitHub stars
- 370
- Token cost
- ~1.9k tokens
- SKILL.md length
- 924 words
- Files
- 1
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- GPL-3.0
At a glance
A skill your agent uses to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix.
- Works in 5 steps: Find the run → Check job-level status, not just the… → Pull only the failing job's log, then… → …
- Check GitHub Actions build status
- SKILL.md covers Workflows in this repo, Step 1 — Find the run, Step 2 — Check job-level… and Step 3 — Pull only the failing…, plus 3 more sections
- Calls gh; needs FIREBASE_TOKEN and SIGN_KEY
What it does
Analyze CI Failure is an agent skill from MartinStyk/apk-analyzer. Use to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix. Triggered by phrases like "check the latest build", "did CI pass", "why did the build fail", "check the GitHub Actions run", "analyze this workflow run", "check run <id", "check the build for this PR".
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering CI/CD and Failing and flaky tests. It works with GitHub Actions. The repository describes itself as: The most downloaded APK analysis app on Google Play. Detailed reports of every app on your device. No root, no ads, nothing leaves the phone. The licence is GPL-3.0.
When your agent uses it
- Check GitHub Actions build status
- Diagnose why a workflow run failed and propose a fix
Example prompts
- “check the latest build”
- “did CI pass”
- “why did the build fail”
- “/analyze-ci-failure”
Requirements
- A credential in FIREBASE_TOKEN
- A credential in SIGN_KEY
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d807559. 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
Shell commands in SKILL.md call:
gh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
FIREBASE_TOKENSIGN_KEYSIGN_KEY_STORE_PASSWORDSIGN_KEY_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Analyze CI Failure loads about 1.9k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 924 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from MartinStyk/apk-analyzer at commit d807559, republished under its GPL-3.0 licence (© MartinStyk). 924 words, ~1,879 tokens.
Download SKILL.mdSave it as
.claude/skills/analyze-ci-failure/SKILL.md (or your agent's skills folder).- name
- analyze-ci-failure
- description
- Use to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix. Triggered by phrases like "check the latest build", "did CI pass", "why did the build fail", "check the GitHub Actions run", "analyze this workflow run", "check run <id>", "check the build for this PR".
Skill: Analyze a GitHub Actions Run and Propose a Fix
Uses the
ghCLI (already authenticated) to inspect workflow runs on GitHub Actions, isolate the actual failing step from a noisy log, and turn it into a root cause + a proposed fix.
Workflows in this repo
They live at .github/workflows/.
| File | Name | Trigger | What it runs |
|---|---|---|---|
.github/workflows/ci.yml | Continuous integration | Push to or pull request against develop | Parallel verify and build-apk jobs; distribute on pushes after both pass |
.github/workflows/release.yml | Release | Push of a semantic version tag (X.Y.Z) | Parallel verify and build-release jobs; GitHub Release, Play Store beta, and Firebase App Distribution publish after both pass |
.github/workflows/agent-context.yml | Agent context | Context, skill, adapter, root-build, or module-graph changes against develop | validate: validateAgentContext |
Step 1 — Find the run
| Given | Command |
|---|---|
| "latest build" / "latest CI run" | gh run list --workflow ci.yml --limit 5 |
| "latest release run" | gh run list --workflow release.yml --limit 5 |
| "latest context check" | gh run list --workflow agent-context.yml --limit 5 |
| A run ID or run URL | gh run view <run-id> |
| A PR number | gh pr checks <pr-number> |
| Only failures | gh run list --status failure --limit 10 |
Step 2 — Check job-level status, not just the run-level conclusion
gh run view <run-id> prints a ✓/X per job — read this before pulling logs. The Android workflows
have parallel verification and artifact-build jobs followed by downstream distribution jobs. The
release workflow also has Play Store and GitHub Release jobs. Confirm the failed job and its
dependencies before assuming the cause; a downstream artifact failure may still originate in
build-apk or build-release.
Step 3 — Pull only the failing job's log, then filter for the signal
On macOS/Linux:
gh run view <run-id> --log-failed | grep -inE "error:|FAILURE:|Execution failed|exception|##\[error\]"gh run view <run-id> --log-failed | sed -n '<start>,<end>p'On Windows PowerShell:
gh run view <run-id> --log-failed |
Select-String -Pattern 'error:|FAILURE:|Execution failed|exception|##\[error\]' `
-CaseSensitive:$false `
-Context 5, 15If filtering finds nothing useful, the failure may be a plain BUILD FAILED with no separate error:
line — in that case find the last > Task :... line before the failure; that's the failing
Gradle task.
Step 4 — Known failure signatures in this repo
| Symptom in the log | Root cause | Fix |
|---|---|---|
Agent context validation failed | A module lacks scoped guidance, an AGENTS.md/CLAUDE.md pair is broken, skill metadata is invalid, a local context link is broken, or a Copilot adapter duplicates a shared skill | Follow each listed validation error, then rerun ./gradlew validateAgentContext |
BUILD FAILED with ktlint-style messages or Compose compile errors traceable to formatting | Unformatted/violating Kotlin broke compilation | Use the spotless-fix skill |
e: file:///path/to/File.kt:12:5 ... | Kotlin compiler error, points directly at file:line | Open the file, fix per AGENTS.md conventions |
Fetch Firebase google-services.json fails in either workflow | FIREBASE_TOKEN, FIREBASE_APP_ID, or FIREBASE_PROJECT_ID is missing/wrong, or the token cannot access the configured Firebase project/app | Use gh secret list to confirm all three exist. Secret values are masked and Firebase access cannot be repaired from logs; report the exact Firebase CLI error to the user |
Signing step fails in release.yml (sign_aab or sign_apk) | One of SIGN_KEY, SIGN_KEY_ALIAS, SIGN_KEY_STORE_PASSWORD, SIGN_KEY_PASSWORD repo secrets is missing/wrong, or the keystore is corrupt/mismatched with the alias | gh secret list to confirm all four exist; can't verify the keystore itself from CI logs — ask the user to check it locally |
Deploy to Play Store step fails with an auth/permission error | GOOGLE_SERVICE_ACCOUNT secret is missing, expired, or the service account lacks Play Console API access for sk.styk.martin.apkanalyzer | Check gh secret list; Play Console access itself can't be fixed from CI — flag to the user |
Distribute APK to Firebase App Distribution fails after a successful build | FIREBASE_TOKEN/FIREBASE_APP_ID is wrong, the token lacks access, or the internal-testers group is unavailable | Confirm both secrets exist with gh secret list, then report the Firebase CLI error; project permissions and tester groups require user access |
A future JDK bump to the Gradle toolchain (jvmToolchain(N), gradle-daemon-jvm.properties) isn't mirrored in one of the two workflows' setup-java step | Usually not the actual failure cause even if they briefly drift — gradle-daemon-jvm.properties has toolchainUrl.* entries for the foojay Disco API, so Gradle auto-downloads a matching JDK regardless of the JDK setup-java installed (needs the org.gradle.toolchains.foojay-resolver-convention plugin in settings.gradle.kts, which is applied). Don't assume a JDK mismatch is the root cause without other evidence | If you do suspect it, search the log for Downloading / Unpacking JDK lines from the toolchain auto-provisioning, or a No matching toolchains found error, before concluding this is the cause |
gradle: Execution failed for task ':...:compileDebugKotlin' or similar per-module compile task | Compile error scoped to one module | Narrow reproduction locally: ./gradlew :module:path:compileDebugKotlin |
Show full SKILL.md (211 more words)Show less
If a failure doesn't match this table, treat the filtered error:/FAILURE: line as authoritative
and reason from there — don't guess.
Step 5 — Reproduce and propose a fix
- Where possible, reproduce locally with the same Gradle task the workflow ran (see
run:steps in the workflow YAML) before proposing a fix — this repo's CI failures are almost always reproducible with./gradlew <same task>. - State the root cause in one sentence, citing the exact log line.
- Propose a minimal diff:
- Workflow YAML bug → confirm with the user before editing
.github/workflows/*.yml(CI/CD pipeline changes are a shared-system change — don't push them unasked). - Application/build code bug → fix the code per
AGENTS.mdconventions and run thespotless-fixskill if it's formatting-related.
- Workflow YAML bug → confirm with the user before editing
- Never "fix" a failure by hiding it — no removing the failing step, no
continue-on-error: true, no|| true, no disabling a check — unless the user explicitly asks for that. The goal is root cause, not a green checkmark.
Verification
- Identified the specific failing step (not just "the run failed")
- Found the actual
error:/FAILURE:line, not just generic exit-code noise - Root cause stated as one sentence with a cited log line
- Fix reproduces/resolves locally where the failure type allows it (e.g. a Gradle task)
- Fix addresses the cause, not just silences the check
© MartinStyk, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/analyze-ci-failure of MartinStyk/apk-analyzer.
Open the folder on GitHubat commit d807559
Compare with similar skills
Analyze CI Failure 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 |
|---|---|---|---|---|---|---|
| Analyze CI Failure this skillMartinStyk/apk-analyzer | 370 | — | ~1.9k | Automated safety check: Pass | GPL-3.0 | |
| CI Failure Triage and RepairChachamaru127/claude-code-harness | 3.2k | 1 repos | ~1.1k | Automated safety check: Notes | MIT | |
| ONNX Runtime CI Managementmicrosoft/onnxruntime | 22k | — | ~4.1k | Automated safety check: Pass | MIT | |
| CI Watchdoglatitude-dev/latitude-llm | 4.7k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Megatron-LM CI Failure TriageNVIDIA/Megatron-LM | 18k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Swig CI Reproswig/swig | 6.3k | — | ~1.2k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
ONNX Runtime CI Management
microsoft/onnxruntime
Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.
CI Watchdog
latitude-dev/latitude-llm
Continuously monitor GitHub PR CI checks and automatically fix failures until all checks pass.
- Official
Megatron-LM CI Failure Triage
NVIDIA/Megatron-LM
Investigates a failing GitHub Actions run or job for Megatron-LM, finds the root cause plus the PR and test author involved, and files a structured bug issue.
Swig CI Repro
swig/swig
Reproduce a GitHub Actions Linux CI failure locally when it does not happen on your machine: a podman/docker image that mirrors the ubuntu-22.04 runner by reusing the real Tools/CI-linux-.sh install…
CI/CD Failure Troubleshooting
ruby-git/ruby-git
Diagnoses and fixes failing GitHub Actions runs by identifying the failure, fetching only the relevant logs, finding the root cause and reproducing it locally.
More from MartinStyk/apk-analyzer
All 18 skills in this repoTriage Crashes
MartinStyk/apk-analyzer
A skill your agent uses to review production Crashlytics crashes and non-fatals for the latest release and file a GitHub issue for each one that isn't tracked yet.
Capture App Flow Media
MartinStyk/apk-analyzer
A skill your agent uses to record or convert ApkAnalyzer app flows into screenshots or GIFs for the README or product docs.
Create Compose Component
MartinStyk/apk-analyzer
A skill your agent uses when creating a new reusable Compose UI component that should live in core:ui-library.
Create Core Module
MartinStyk/apk-analyzer
A skill your agent uses when creating a new core or shared library module for domain logic, data access, repositories, managers, or utilities.
Create Feature Module
MartinStyk/apk-analyzer
A skill your agent uses when creating a new feature module, screen, or feature area.
Fix Crash
MartinStyk/apk-analyzer
A skill your agent uses to fix a specific production crash or non-fatal — pulling its Crashlytics data, finding the linked GitHub issue, root-causing it, reproducing it, fixing it, and verifying the…
Related
Works with
Categories
Questions about Analyze CI Failure
What does Analyze CI Failure do?
A skill your agent uses to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix. Analyze CI Failure is an agent skill from MartinStyk/apk-analyzer. Use to check GitHub Actions build status or diagnose why a workflow run failed and propose a fix.
When should I use Analyze CI Failure?
Analyze CI Failure fits situations like: check GitHub Actions build status; diagnose why a workflow run failed and propose a fix.
How do I install Analyze CI Failure in Claude Code?
Run `npx skills add MartinStyk/apk-analyzer --skill analyze-ci-failure -a claude-code`. Or copy the skill folder (.claude/skills/analyze-ci-failure in MartinStyk/apk-analyzer) into .claude/skills/analyze-ci-failure in your project. Claude Code loads it when a task matches its description.
How do I install Analyze CI Failure in Codex?
Run `npx skills add MartinStyk/apk-analyzer --skill analyze-ci-failure -a codex`. Or copy the skill folder (.claude/skills/analyze-ci-failure in MartinStyk/apk-analyzer) into .agents/skills/analyze-ci-failure in your project. Codex loads it when a task matches its description.
Can I use Analyze CI Failure 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 MartinStyk/apk-analyzer --skill analyze-ci-failure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/analyze-ci-failure, .gemini/skills/analyze-ci-failure, .github/skills/analyze-ci-failure and .opencode/skills/analyze-ci-failure in your project.
What does Analyze CI Failure need to run?
Going by SKILL.md and its folder, Analyze CI Failure needs the command-line tools its instructions call (gh) and credentials named FIREBASE_TOKEN, SIGN_KEY, SIGN_KEY_STORE_PASSWORD and SIGN_KEY_PASSWORD. Our summary lists: A credential in FIREBASE_TOKEN; A credential in SIGN_KEY.
Does Analyze CI Failure access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Analyze CI Failure 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. Review the folder before installing.
What licence does Analyze CI Failure use?
Analyze CI Failure is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Analyze CI Failure use?
About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Analyze CI Failure?
Skills that share tags, products or a category with Analyze CI Failure: CI Failure Triage and Repair (Chachamaru127/claude-code-harness, 3.2k stars), ONNX Runtime CI Management (microsoft/onnxruntime, 22k stars), CI Watchdog (latitude-dev/latitude-llm, 4.7k stars) and Megatron-LM CI Failure Triage (NVIDIA/Megatron-LM, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Analyze CI Failure?
MartinStyk (a GitHub user) maintains it in MartinStyk/apk-analyzer, which has 370 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 5, 2026.
Source: MartinStyk/apk-analyzer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.