Product Diagnosis
amplitude/builder-skills
Diagnoses product health by cross-referencing Amplitude analytics (dashboards, charts, funnels, feedback, AI agent analytics), optionally Datadog (errors, latency, stack traces), and optionally…
Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID.
Install Investigate Incident
$ npx skills add Mentra-Community/MentraOS --skill investigate-incident -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Mentra-Community/MentraOS investigate-incident --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/Mentra-Community/MentraOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/investigate-incident .claude/skills/investigate-incident && 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 "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .claude/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incidentType 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 Mentra-Community/MentraOS --skill investigate-incident -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Mentra-Community/MentraOS investigate-incident --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mentra-Community/MentraOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/investigate-incident .agents/skills/investigate-incident && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .agents/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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 Mentra-Community/MentraOS --skill investigate-incident -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Mentra-Community/MentraOS investigate-incident --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mentra-Community/MentraOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/investigate-incident .cursor/skills/investigate-incident && 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 "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .cursor/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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/Mentra-Community/MentraOS.git --path .agents/skills/investigate-incident--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 Mentra-Community/MentraOS --skill investigate-incident -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Mentra-Community/MentraOS investigate-incident --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mentra-Community/MentraOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/investigate-incident .gemini/skills/investigate-incident && 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 "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .gemini/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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 Mentra-Community/MentraOS investigate-incidentInstalls 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 Mentra-Community/MentraOS --skill investigate-incident -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Mentra-Community/MentraOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/investigate-incident .github/skills/investigate-incident && 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 "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .github/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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 Mentra-Community/MentraOS --skill investigate-incident -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Mentra-Community/MentraOS investigate-incident --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mentra-Community/MentraOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/investigate-incident .opencode/skills/investigate-incident && 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 "investigate-incident" agent skill from https://github.com/Mentra-Community/MentraOS/tree/dev/.agents/skills/investigate-incident into .opencode/skills/investigate-incident/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "investigate-incident", 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
investigate-incident- GitHub stars
- 2.4k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 539 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID.
- Tasks that involve QA and bug reports
- SKILL.md covers Resolve the report, Fetch through the existing… and Investigate the evidence
- Needs MENTRA_ADMIN_TOKEN
What it does
Investigate Incident is an agent skill from Mentra-Community/MentraOS. Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID. Fetch the report and device artifacts through the Cloud V2 reports API, then trace the evidence to the responsible source code.
Its SKILL.md is about 1.1k 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 Testing & QA, covering QA and bug reports. It works with Slack. The repository describes itself as: MentraOS is the leading smart glasses OS. See live captions, stream your view, talk to AI, and capture photos hands-free on compatible glasses. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve QA and bug reports
Example prompts
- “/investigate-incident”
Requirements
- A credential in MENTRA_ADMIN_TOKEN
What it can do on your machine
Read from SKILL.md and the folder at commit 223f5b9. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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 these keys or tokens, usually read from environment variables:
MENTRA_ADMIN_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Investigate Incident loads about 1.1k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 539 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 Mentra-Community/MentraOS at commit 223f5b9, republished under its Apache-2.0 licence (© Mentra-Community). 539 words, ~1,121 tokens.
Download SKILL.mdSave it as
.claude/skills/investigate-incident/SKILL.md (or your agent's skills folder).- name
- investigate-incident
- description
- Investigate Mentra App bug reports and feedback from a reports Slack link or rep_ report ID. Fetch the report and device artifacts through the Cloud V2 reports API, then trace the evidence to the responsible source code.
Investigate an incident
Use the API for report detail and artifact downloads. Do not open the admin console with browser or computer-use tools to retrieve incident logs.
Resolve the report
For a Slack link, read its message and thread with the Slack connector. A URL
ending in /archives/CHANNEL/p1789682365377999 identifies channel CHANNEL
and message timestamp 1789682365.377999. Extract the rep_... report ID,
environment, symptoms, and relevant replies. The notification's artifact count
can be stale while devices upload; fetch the report's current artifact list.
If Slack access is unavailable and no report ID is known, ask for the ID or message text. Do not substitute a different recent report.
Fetch through the existing script
Run scripts/fetch-incident-logs.sh from the repository root. It calls
GET /api/admin/reports/:reportId and downloads each artifact through
GET /api/admin/reports/:reportId/artifacts/:artifactId.
The script reads MENTRA_ADMIN_TOKEN. Use it if already configured. Otherwise
check for an existing MENTRA_ADMIN_TOKEN_PROD or MENTRA_ADMIN_TOKEN_DEV
matching the notification's environment and pass it to this command only:
MENTRA_ADMIN_TOKEN="$MENTRA_ADMIN_TOKEN_PROD" \
./scripts/fetch-incident-logs.sh rep_REPORT_ID --env prod
MENTRA_ADMIN_TOKEN="$MENTRA_ADMIN_TOKEN_DEV" \
./scripts/fetch-incident-logs.sh rep_REPORT_ID --env devCheck whether a variable is set without printing its value. Do not print
credentials, enable shell tracing, put tokens in committed files, or extract
browser sessions. If no suitable credential is available, request that the user
configure MENTRA_ADMIN_TOKEN in the environment. Authentication requires an
admin-allowlisted org API key (msk_...).
Use the environment from the report notification. Without --env, the script
tries prod, dev, then staging. MENTRA_CORE_URL overrides even --env; check
for an unintended override before interpreting a missing report. Distinguish
401 (rejected credential), 403 (not admin-allowlisted), and 404 (wrong ID,
environment, or unavailable endpoint). Report authentication failures directly;
do not fall back to console automation.
Downloads go to gitignored incident-logs/<reportId>/. Use --out for an
alternative local directory, such as .context/incidents/<reportId>/.
--json returns detail only; it does not download logs. --list lists
recent reports and supports --kind, --status, and --limit.
If the report is still collecting or an artifact download failed, distinguish
partial evidence from a complete bundle. Re-fetch when uploads have finished;
do not treat absent logs as proof that nothing happened.
Show full SKILL.md (211 more words)Show less
Investigate the evidence
report.json is the API envelope: the document is under .report, including
.report.report (user description), .report.context (device/app snapshot),
and .report.artifacts. Log files contain {entries: [...]} with timestamps,
levels, messages, and optional sources. Artifacts can include phone, glasses,
glasses firmware, and screenshots; inspect the actual metadata rather than
assuming fixed file numbers or sources.
Select relevant fields and time ranges before displaying output. Context and log messages may contain credentials, personal information, signed URLs, and large inline audio payloads. Keep raw bundles local and include only necessary, redacted excerpts in PRs or responses.
Correlate timestamps across sources, record the app build and firmware
versions, and compare the reported build with current origin/dev. Separate
the user's symptoms, observed log evidence, and hypotheses. Read the owning
module's AGENTS.md before editing. BES firmware belongs to mentra-live-bes;
follow its guidance and OTA gates if a fix belongs there. Do not assume every
incident needs a mobile or cloud patch.
When a fix is supported by the evidence, add focused regression coverage and follow the repository's PR workflow if a PR was requested. Include the report ID, source Slack link, findings, validation, and any required device checks. Do not reply in Slack, close the report, or deploy firmware merely because an investigation or PR was requested.
© Mentra-Community, Apache-2.0. 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 .agents/skills/investigate-incident of Mentra-Community/MentraOS.
Open the folder on GitHubat commit 223f5b9
Compare with similar skills
Investigate Incident 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 |
|---|---|---|---|---|---|---|
| Investigate Incident this skillMentra-Community/MentraOS | 2.4k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Product Diagnosisamplitude/builder-skills | 159 | — | ~4k | Automated safety check: Pass | None | |
| Agent Browser CLIvercel-labs/agent-browser | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | |
| Test Slack Appslackapi/slack-skills-plugin | 147 | — | ~2.4k | Automated safety check: Notes | MIT | |
| Reproduce Chat Statesdifferent-ai/openwork | 24k | — | ~673 | Automated safety check: Pass | Custom licence | |
| Dynamo Jira TicketDynamoDS/Dynamo | 2k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Agent Browser CLI
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
- Official
Test Slack App
slackapi/slack-skills-plugin
A skill your agent uses when a developer wants to test, try out, smoke-test, verify, or confirm that a Slack app built with the Slack CLI (or a plain Bolt app) actually works, by running it in a…
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
Dynamo Jira Ticket
DynamoDS/Dynamo
Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.
Moav E2E
MotherofallVPNs/MoaV
Run and debug MoaV's end-to-end tests — real protocol connectivity (client-test.sh) and the moav CLI smoke test — against a LIVE server, via the self-hosted e2e workflow or a local test VPS.
More from Mentra-Community/MentraOS
All 11 skills in this repoInvestigate Routine Failure
Mentra-Community/MentraOS
Investigate a Mentra routine failure from an Admin testRun URL or run/request ID, fetch authenticated results and verified artifacts with the existing incident-report token, trace the exact routine…
Mentra Update Live Firmware
Mentra-Community/MentraOS
Update MentraOS firmwarelive.json from the published BES and MTK feeds and prepare a PR, preserving production MTK upgrade paths.
CI Triage
Mentra-Community/MentraOS
Triage failing GitHub PR checks: list failures with gh, fetch capped Actions logs, skip non-Actions checks, and summarize root cause.
Codex PR Review
Mentra-Community/MentraOS
Run an independent local Codex (gpt-6.1-sol, medium) review of a GitHub pull request and relay its verdict.
Manage Cloud Env
Mentra-Community/MentraOS
Add or change backend deployment environment variables through Doppler shared configs and native Porter syncs.
Fix Nightly Failures
Mentra-Community/MentraOS
Diagnose an ongoing or finished Mentra nightly suite, group demonstrated shared failures, implement fixes, and carry PRs through independent Codex review and merge.
Related
Works with
Categories
Questions about Investigate Incident
What does Investigate Incident do?
Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID. Investigate Incident is an agent skill from Mentra-Community/MentraOS. Investigate Mentra App bug reports and feedback from a reports Slack link or rep report ID.
When should I use Investigate Incident?
Investigate Incident fits situations like: tasks that involve QA and bug reports.
How do I install Investigate Incident in Claude Code?
Run `npx skills add Mentra-Community/MentraOS --skill investigate-incident -a claude-code`. Or copy the skill folder (.agents/skills/investigate-incident in Mentra-Community/MentraOS) into .claude/skills/investigate-incident in your project. Claude Code loads it when a task matches its description.
How do I install Investigate Incident in Codex?
Run `npx skills add Mentra-Community/MentraOS --skill investigate-incident -a codex`. Or copy the skill folder (.agents/skills/investigate-incident in Mentra-Community/MentraOS) into .agents/skills/investigate-incident in your project. Codex loads it when a task matches its description.
Can I use Investigate Incident 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 Mentra-Community/MentraOS --skill investigate-incident -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/investigate-incident, .gemini/skills/investigate-incident, .github/skills/investigate-incident and .opencode/skills/investigate-incident in your project.
What does Investigate Incident need to run?
Going by SKILL.md and its folder, Investigate Incident needs credentials named MENTRA_ADMIN_TOKEN. Our summary lists: A credential in MENTRA_ADMIN_TOKEN.
Does Investigate Incident 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 Investigate Incident 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 Investigate Incident use?
Investigate Incident is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Investigate Incident use?
About 1.1k tokens (SKILL.md is roughly 4.5k 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 Investigate Incident?
Skills that share tags, products or a category with Investigate Incident: Product Diagnosis (amplitude/builder-skills, 159 stars), Agent Browser CLI (vercel-labs/agent-browser, 44k stars), Test Slack App (slackapi/slack-skills-plugin, 147 stars) and Reproduce Chat States (different-ai/openwork, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Investigate Incident?
Mentra-Community (a GitHub organization) maintains it in Mentra-Community/MentraOS, which has 2,381 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 11, 2026.
Source: Mentra-Community/MentraOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.