HIPAA Safe Harbor Coverage Audit
maziyarpanahi/openmed
Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.
Cognitive triage of fleet audit findings. An agent skill from google-labs-code/jules-sdk.
Install Fleet Triage
$ npx skills add google-labs-code/jules-sdk --skill fleet-triage -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install google-labs-code/jules-sdk fleet-triage --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/google-labs-code/jules-sdk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/fleet-triage .claude/skills/fleet-triage && 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 "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .claude/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triageType 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 google-labs-code/jules-sdk --skill fleet-triage -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install google-labs-code/jules-sdk fleet-triage --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-labs-code/jules-sdk.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/fleet-triage .agents/skills/fleet-triage && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .agents/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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 google-labs-code/jules-sdk --skill fleet-triage -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install google-labs-code/jules-sdk fleet-triage --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-labs-code/jules-sdk.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/fleet-triage .cursor/skills/fleet-triage && 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 "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .cursor/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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/google-labs-code/jules-sdk.git --path .agents/skills/fleet-triage--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 google-labs-code/jules-sdk --skill fleet-triage -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install google-labs-code/jules-sdk fleet-triage --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-labs-code/jules-sdk.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/fleet-triage .gemini/skills/fleet-triage && 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 "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .gemini/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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 google-labs-code/jules-sdk fleet-triageInstalls 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 google-labs-code/jules-sdk --skill fleet-triage -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/google-labs-code/jules-sdk.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/fleet-triage .github/skills/fleet-triage && 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 "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .github/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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 google-labs-code/jules-sdk --skill fleet-triage -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install google-labs-code/jules-sdk fleet-triage --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/google-labs-code/jules-sdk.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/fleet-triage .opencode/skills/fleet-triage && 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 "fleet-triage" agent skill from https://github.com/google-labs-code/jules-sdk/tree/main/.agents/skills/fleet-triage into .opencode/skills/fleet-triage/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fleet-triage", 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
fleet-triage- GitHub stars
- 136
- Token cost
- ~1.2k tokens
- SKILL.md length
- 507 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Cognitive triage of fleet audit findings. An agent skill from google-labs-code/jules-sdk.
- Works in 4 steps: Build a Lightweight Index → Batch Triage from Index → Deep Dive (One at a Time) → …
- Triaging undispatched issues
- SKILL.md covers When to Use, Core Principle, Process and Triage Artifact, plus 2 more sections
- Calls gh
What it does
Fleet Triage is an agent skill from google-labs-code/jules-sdk, published by the product's own GitHub organization. Cognitive triage of fleet audit findings. Read issue content, evaluate labeling accuracy, and determine open/close/dispatch/relabel actions for fleet-managed issues. Use when triaging undispatched issues or reviewing audit scan results.
Its SKILL.md is about 1.2k 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 Legal & Compliance, covering Audit readiness. The licence is Apache-2.0.
When your agent uses it
- Triaging undispatched issues
- Reviewing audit scan results
Example prompts
- “/fleet-triage”
Requirements
- Pre-approved tools (allowed-tools): run_command(gh:*), run_command(fleet:*), view_file, write_to_file, read_url_content
Workflow steps
4 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 19fc117. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
run_command(gh:*)run_command(fleet:*)view_filewrite_to_fileread_url_content
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Fleet Triage loads about 1.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 507 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 google-labs-code/jules-sdk at commit 19fc117, republished under its Apache-2.0 licence (© google-labs-code). 507 words, ~1,214 tokens.
Download SKILL.mdSave it as
.claude/skills/fleet-triage/SKILL.md (or your agent's skills folder).- name
- fleet-triage
- description
- Cognitive triage of fleet audit findings. Read issue content, evaluate labeling accuracy, and determine open/close/dispatch/relabel actions for fleet-managed issues. Use when triaging undispatched issues or reviewing audit scan results.
- allowed-tools
- run_command(gh:*), run_command(fleet:*), view_file, write_to_file, read_url_content
Fleet Triage
Cognitive triage of fleet-managed issues. The audit scan surfaces findings deterministically; you make the judgment calls.
When to Use
- After running
fleet audit scanand seeing cognitive findings - Before running
fleet dispatchto prevent wasting sessions on non-actionable issues - When asked to triage, clean up, or review fleet issues
Core Principle
Tools are evidence, you are expertise. The scan tells you what exists. You read the content and decide what to do.
Process
Phase 1: Build a Lightweight Index
Pull all open issues as a summary table. Do NOT read issue bodies yet.
gh issue list --repo <owner>/<repo> --state open --limit 50 \
--json number,title,labels,milestoneClassify each issue into buckets by title and labels alone:
| Bucket | Signal | Typical Action |
|---|---|---|
| Insight | Title contains [Insight], [Fleet Insight], or label fleet-insight | Likely close — informational only |
| Assessment | Title contains [Assessment], or label fleet-assessment | Evaluate — may be actionable or stale |
| Execution | Title contains [Fleet Execution], label fleet without insight/assessment | Likely dispatch — has code work |
| Ambiguous | Mixed signals or unlabeled | Needs deep dive (Phase 3) |
Record the index in a triage artifact (see Triage Artifact).
Phase 2: Batch Triage from Index
For Insight and Assessment buckets, you can often decide without reading the body:
- Duplicate insights (same title pattern, sequential numbers like "Update 2", "Update 3", "Update 4") → Close older duplicates, keep latest
- Insights with no milestone → Likely orphaned, close
- Assessments with linked PRs → Check if PR is merged; if so, close
Update the triage artifact with decisions.
Phase 3: Deep Dive (One at a Time)
For Ambiguous or Execution issues only:
gh issue view <N> --repo <owner>/<repo>Read the body. Evaluate:
- Is there actionable code work? Look for "Files to modify:", "Proposed Implementation", specific code paths
- Is it stale? Has the work already been done by another PR? Check linked PRs
- Are the labels accurate? Does an "Execution" issue actually describe an insight?
- Should it be dispatched? Only if there's concrete code work with clear acceptance criteria
Record your decision in the triage artifact before moving to the next issue.
Show full SKILL.md (184 more words)Show less
Phase 4: Apply Decisions
After all decisions are recorded, present the triage artifact to the user for review. Then apply:
# Close issues
gh issue close <N> --repo <owner>/<repo> --comment "Closing: <reason>"
# Relabel
gh issue edit <N> --repo <owner>/<repo> --remove-label fleet --add-label fleet-insight
# Dispatch (only confirmed actionable issues)
fleet dispatch --owner <owner> --repo <repo>Triage Artifact
Create a persistent artifact at triage-<repo>.md:
# Triage: <owner>/<repo>
## Summary
- Total open: N
- Reviewed: N
- Close: N | Keep: N | Dispatch: N | Relabel: N
## Decisions
| # | Title | Labels | Decision | Reason |
|---|-------|--------|----------|--------|
| 194 | [Fleet Insight] Coverage | fleet, fleet-insight | CLOSE | Insight, no code action |
| 141 | [Fleet Execution] Update Enums | fleet, fleet-assessment | DEEP DIVE | Mixed labels, need to read body |Token Management
- Never load all 25 issue bodies at once — each body can be 500-2000 tokens
- Process one deep dive at a time, record decision, then move on
- The triage artifact survives context resets — pick up where you left off
- For batch closes, use
gh issue closein a single command per issue
Common Patterns
Duplicate Detection
Fleet analyzers often create duplicate insights across runs. Look for:
- Sequential "Update N" suffixes (keep only the latest)
- Same title with different numbers
- Same objective described in different words
Stale Assessment Detection
An assessment may have been addressed by a PR that didn't reference the issue:
- Check if the described code changes already exist in
main - Check if a similar PR was merged without
Fixes #N
Mislabeled Issues
The analyzer sometimes labels insights as fleet (execution-worthy) when they're informational:
- Body says "No source changes" → should be
fleet-insight, notfleet - Body says "N/A - This is an Insight report" → not dispatchable
© google-labs-code, 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/fleet-triage of google-labs-code/jules-sdk.
Open the folder on GitHubat commit 19fc117
Compare with similar skills
Fleet Triage 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 |
|---|---|---|---|---|---|---|
| Fleet Triage this skillgoogle-labs-code/jules-sdk | 136 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| HIPAA Safe Harbor Coverage Auditmaziyarpanahi/openmed | 5.5k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| ISO Standards Readiness EvidenceK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~4.6k | Automated safety check: Notes | MIT | |
| Iso42001Sushegaad/Claude-Skills-Governance-Risk-and-Compliance | 939 | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| PCI DSS Compliancewshobson/agents | 40k | 10 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Trust Center BuilderGRCEngClub/claude-grc-engineering | 419 | — | ~2.6k | Automated safety check: Pass | Custom licence |
Similar skills
ISO Standards Readiness Evidence
K-Dense-AI/scientific-agent-skills
Organizes scope, controlled documents, risk files and traceability into draft evidence for human review against ISO 13485, 14971, 17025 and 15189.
Iso42001
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert ISO 42001 AI Management System (AIMS) compliance advisor.
PCI DSS Compliance
wshobson/agents
Reference for building payment systems that meet PCI DSS: the 12 requirements, merchant levels, data that must never be stored, tokenization and encryption.
Trust Center Builder
GRCEngClub/claude-grc-engineering
Builds and deploys a serverless trust center that publishes a company's compliance posture, with gated access to audit reports and an admin dashboard.
Eu AI Act Readiness
seb1n/awesome-ai-agent-skills
Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…
More from google-labs-code/jules-sdk
- Official
Gws Agent CLI Operations
google-labs-code/jules-sdk
Comprehensive instructions for executing tasks using the gws (Google Workspace) CLI or similar agent-first command-line tools.
Related
Categories
Questions about Fleet Triage
What does Fleet Triage do?
Cognitive triage of fleet audit findings. An agent skill from google-labs-code/jules-sdk. Fleet Triage is an agent skill from google-labs-code/jules-sdk, published by the product's own GitHub organization. Cognitive triage of fleet audit findings.
When should I use Fleet Triage?
Fleet Triage fits situations like: triaging undispatched issues; reviewing audit scan results.
How do I install Fleet Triage in Claude Code?
Run `npx skills add google-labs-code/jules-sdk --skill fleet-triage -a claude-code`. Or copy the skill folder (.agents/skills/fleet-triage in google-labs-code/jules-sdk) into .claude/skills/fleet-triage in your project. Claude Code loads it when a task matches its description.
How do I install Fleet Triage in Codex?
Run `npx skills add google-labs-code/jules-sdk --skill fleet-triage -a codex`. Or copy the skill folder (.agents/skills/fleet-triage in google-labs-code/jules-sdk) into .agents/skills/fleet-triage in your project. Codex loads it when a task matches its description.
Can I use Fleet Triage 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 google-labs-code/jules-sdk --skill fleet-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fleet-triage, .gemini/skills/fleet-triage, .github/skills/fleet-triage and .opencode/skills/fleet-triage in your project.
What does Fleet Triage need to run?
Going by SKILL.md and its folder, Fleet Triage needs the command-line tools its instructions call (gh). Its frontmatter pre-approves these tools: run_command(gh:*), run_command(fleet:*), view_file, write_to_file, read_url_content.
Does Fleet Triage 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 Fleet Triage 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 Fleet Triage use?
Fleet Triage 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 Fleet Triage use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Fleet Triage?
Skills that share tags, products or a category with Fleet Triage: HIPAA Safe Harbor Coverage Audit (maziyarpanahi/openmed, 5.5k stars), ISO Standards Readiness Evidence (K-Dense-AI/scientific-agent-skills, 48k stars), Iso42001 (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 939 stars) and PCI DSS Compliance (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Fleet Triage?
google-labs-code (a GitHub organization, an official publisher) maintains it in google-labs-code/jules-sdk, which has 136 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 23, 2026.
Source: google-labs-code/jules-sdk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.