Google SEO APIs
AgriciDaniel/claude-seo
Pulls real Google data for SEO work: Search Console, PageSpeed Insights, CrUX field data, the Indexing API and GA4 organic traffic, through /seo google commands.
FortiOS VDOM segmentation audit with UTM profile binding validation, FortiGuard service health assessment, SD-WAN security evaluation, and HA cluster posture check.
$ npx skills add LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fortigate-firewall-audit --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fortigate-firewall-audit .claude/skills/fortigate-firewall-audit && 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 "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .claude/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-auditType 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 LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fortigate-firewall-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/fortigate-firewall-audit .agents/skills/fortigate-firewall-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .agents/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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 LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fortigate-firewall-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/fortigate-firewall-audit .cursor/skills/fortigate-firewall-audit && 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 "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .cursor/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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/LeoYeAI/openclaw-master-skills.git --path skills/fortigate-firewall-audit--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 LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fortigate-firewall-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/fortigate-firewall-audit .gemini/skills/fortigate-firewall-audit && 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 "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .gemini/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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 LeoYeAI/openclaw-master-skills fortigate-firewall-auditInstalls 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 LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/fortigate-firewall-audit .github/skills/fortigate-firewall-audit && 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 "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .github/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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 LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills fortigate-firewall-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/fortigate-firewall-audit .opencode/skills/fortigate-firewall-audit && 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 "fortigate-firewall-audit" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/fortigate-firewall-audit into .opencode/skills/fortigate-firewall-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fortigate-firewall-audit", 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.
fortigate-firewall-auditFortiOS VDOM segmentation audit with UTM profile binding validation, FortiGuard service health assessment, SD-WAN security evaluation, and HA cluster posture check.
Fortigate Firewall Audit is an agent skill from LeoYeAI/openclaw-master-skills. FortiOS VDOM segmentation audit with UTM profile binding validation, FortiGuard service health assessment, SD-WAN security evaluation, and HA cluster posture check. Systematic per-VDOM policy analysis for FortiGate appliances and FortiGate-VM instances.
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `_meta.json`, `references/cli-reference.md` and `references/policy-model.md`).
It sits in Marketing & SEO, covering Marketing analytics. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Fortigate Firewall Audit loads about 4.9k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 1,695 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.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its Apache-2.0 licence (© LeoYeAI). 1,695 words, ~4,922 tokens.
.claude/skills/fortigate-firewall-audit/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Policy-audit-driven analysis of FortiGate/FortiOS firewall policies. Unlike generic firewall checklists that check for open ports and default-deny, this skill evaluates the FortiOS-specific security architecture: Virtual Domain (VDOM) segmentation, UTM profile binding on every allow policy, FortiGuard signature freshness, and SD-WAN SLA-based traffic steering security implications.
Covers FortiOS 7.x+ on FortiGate hardware appliances and FortiGate-VM virtual
instances. For FortiManager-managed deployments, the audit addresses ADOM
hierarchy and policy package consistency. Reference references/policy-model.md
for the full VDOM/UTM inspection chain and references/cli-reference.md for
read-only CLI commands.
diagnose-level privilege for runtime state)Follow this audit flow sequentially. Each step builds on prior findings. The procedure moves from VDOM architecture inventory through per-VDOM rule-level analysis to UTM coverage, FortiGuard health, SD-WAN security, and HA posture.
Collect all VDOMs and their roles.
config vdom
edit root
end
get system statusOn a multi-VDOM system, list all VDOMs:
diagnose sys vd listFor each VDOM, record: name, type (traffic/management/admin), assigned interfaces (physical and virtual), inter-VDOM link pairs, and VDOM resource limits (session count, CPU quota). Identify the management VDOM — this is where FortiGuard updates, logging, and administrative access are configured.
Check inter-VDOM links:
show system vdom-linkInter-VDOM links function as virtual interfaces connecting two VDOMs. Traffic crossing a VDOM link is subject to the receiving VDOM's firewall policies — verify that inter-VDOM traffic is not bypassing inspection.
Verify VDOM resource limits to detect unbounded VDOMs that could starve other VDOMs during volumetric events:
config global
get system vdom-propertyFlag any VDOM without explicit resource limits in a multi-VDOM deployment.
For each VDOM, retrieve the full policy table:
config vdom
edit <vdom-name>
show firewall policyFortiOS evaluates firewall policies top-down by sequence number within each VDOM. The first matching policy is applied. Evaluate each policy against these criteria:
srcaddr "all",
dstaddr "all", service "ALL", and action accept are Critical
findings — they accept all traffic on all ports with no restriction.utm-status, av-profile, webfilter-profile,
application-list, and ips-sensor on each allow policy.status disable still occupy
sequence numbers and create audit confusion. Flag for cleanup.schedule other than always
may create time-window security gaps. Verify schedules align with
intended access windows.Check for unused policies using hit count data:
diagnose firewall iprope show 100004 <policy-id>Policies with zero hits over 90+ days are cleanup candidates.
For each allow policy in every VDOM, verify that UTM inspection profiles are bound. The goal is zero allow policies without threat inspection.
Check each allow policy for these profile bindings:
av-profile): File-based malware scanning. Required on
all internet-bound and inter-zone policies.webfilter-profile): URL categorization and blocking.
Required on all policies permitting HTTP/HTTPS.application-list): Application identification
and enforcement. FortiOS equivalent of App-ID.ips-sensor): Intrusion prevention signatures. Required on
all allow policies carrying untrusted traffic.emailfilter-profile): Anti-spam for SMTP/IMAP/POP3.
Required on email-carrying policies.dlp-sensor): Data loss prevention pattern matching.
Required where sensitive data egress risk exists.ssl-ssh-profile): Determines whether encrypted
traffic is decrypted for UTM inspection. Without SSL inspection set to
deep-inspection, AV and IPS see only connection metadata on HTTPS.Summarize coverage: count allow policies with full UTM binding versus allow policies with partial or no UTM profiles. Calculate the UTM coverage ratio.
Check the inspection mode per VDOM:
config vdom
edit <vdom-name>
get system settings | grep inspection-modeFlow-based mode applies all UTM in a single pass (faster, less thorough). Proxy-based mode buffers and inspects fully (more thorough, more resource intensive). The mode affects which UTM features are available and their efficacy.
FortiGuard provides the signature databases that UTM profiles depend on. Stale signatures reduce detection efficacy.
get system fortiguard-service status
diagnose autoupdate versionsVerify the following signature databases are current:
| Database | Maximum Acceptable Age | Check Command |
|---|---|---|
| Antivirus definitions | 24 hours | `diagnose autoupdate versions |
| IPS signatures | 7 days | `diagnose autoupdate versions |
| Web filter database | 7 days | get webfilter status |
| Application control DB | 7 days | `diagnose autoupdate versions |
| Anti-spam database | 7 days | `diagnose autoupdate versions |
Check FortiGuard connectivity:
diagnose debug rating
execute ping service.fortiguard.netIf FortiGuard is unreachable, all cloud-dependent features (web filter rating queries, FortiSandbox cloud, outbreak prevention) operate in degraded mode using cached data only.
Verify the update schedule:
show system autoupdate scheduleBest practice is scheduled updates every 1–4 hours for AV and daily for IPS/App-Control. Manual-only updates are a finding.
If SD-WAN is configured, evaluate security implications of traffic steering.
config vdom
edit <vdom-name>
show system sdwanReview SD-WAN components:
diagnose sys sdwan health-checktie-break method.diagnose sys sdwan serviceFail-open behavior: When all SLA members fail, SD-WAN rules may fall through to standard routing. Determine whether this fallback path still traverses security inspection. A fail-open that routes around a security VDOM or UTM-inspecting policy is a Critical finding.
SD-WAN + firewall policy interaction: SD-WAN selects the egress interface, but firewall policies still control access. Verify that firewall policies cover all SD-WAN member interfaces. A policy that references a specific interface may not match when SD-WAN steers traffic to an alternate member.
Evaluate HA cluster security posture.
get system ha status
diagnose sys ha checksum clusterCheck the following:
diagnose sys ha checksum clusterCompare configuration checksums between members. Mismatched checksums indicate configuration drift — a security risk when policies differ between HA members.
show system haCheck session-pickup and session-pickup-connectionless settings.
| Finding | Severity | Rationale |
|---|---|---|
srcaddr "all" + dstaddr "all" + service "ALL" + action accept | Critical | Fully open policy — no restriction on source, destination, or service |
| Allow policy without any UTM profile (no AV, IPS, web-filter) | Critical | Traffic passes without threat inspection |
| FortiGuard unreachable — all signatures stale | Critical | UTM profiles active but signatures outdated; detection efficacy severely degraded |
| SD-WAN fail-open bypasses security inspection path | Critical | SLA failure routes traffic around UTM inspection |
Allow policy with service "ALL" (specific src/dst) | High | Permits all services — evaluate whether specific services can be defined |
| FortiGuard signatures >7 days old | High | Detection gap for new threats discovered in the past week |
| VDOM without resource limits in multi-VDOM deployment | High | Unbounded VDOM can starve other VDOMs during volumetric events |
| HA configuration checksum mismatch between members | High | Policy or configuration drift — active and standby may enforce different rules |
| HA firmware version mismatch | High | Session sync and feature parity issues during failover |
| Allow policy with partial UTM (missing IPS or AV) | Medium | Some inspection, but exploit or malware detection gap |
| Disabled policies in production VDOM | Medium | Audit confusion; stale configuration; cleanup recommended |
| SSL inspection not set to deep-inspection on internet-bound policy | Medium | UTM sees only metadata on encrypted traffic — AV/IPS efficacy reduced |
| Schedule-based policy creates off-hours security gap | Medium | Access permitted during window only, but gap during that window is intentional risk |
| Inter-VDOM link without receiving-side policy | Medium | Traffic may traverse VDOM boundary without inspection |
| Policies with zero hits >90 days | Low | Unused rules — cleanup candidates |
| UTM Coverage Ratio | Maturity | Guidance |
|---|---|---|
| >90% allow policies with full UTM | Mature | Maintain; review remaining gaps quarterly |
| 60–90% allow policies with UTM | Developing | Prioritize internet-bound and inter-zone policies for UTM binding |
| <60% allow policies with UTM | Immature | Systematic UTM profile binding campaign needed |
Allow policy without UTM profiles
├── What traffic does this policy carry?
│ ├── Internet-bound → CRITICAL: Bind full UTM (AV+IPS+WebFilter+AppCtrl+SSL deep-inspection)
│ ├── Inter-VDOM or inter-zone → HIGH: Bind AV+IPS+AppCtrl minimum
│ ├── Intra-zone management → MEDIUM: Bind IPS+AppCtrl; AV optional
│ └── Monitoring/logging only → LOW: Evaluate if allow is needed
│
├── SSL inspection mode?
│ ├── certificate-inspection → UTM limited to metadata on HTTPS
│ │ └── Evaluate switching to deep-inspection for this policy
│ ├── deep-inspection → Full UTM efficacy on encrypted traffic
│ └── none → Only unencrypted traffic inspected
│ └── Add ssl-ssh-profile before UTM profiles
│
└── Inspection mode (VDOM-level)?
├── flow-based → Single-pass; good performance, some UTM features limited
└── proxy-based → Full buffered inspection; verify resource impact
└── Check CPU/memory: diagnose sys topMulti-VDOM deployment evaluation
├── How many VDOMs are configured?
│ ├── >10 VDOMs → Evaluate consolidation; management complexity increases risk
│ ├── 3–10 VDOMs → Typical; verify each serves a distinct security function
│ └── 1–2 VDOMs → Minimal; verify VDOM is needed vs single-VDOM mode
│
├── Do all VDOMs have active policies?
│ ├── Empty or minimal policy VDOMs → Candidates for consolidation or removal
│ └── Active policy VDOMs → Verify traffic segmentation justification
│
├── Are inter-VDOM links necessary?
│ ├── Inter-VDOM traffic inspected by receiving VDOM → Correct architecture
│ └── Inter-VDOM traffic not inspected → Finding: add policies on VDOM links
│
└── Resource contention?
├── VDOM resource limits configured → Check utilization vs limits
└── No limits → Set limits per VDOM to prevent starvationSD-WAN SLA failure scenario
├── All SLA members for a rule fail
│ ├── Rule has dst = security VDOM or UTM-inspecting path?
│ │ ├── Yes → Traffic falls to routing table
│ │ │ ├── Routing table path includes UTM inspection? → Acceptable
│ │ │ └── Routing table path bypasses UTM? → CRITICAL: fail-open gap
│ │ └── No → Standard egress; verify firewall policy still matches
│ │
│ └── SLA health-check server unreachable (false positive)?
│ ├── Single health-check server → HIGH: Add redundant check servers
│ └── Multiple servers, all down → Likely real outage; verify failover
│
└── Partial SLA failure (some members down)
├── Traffic steers to remaining members → Verify capacity
└── Remaining member is a lower-security path → Evaluate riskFORTIGATE SECURITY POLICY AUDIT REPORT
========================================
Device: [hostname]
FortiOS Version: [version]
Platform: [FortiGate model / FortiGate-VM]
VDOM Mode: [multi-vdom / split-vdom / disabled]
Management: [standalone / FortiManager ADOM name]
Audit Date: [timestamp]
Performed By: [operator/agent]
VDOM ARCHITECTURE:
- VDOMs configured: [count]
- Management VDOM: [name]
- Inter-VDOM links: [count] ([list pairs])
- VDOMs with resource limits: [n] / [total]
PER-VDOM POLICY SUMMARY:
VDOM: [name]
- Total firewall policies: [count]
- Accept policies: [n] | Deny policies: [n]
- Policies with full UTM profiles: [n] / [accept count]
- Inspection mode: [flow-based / proxy-based]
- SSL inspection (deep): [n] policies
[Repeat for each VDOM]
FORTIGUARD STATUS:
- Connectivity: [connected / unreachable]
- AV signatures: [version] ([age])
- IPS signatures: [version] ([age])
- Web filter DB: [version] ([age])
- Application control DB: [version] ([age])
- Update schedule: [interval]
SD-WAN STATUS:
- SD-WAN enabled: [yes/no]
- SLA health checks: [count] ([all passing / N failing])
- Fail-open risk: [none identified / risk details]
HA STATUS:
- HA mode: [active-passive / active-active / standalone]
- Firmware parity: [matched / mismatched — versions]
- Config checksum: [matched / mismatched]
- Session sync: [enabled / disabled]
FINDINGS:
1. [Severity] [Category] — [Description]
VDOM: [vdom-name]
Policy ID: [id] (Seq: [sequence])
Interfaces: [srcintf] → [dstintf]
Issue: [specific problem]
Current Config: [relevant policy fields]
Recommendation: [specific remediation]
UTM COVERAGE:
- Per-VDOM coverage ratios: [list each VDOM: n/total (%)]
- Policies missing AV: [count]
- Policies missing IPS: [count]
- Policies missing web-filter: [count]
- Policies missing application-control: [count]
RECOMMENDATIONS:
- [Prioritized action list by severity]
NEXT AUDIT: [CRITICAL findings: 30d, HIGH: 90d, clean: 180d]Auditing more than 10 VDOMs manually is impractical. Export per-VDOM policy
tables via the FortiOS REST API (/api/v2/cmdb/firewall/policy?vdom=<name>)
for programmatic analysis. Prioritize VDOMs carrying internet-bound or
inter-zone traffic — management VDOMs are lower risk.
In FortiManager-managed deployments, audit the installed policy on the
FortiGate (via show firewall policy), not just the FortiManager package —
local policies and installation state may differ. Use
diagnose fortimanager policy-check to identify discrepancies.
Before binding UTM profiles on high-throughput policies, assess headroom:
get system performance status
diagnose sys top 2 20FortiGate models have rated throughput for NGFW and Threat Protection profiles. Ensure traffic volume is within rated capacity. If constrained, prioritize UTM on internet-bound policies and use flow-based inspection.
FortiOS major upgrades may change UTM profile schema or deprecate features. Export the policy baseline before upgrading, then post-upgrade verify: UTM profile bindings preserved, policy sequence intact, SD-WAN rules migrated, and HA cluster upgraded in sequence (secondary first).
Split-VDOM provides two VDOMs (root + FG-traffic); full multi-VDOM allows custom count. Audit whether split-VDOM segmentation is sufficient for compliance requirements. Changing VDOM mode requires a reboot.
© LeoYeAI, 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
SKILL.md and 3 other files (references) in skills/fortigate-firewall-audit of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Fortigate Firewall Audit 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 |
|---|---|---|---|---|---|---|
| Fortigate Firewall Audit this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | |
| Google SEO APIsAgriciDaniel/claude-seo | 19k | 1 repos | ~4.2k | Automated safety check: Pass | MIT | |
| AnalyticsNexus-JPF/note-companion | 870 | 7 repos | ~2.2k | Automated safety check: Pass | MIT | |
| GEO Monthly Delta Reportzubair-trabzada/geo-seo-claude | 11k | — | ~2.4k | Automated safety check: Notes | MIT | |
| Conversion Signal QAaaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| LLM Mention Trackingunifapi-agent/agents | 589 | — | ~1.8k | Automated safety check: Pass | MIT |
AgriciDaniel/claude-seo
Pulls real Google data for SEO work: Search Console, PageSpeed Insights, CrUX field data, the Indexing API and GA4 organic traffic, through /seo google commands.
Nexus-JPF/note-companion
When the user wants to set up, improve, or audit analytics tracking and measurement.
zubair-trabzada/geo-seo-claude
Compares a baseline and a current GEO audit for a client, calculates score changes and action item progress, and writes a monthly progress report.
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", or "set the dedup rule so Meta and…
unifapi-agent/agents
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over…
LichAmnesia/lich-skills
Pulls Google Analytics 4 data through the Data API with TypeScript scripts and turns it into a daily SEO report or prioritized traffic and bounce-rate recommendations.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
FortiOS VDOM segmentation audit with UTM profile binding validation, FortiGuard service health assessment, SD-WAN security evaluation, and HA cluster posture check. Fortigate Firewall Audit is an agent skill from LeoYeAI/openclaw-master-skills. FortiOS VDOM segmentation audit with UTM profile binding validation, FortiGuard service health assessment, SD-WAN security evaluation, and HA cluster posture check.
Fortigate Firewall Audit fits situations like: tasks that involve Marketing analytics.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a claude-code`. Or copy the skill folder (skills/fortigate-firewall-audit in LeoYeAI/openclaw-master-skills) into .claude/skills/fortigate-firewall-audit in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a codex`. Or copy the skill folder (skills/fortigate-firewall-audit in LeoYeAI/openclaw-master-skills) into .agents/skills/fortigate-firewall-audit in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill fortigate-firewall-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fortigate-firewall-audit, .gemini/skills/fortigate-firewall-audit, .github/skills/fortigate-firewall-audit and .opencode/skills/fortigate-firewall-audit in your project.
SKILL.md names no scripts, command-line tools or credentials: Fortigate Firewall Audit is instructions for the agent only.
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.
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.
Fortigate Firewall Audit is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.9k tokens (SKILL.md is roughly 20k 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 6.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Fortigate Firewall Audit: Google SEO APIs (AgriciDaniel/claude-seo, 19k stars), Analytics (Nexus-JPF/note-companion, 870 stars), GEO Monthly Delta Report (zubair-trabzada/geo-seo-claude, 11k stars) and Conversion Signal QA (aaron-he-zhu/aaron-marketing-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.