New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Sdaf Ha Diagnostics

by Azure in Azure/sap-automation

Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state.

OfficialMITAuto-check passedTesting & QA

Install Sdaf Ha Diagnostics

skills CLI
$ npx skills add Azure/sap-automation --skill sdaf-ha-diagnostics -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Azure/sap-automation sdaf-ha-diagnostics --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Azure/sap-automation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sdaf-ha-diagnostics .claude/skills/sdaf-ha-diagnostics && rm -rf skills-src

Use ~/.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/

Facts

Skill name
sdaf-ha-diagnostics
GitHub stars
145
Token cost
~1.4k tokens
SKILL.md length
627 words
Files
2 (incl. references)
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state.

  • Works in 4 steps: classify the request before touching the… → collect read-only evidence first → map the evidence to the right owner → …
  • A user says diagnose my HANA failover
  • SKILL.md covers When to invoke, Preconditions, Recipe and Hard rules, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sdaf Ha Diagnostics is an agent skill from Azure/sap-automation, published by the product's own GitHub organization. Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state. Start read-first: capture crm status full or pcs status --full, inspect SBD or fencing evidence, confirm current resource placement, and reuse existing quality-assurance or HCMT artifacts. Grounded in docs/local/07-10-quality-assurance.md, the shipped Pacemaker role vars/tasks, and the SAP Automation QA setup role. Use when a user says "diagnose my HANA failover", "crm status", "pcs status", "check fencing", "why is…

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/cluster-evidence.md`).

It sits in Testing & QA, covering Backup and disaster recovery and QA and bug reports. It works with Microsoft Azure. The repository describes itself as: This is the repository supporting the SAP deployment automation framework on Azure. The licence is MIT.

When your agent uses it

  • A user says diagnose my HANA failover
  • Why is the SCS/ERS cluster unhealthy
  • Offlinevalidation/cib
  • Review an HCMT result zip

Example prompts

  • “diagnose my HANA failover”
  • “crm status”
  • “pcs status”
  • “/sdaf-ha-diagnostics”

Requirements

  • Pre-approved tools (allowed-tools): shell

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. classify the request before touching the cluster
  2. collect read-only evidence first
  3. map the evidence to the right owner
  4. stop before state changes

What it can do on your machine

Read from SKILL.md and the folder at commit 78835f0. 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:

    • shell

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sdaf Ha Diagnostics loads about 1.4k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 203 tokens; SKILL.md has 627 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~203
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

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 Azure/sap-automation at commit 78835f0, republished under its MIT licence (© Azure). 627 words, ~1,423 tokens.

Download SKILL.mdSave it as .claude/skills/sdaf-ha-diagnostics/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sdaf-ha-diagnostics
description
Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state. Start read-first: capture `crm status full` or `pcs status --full`, inspect SBD or fencing evidence, confirm current resource placement, and reuse existing quality-assurance or HCMT artifacts. Grounded in `docs/local/07-10-quality-assurance.md`, the shipped Pacemaker role vars/tasks, and the SAP Automation QA setup role. Use when a user says "diagnose my HANA failover", "crm status", "pcs status", "check fencing", "why is the SCS/ERS cluster unhealthy", "offline_validation/cib", or "review an HCMT result zip". Do NOT use for pre-deploy topology or design choices (see `sdaf-ha-topology`), fresh installation/deploy, or disruptive failover/fencing exercises (see `sdaf-quality-assurance`).
allowed-tools
shell
license
MIT

SDAF HA Diagnostics

Action-loop skill. Owns read-first, safe diagnostics for a live or recently failed SDAF HA cluster. It does not choose the topology, move resources, clean up stonith history, or invent a recovery procedure.

For the exact evidence ladder, current-code anchors, and stop-list, read references/cluster-evidence.md.

When to invoke

Trigger on: "diagnose HA cluster", "HANA failover failed", "crm status", "pcs status", "check fencing", "resource placement", "cluster unhealthy", "offline_validation/cib", "HCMT result", "SCS/ERS failover", or "read the current Pacemaker state".

Do NOT trigger on:

  • pre-deploy design questions such as SBD vs Azure fence agent, ANF vs AFS, ANGI eligibility, distro choice, or scale-out design — route to sdaf-ha-topology;
  • requests to run online failover, crash, fencing, or blocked-network tests — route to sdaf-quality-assurance;
  • a broader SDAF run failure whose primary symptom is the stage execution itself — route to sdaf-failure-triage.

Preconditions

Ask for the layer under test (HANA DB HA or SCS/ERS HA), OS family, evidence type (live cluster, captured bundle, or prior test run), and any existing crm / pcs output, QA reports, execution logs, or HCMT bundles. If cluster state was already changed manually, preserve who changed what and when before diagnosing anything else.

Recipe

Step 1 — classify the request before touching the cluster

Pick one lane:

  1. Live read-only diagnosis — explain current cluster state from status, placement, and existing logs.
  2. Captured artefact review — read an existing offline_validation bundle, QA report, or HCMT result without acting on the running cluster.
  3. Framework-run or disruptive validation — route to sdaf-quality-assurance; the online functional tests stop resources, move groups, fence nodes, and crash processes.
  4. Topology/design — route to sdaf-ha-topology.
  5. Stage/run failure — route to sdaf-failure-triage.
Step 2 — collect read-only evidence first

Use the evidence ladder in references/cluster-evidence.md. Minimum safe evidence is:

  • OS-specific status: crm status full on SUSE or pcs status --full on Red Hat;
  • current placement evidence such as crm_resource --locate for SCS/ERS;
  • existing fencing, SBD, or HANA hook-verification evidence;
  • existing QA, offline cib, and HCMT artefacts.

Preserve raw output, host, and timestamp. Do not paraphrase away the cluster's own wording.

Show full SKILL.md (292 more words)Show less
Step 3 — map the evidence to the right owner
  • Stay in this skill for read-only interpretation of current Pacemaker state, placement, fencing/SBD evidence, hook traces, or existing QA/HCMT artefacts.
  • Route to sdaf-quality-assurance to run configuration checks, offline HA validation from captured offline_validation/<host>/cib bundles, or disruptive online HA exercises in an approved maintenance window.
  • Route to sdaf-failure-triage for failed SDAF runs or install-phase assertions such as missing fencing SPN details, cluster password, or required clustering scripts.
  • Route to sdaf-ha-topology when the question is what the cluster should look like rather than what the current evidence says.
Step 4 — stop before state changes

The current codebase contains state-changing cluster actions in validation and post-provision tasks. This skill is not the place to run them.

The explicit stop-list lives in the reference. From this skill do not execute crm/pcs resource move, stonith_admin --cleanup, role-defined cluster cleanup, StartService, StartSystem ALL, or online functional HA tests. If the user asks for recovery or failover action, stop at evidence collection and routing; do not invent or approve a repair step.

Hard rules

  • Read-first only. Start with existing cluster status, logs, and artefacts.
  • Documented/current-code only (D19). If the docs or shipped roles do not describe a diagnostic path, say so and stop.
  • Do not invent recovery commands, failover steps, or cleanup procedures.
  • Keep topology and design separate; route those questions to sdaf-ha-topology.
  • Treat disruptive validation as a separate workflow owned by sdaf-quality-assurance.

What this skill does NOT do

  • Does not choose SBD vs Azure fence agent, storage, distro, ANGI, or scale-out design.
  • Does not build, rebuild, reinstall, or actively fail over the cluster.
  • Does not treat HCMT as the first diagnostic step; it only reuses existing HCMT artefacts if they are already present.

See also

  • sdaf-ha-topology
  • sdaf-quality-assurance
  • sdaf-failure-triage
  • docs/local/07-10-quality-assurance.md

© Azure, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/sdaf-ha-diagnostics of Azure/sap-automation.

  • SKILL.md
  • references/cluster-evidence.md

Open the folder on GitHubat commit 78835f0

Compare with similar skills

Sdaf Ha Diagnostics 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.

Sdaf Ha Diagnostics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sdaf Ha Diagnostics this skillAzure/sap-automation145—~1.4kAutomated safety check: PassMIT
Azure DeploymentEmeaAppGbb/spec2cloud100—~1.8kAutomated safety check: PassMIT
Deploy DiagnosticsEmeaAppGbb/spec2cloud100—~511Automated safety check: PassMIT
Provider Verificationmondoohq/mql412—~3.7kAutomated safety check: PassCustom licence
Azureml K3s Compute Target Setupmicrosoft/physical-ai-toolchain123—~5.7kAutomated safety check: NotesMIT
Deploy QAhmislk/hmis236—~2.1kAutomated safety check: NotesGPL-3.0

Similar skills

  • Azure Deployment

    EmeaAppGbb/spec2cloud

    Provision Azure infrastructure, deploy to Azure Container Apps, and verify via smoke tests.

    100 GitHub stars~1.8k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

  • Deploy Diagnostics

    EmeaAppGbb/spec2cloud

    Diagnose and resolve Azure deployment failures by analyzing error output, checking Azure resource state, and suggesting fixes.

    100 GitHub stars~511 tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

  • Provider Verification

    mondoohq/mql

    Verify mql provider resource/field changes against real cloud infrastructure.

    412 GitHub stars~3.7k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Azureml K3s Compute Target Setup

    microsoft/physical-ai-toolchain

    Official

    Set up a K3s cluster on an NVIDIA GPU host, connect it to Azure Arc, and configure Azure ML to use it as a Kubernetes compute target.

    123 GitHub stars~5.7k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes

  • Deploy QA

    hmislk/hmis

    Sync development into QA/testing environment branches (QA1-QA4, local RH staging) via PR + merge on GitHub.

    236 GitHub stars~2.1k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    A skill your agent uses when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration.

    77k GitHub stars~1.1k tokensUpdated 20 days ago
    Testing & QAAuto-check: notes

More from Azure/sap-automation

All 19 skills in this repo

  • Sdaf Bom Selection

    Azure/sap-automation

    Official

    Pick the right SDAF BOM for a target SAP product / release / DB platform / version / kernel / topology.

    145 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Sdaf Orientation And Surface

    Azure/sap-automation

    Official

    Orient a newcomer to the SAP Deployment Automation Framework (SDAF): explain the spine (control plane → workload zone → SAP system → software → install → operate/remove), summarise the three…

    145 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Sdaf Quality Assurance

    Azure/sap-automation

    Official

    Validate a deployed SDAF SAP system through the SDAF-owned QA entry points: the local quality-assurance menu and the documented Azure DevOps pipeline 13 path.

    145 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed

  • Sdaf Sap Installation

    Azure/sap-automation

    Official

    Guide SDAF operating-system, database, and SAP installation after the SAP-system workspace and reviewed media are ready.

    145 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Sdaf Sovereign Cloud

    Azure/sap-automation

    Official

    Explain the current SDAF sovereign-cloud deltas without inventing a generic "all sovereigns" runbook.

    145 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

  • Sdaf State Management

    Azure/sap-automation

    Official

    Inspect and repair SDAF Terraform state safely before any reviewed import/remove.

    145 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Sdaf Ha Diagnostics

What does Sdaf Ha Diagnostics do?

Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state. Sdaf Ha Diagnostics is an agent skill from Azure/sap-automation, published by the product's own GitHub organization. Diagnose a live or recently failed SDAF high-availability cluster without changing cluster state.

When should I use Sdaf Ha Diagnostics?

Sdaf Ha Diagnostics fits situations like: A user says diagnose my HANA failover; why is the SCS/ERS cluster unhealthy; offlinevalidation/cib; review an HCMT result zip.

How do I install Sdaf Ha Diagnostics in Claude Code?

Run `npx skills add Azure/sap-automation --skill sdaf-ha-diagnostics -a claude-code`. Or copy the skill folder (skills/sdaf-ha-diagnostics in Azure/sap-automation) into .claude/skills/sdaf-ha-diagnostics in your project. Claude Code loads it when a task matches its description.

How do I install Sdaf Ha Diagnostics in Codex?

Run `npx skills add Azure/sap-automation --skill sdaf-ha-diagnostics -a codex`. Or copy the skill folder (skills/sdaf-ha-diagnostics in Azure/sap-automation) into .agents/skills/sdaf-ha-diagnostics in your project. Codex loads it when a task matches its description.

Can I use Sdaf Ha Diagnostics 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 Azure/sap-automation --skill sdaf-ha-diagnostics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sdaf-ha-diagnostics, .gemini/skills/sdaf-ha-diagnostics, .github/skills/sdaf-ha-diagnostics and .opencode/skills/sdaf-ha-diagnostics in your project.

What does Sdaf Ha Diagnostics need to run?

SKILL.md names no scripts, command-line tools or credentials: Sdaf Ha Diagnostics is instructions for the agent only. Its frontmatter pre-approves these tools: shell.

Does Sdaf Ha Diagnostics 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 Sdaf Ha Diagnostics 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 Sdaf Ha Diagnostics use?

Sdaf Ha Diagnostics is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sdaf Ha Diagnostics use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 243 tokens, read only when the agent opens those files.

What are the alternatives to Sdaf Ha Diagnostics?

Skills that share tags, products or a category with Sdaf Ha Diagnostics: Azure Deployment (EmeaAppGbb/spec2cloud, 100 stars), Deploy Diagnostics (EmeaAppGbb/spec2cloud, 100 stars), Provider Verification (mondoohq/mql, 412 stars) and Azureml K3s Compute Target Setup (microsoft/physical-ai-toolchain, 123 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sdaf Ha Diagnostics?

Azure (a GitHub organization, an official publisher) maintains it in Azure/sap-automation, which has 145 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

Source: Azure/sap-automation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.