SherpaMind

Use SherpaMind as the OpenClaw query/action layer over the local SherpaDesk dataset prepared by the backend service.

Repo root and stable entrypoint

Work from the repo root:

CODEBLOCK0

When the repo is installed under an OpenClaw skills/ directory, SherpaMind automatically uses the parent workspace as SHERPAMIND_WORKSPACE_ROOT, so runtime state stays in workspace-level .SherpaMind/ rather than inside the skill checkout.

Use the stable runner:

CODEBLOCK1

Do not invent alternate runtime paths.
Do not treat OpenClaw as the background scheduler for this backend.

Transparency and operator expectations

SherpaMind is not an instruction-only skill.

When installed and configured for live use, it can:

• - create workspace-local runtime state under INLINECODE3
• create staged runtime dirs under .SherpaMind/private/config/, .SherpaMind/private/secrets/, .SherpaMind/private/data/, .SherpaMind/private/state/, .SherpaMind/private/logs/, .SherpaMind/private/runtime/, and INLINECODE10
• create a local SQLite database and generated public artifacts
• create a Python runtime venv under INLINECODE11
• install Python dependencies from PyPI during bootstrap
• store the SherpaDesk API key locally in INLINECODE12
• optionally store a SherpaDesk API user hint in INLINECODE13
• store non-secret connection/runtime settings in INLINECODE14
• optionally install and run a user-level systemd background service

Required live staged credentials/config for real SherpaDesk use:

• - staged API key under INLINECODE16
• staged org/instance settings in INLINECODE17

If the user only wants query guidance or offline inspection of an existing local dataset, do not imply that fresh credentials or service installation are unnecessary for live sync.

Choose the lightest path that answers the question

Exact facts, counts, status, and workload

Start with structured commands:

• - INLINECODE18
• INLINECODE19
• INLINECODE20
• INLINECODE21
• INLINECODE22
• INLINECODE23
• INLINECODE24
• INLINECODE25
• INLINECODE26
• INLINECODE27
• INLINECODE28
• INLINECODE29
• INLINECODE30
• INLINECODE31
• INLINECODE32
• INLINECODE33
• INLINECODE34

Examples:

• - open-ticket count → INLINECODE35
• technician backlog/load → INLINECODE36
• account snapshot → INLINECODE37
• ticket inspection / retrieval-ready context → INLINECODE38

Fuzzy investigation, prior-art lookup, and support-history recall

Use retrieval commands:

• - INLINECODE39
• INLINECODE40
• INLINECODE41
• INLINECODE42
• INLINECODE43
• INLINECODE44
• INLINECODE45
• INLINECODE46
• INLINECODE47

Default retrieval workflow:

1. 1. Start with keyword/text search when the issue words are concrete.
2. Widen to vector search when wording may vary or keyword recall looks thin.
3. Use account/technician/status/priority/category/department/class/submission/resolution filters when they materially narrow the search.
4. Answer from retrieved evidence instead of jumping to canned conclusions.

Quick factual context from generated artifacts

Read these when a concise derived artifact is enough:

• - INLINECODE48
• INLINECODE49
• INLINECODE50
• INLINECODE51
• INLINECODE52
• INLINECODE53
• INLINECODE54
• INLINECODE55
• INLINECODE56
• INLINECODE57
• INLINECODE58
• INLINECODE59

Preferred answer flow

For broad questions like “what’s been going on with account X lately?” or “have we seen this before?”:

1. 1. Pull one structural summary first.
2. Pull retrieval evidence second.
3. Use generated public docs only when they add concise context.
4. Give the user an answer grounded in the retrieved evidence.

Prefer factual retrieval over hand-authored interpretation.

End-to-end install and onboarding on another OpenClaw instance

If the user asks to install SherpaMind properly end-to-end into an OpenClaw instance, first check the host prerequisites and report any missing pieces plainly before continuing.

Minimum prerequisites to check:

• - python3 is present
• Python venv/pip bootstrap works on that host
• the host has network access for Python package installation
• INLINECODE61 is available if background service mode is expected

If any prerequisite is missing, stop and tell the user exactly what is missing and what needs to be fixed.

Then use this flow from the installed skill bundle root:

1. 1. audit bootstrap/readiness first

1. 2. bootstrap the skill-local runtime

1. 3. run the setup flow

1. 4. verify runtime state

1. 5. stage the SherpaDesk API key

1. 6. discover organizations/instances

1. 7. write the chosen org/instance into non-secret settings

1. 8. seed the local dataset

1. 9. generate/refine the derived artifacts if needed

1. 10. confirm the install is actually usable

1. 11. only then decide whether unattended background mode is wanted

Default expectation on Linux is that setup initializes the DB, cleans up any old SherpaMind cron jobs, and can generate an initial public snapshot. Treat user-level systemd installation as a later, explicit operator choice rather than part of the earliest bootstrap steps.

If service installation fails because the target host lacks usable systemctl --user, continue the bootstrap/config/seed flow anyway, report the service limitation clearly, and use python3 scripts/run.py service-run-once or python3 scripts/run.py service-run as the fallback operational mode instead of pretending the service installed.

If install/runtime/use issues or meaningful feature gaps are discovered while operating SherpaMind, check . If a matching issue exists, add supporting detail; otherwise open a new issue with clear reproduction/context. Keep issue content anonymized and public-safe.

Lifecycle and maintenance commands

Use these for setup/maintenance, not routine user queries:

• - INLINECODE82
• INLINECODE83
• INLINECODE84
• INLINECODE85
• INLINECODE86
• INLINECODE87
• INLINECODE88
• INLINECODE89
• INLINECODE90
• INLINECODE91
• INLINECODE92
• INLINECODE93
• INLINECODE94
• INLINECODE95
• INLINECODE96
• INLINECODE97
• INLINECODE98
• INLINECODE99

Boundaries

• - Treat SherpaMind as read-only unless the project explicitly grows write behavior later.
• Keep attachment handling metadata-only by default.
• Do not auto-download attachment bodies by default.
• Treat docs, chunks, vector rows, and public Markdown artifacts as replaceable derived caches.
• Let SherpaMind prepare and expose data; let OpenClaw interpret it at answer time.

References

Read these only when needed. Keep the action layer in this file lean; use the reference files for deeper architecture, retrieval, automation, and API details.

• - {baseDir}/README.md — current live project overview and command surface
• INLINECODE101 — query/retrieval model
• INLINECODE102 — backend vs skill-front boundary
• INLINECODE103 — retrieval and vector design
• INLINECODE104 — audit-first install/onboarding model
• INLINECODE105 — service/install/update model
• INLINECODE106 — hot/warm/cold sync behavior
• INLINECODE107 — verified API/auth behavior