Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/dev-guide-runtime-self-check
Nested lingtai-dev-guide reference for developer/operator runtime self-checks after a refresh, checkout, or preset/MCP change: probe which lingtai code is actually running, confirm the editable source and git HEAD, verify the active TUI/portal binary and dev-mode symlinks, rebuild the TUI from a clean release worktree, inspect MCP/addon module sources and tool surface, and report evidence safely with secrets redacted. Includes verifying that long-lived runtime objects (services/adapters/caches)
Passed 17 of 21 test cases with the skill, and 6 of 21 without it.
and 16 more in the full report
13 fixed7 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to output the standardized evidence pack text format for a completed import provenance check that found no issues. What is the required header line and what should be listed under anomalies?
| Checked | Without skill | With skill |
|---|---|---|
| Uses header format runtime self-check @ <iso-timestamp>. | Missed | Passed |
| Lists anomalies as none when no issues are found. | Passed | Passed |
The instructions your model reads when the skill loads.
Nested lingtai-dev-guide reference. This is a deep diagnostic library selected
only when a cutover, observed failure, or suspected mismatch raises a provenance
or lifecycle question. Kernel system-manual →
reference/refresh-precheck/SKILL.md is the single owner of ordinary agent
refresh sequencing; this reference neither repeats nor initiates that
transaction.
Probe, confirm, and report only the assertion named by the trigger. Diagnosis is
read-only. A rebuild, editable reinstall, relink, source update, process stop, or
clean relaunch needs separate exact authorization and its owning procedure. Never
paste secrets into a report: redact tokens, keys, chat IDs, and private absolute
paths, preferring <your-lingtai-checkout> / ~/.lingtai-tui/... forms.
PYTHONPATH mismatch needs source diagnosis or the
separately authorized clean-relaunch recovery.Ordinary same-runtime reload does not use this deep checklist. A routine
reload or preset swap with no provenance question routes directly to kernel
system-manual → reference/refresh-precheck/SKILL.md.
A merged change or correct-looking checkout is not proof of what the live agent imports. Keep the owner boundary explicit:
test cases passed, vs 6 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.