Key is now provisioned + live-verified, so grounded the skill in the real spec (RTFM):
- Mapped the OpenAPI surface (v44.4.10, 239 paths / 354 ops) — capability map added to
SKILL.md (what the platform exposes vs what's wrapped vs raw-only).
- Added 6 live-verified read wrappers (ns.py + ns_client.py): callqueues, timeframes,
sites, contacts, autoattendants, billing (domain limits/usage).
- Replaced the stale "not yet provisioned" credentials section with the live status
(vaulted nsr_ reseller key, key-id nsr_hSGUB5Wo, scope Reseller 91912.service, RW) +
the pbx.packetdial.com vs api.ucaasnetwork.com hostname note + override.
- api.md history updated. Writes remain gated behind --confirm; everything unwrapped
reachable via `raw`.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add .claude/scripts/log-skill-error.sh — the canonical agent error log helper
(writes errorlog.md in DATE | MACHINE | skill | [type] error format, soft-fails).
Three categories: execution failures (default), user corrections (--correction),
and preventable self-inflicted friction (--friction; cite ref= when it repeats a
documented gotcha). Goal: stop paying tokens twice for the same avoidable mistake.
- CLAUDE.md: make logging mandatory for all skills + corrections + friction.
- skill-creator: new skills must wire in the helper (guidance + checklist).
- Retrofit every skill script's genuine failure branches to call the helper
(b2/bitdefender/mailprotector/packetdial/coord python CLIs; remediation-tool
+ onboard365 bash; vault, rmm-auth, post-bot-alert, agy, grok, 1password,
run-onboarding-diagnostic). Handled conditions + self-tests left alone.
- errorlog.md: broaden header to cover skills + harness + corrections; seed this
session's corrections (INKY, Mail.Send token-audience, omnibox-strictness) and
friction (git-bash /tmp, env-persistence, argv-limit, PowerShell var-case).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
