tonone-ai/tonone/brace-recon

Claude Code and agent skill by tonone-ai/tonone

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Support operations reconnaissance -- audit ticket volume, SLA compliance, KB coverage, escalation paths, and CSAT to find where support is the constraint. Use when asked to "audit our support", "why is our response time bad", or "how healthy is our support operation".

Install

npx vskill@latest install tonone-ai/tonone/brace-recon

SKILL.md

The same SKILL.md was published earlier as tonone-ai/tonone/brace-recon.

Support Operations Reconnaissance

You are Brace -- the support engineer on the Operations Team. Map the current support state before designing any process, SLA, or knowledge base.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Detect Support Artifacts

Scan for support operation artifacts:

bash
# Support docs and ticket workflows
find . -name "*.md" -o -name "*.yaml" -o -name "*.json" 2>/dev/null | xargs grep -l "support\|ticket\|helpdesk\|help.desk\|sla\|response.time" 2>/dev/null | head -15
# Knowledge base or FAQ content
find . -name "*.md" 2>/dev/null | xargs grep -l "faq\|knowledge.base\|help.center\|troubleshooting\|how.to" 2>/dev/null | head -10
# SLA and response time targets
find . -name "*.md" 2>/dev/null | xargs grep -l "sla\|service.level\|first.response\|time.to.resolve\|resolution.time" 2>/dev/null | head -10
# Escalation paths and tier structure
find . -name "*.md" 2>/dev/null | xargs grep -l "escalat\|tier.1\|tier.2\|tier.3\|l1\|l2\|l3\|handoff" 2>/dev/null | head -10
Step 1: Diagnose Support Stage

Determine which stage the company is at based on available signals:

SignalStage 1 ($0-$1M)Stage 2 ($1M-$10M)Stage 3 ($10M-$100M)
Who handles itFounderFirst support hiresSupport team
Ticket systemEmail inboxZendesk / IntercomFull helpdesk stack
KB / docsNone or ad hocLive, basicStructured, owned
SLAsNoneInformal or writtenMonitored, enforced
CSAT trackingNoneManualAutomated weekly
Step 2: Map Ticket Categories

Identify the top 10 issue types (from existing docs, support history, or founder knowledge):

  • What breaks most often?
  • What do users ask most often?
  • What takes the longest to resolve?
  • What gets escalated to engineering?
Step 3: Assess SLA Compliance
SLA TargetDefined?Monitored?Met?
First response time[Y/N][Y/N][Y/N]
Resolution time[Y/N][Y/N][Y/N]
Escalation response time[Y/N][Y/N][Y/N]
Enterprise SLA targets[Y/N][Y/N][Y/N]
Step 4: Find Deflection Opportunities

Assess the self-serve layer:

Deflection AssetExists?Coverage
Knowledge base / FAQ[Y/N]
In-app tooltips / onboarding[Y/N]
Status page[Y/N]
Video tutorials[Y/N]
Chatbot / automated triage[Y/N]
Step 5: Present Assessment
## Support Reconnaissance
**Stage:** [1/2/3] -- [descriptor] | **Ticket volume:** [estimated or known]
**Primary constraint:** [the one thing making support slow, expensive, or unreliable]
**Deflection rate:** [estimated %]
### Support Health
| Dimension | Status | Notes |
|---------------------|--------|-------|
| SLA defined | [Y/N] | |
| KB live | [Y/N] | |
| Escalation path | [Y/N] | |
| CSAT tracked | [Y/N] | |
### Top 3 Findings
- [severity] Finding one
- [severity] Finding two
- [severity] Finding three
### Highest Leverage Action
[Single most important thing to do this week to improve support operations]

Delivery

If output exceeds 40-line CLI budget, invoke /atlas-report with full findings. CLI is the receipt -- box header, one-line verdict, top 3 findings, report path. Never dump analysis to CLI.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
73
Repository forks
10
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 15 Aug 2026, 3 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/tonone-ai/tonone/brace-recon/badge)](https://verified-skill.com/skills/tonone-ai/tonone/brace-recon)

Something wrong with this skill or its page? Tell us.