bitwisecook/tcl-lsp/explain-flow

Claude Code and agent skill by bitwisecook/tcl-lsp

Trust tier 3
  • community
Source check pending

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

Trace each session in a PCAP through a BIG-IP configuration and explain what the device did to it: matched virtual server, profiles, iRule HUD decisions (the `[HTTP::host]`, `[SSL::extensions]`, `[LB::server]` values the iRule branched on), event firing order, observed pool member and SNAT, termination analysis (TCP RST, F5 reset cause, TLS alert), and — with `simulate=true` — the actual outcome of running the iRule under c-tcl. Understands `tcpdump -i <vlan>:np` captures that carry both front (client↔VIP) and back (TMM↔pool member) sides of the same conversation, paired via the F5 ethernet trailer. Decrypts TLS when given a NSS-format keylog file. Use when a user asks "what would BIG-IP do with this capture?", "which iRule events fired for this flow?", "why did this connection reset?", or "explain this PCAP against this bigip.conf".

Install

npx vskill@latest install bitwisecook/tcl-lsp/explain-flow

SKILL.md

Explain a flow against a BIG-IP config

Steps

  1. Read ../_prompts/explain_flow_system.md: the JSON shape, how to

narrate each field, and the limitations.

  1. Call mcp__tcl-lsp__explain_flow — preferred — with pcap_path,

config_paths (array) or config_text, and as needed use_tshark, keylog_path (NSS keylog for HTTPS), tshark_filter (e.g. "host 10.0.0.5 and port 443"), max_event_body_lines, simulate.

  1. Narrate each session per the guide.

Keep the context small

  • tshark_filter whenever the user asks about one flow; a big capture

otherwise returns a session per 5-tuple.

  • max_event_body_lines 4 when they want the decision, 0 to drop bodies.
  • CLI fallback only when the MCP tool is unreachable, and then the text

report: f5-query explain-flow capture.pcap bigip.conf (--max-event-lines 8, --no-event-bodies, --tshark-filter '…'). --json is the same value the MCP tool returns — for piping to another tool, never for your own reasoning.

$ARGUMENTS

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

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

Source

Popularity

7-day trend score
5

Not refreshed yet.

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/bitwisecook/tcl-lsp/explain-flow/badge)](https://verified-skill.com/skills/bitwisecook/tcl-lsp/explain-flow)

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