AC debugging-network-issues
Investigates network, streaming, and protocol failures with falsification-first layered experiments. Use for ECONNRESET, HTTP/2 RST_STREAM, SSE or long-polling stalls, fixed-time drops, CDN/proxy/CGNAT timeouts, client-side proxy/TUN misrouting, CNAME-rule surprises, certificate errors, generic throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Trigger phrases include "socket closed unexpectedly", "stream interrupted", "fails after N seconds", "works sometimes but not always", "upstream silent for X seconds", ERR_CONNECTION_CLOSED, SSL_ERROR_SYSCALL, UNKNOWN_CERTIFICATE_VERIFICATION_ERROR, and wrong-site certificate. Treat this as the general method and unknown-root-cause fallback. Use tunnel-doctor for known Tailscale/TUN/DNS/route/WSL-Docker conflicts and for a confirmed proxy exit/node/chain quality problem.
Investigates network, streaming, and protocol failures with falsification-first layered experiments.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 13576 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 13576 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 85Steps. 112 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (32 tags): a typed call is more reliable
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 877: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 31 headings
- +3Step-by-step instructions: 112 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.