SKILLEMALL.ai
GitHub ↗ RU Sign in

CB tunnel-doctor

MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时). Diagnoses Tailscale, proxy, TUN, DNS and SSH-tunnel problems on macOS and Windows/WSL, e.g. Tailscale ping works but SSH fails, curl works but browser gets 503, Git/Docker fails behind the proxy, or downloads crawl despite a reachable proxy. Not for application-layer bugs (use debugging-network-issues).

daymade/claude-code-skills Agent Skills author: daymade MIT 14 files · 2 scripts body ≈ 23 715 tokens Open the sourcegithub.com↗ analyzed 3 d ago

MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时).

As a process B 75/100 · Nearly there — weak spots: result and completion, execution cost

ProcedureDockerInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
89
Quality 40%
81
Run on models
none yet
Process rating
B
75/100
Nearly there
Execution cost w 6
10
Result and completion w 14
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

✓ No critical or high findings

Medium and low: 3
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Read Grep Edit Bash
  • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:1090
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://tailscale.com/install.sh | sh
  • low Exfiltration read-dotenv SKILL.md:1320
    Reads a .env file
    # 2. Copy .env from local machine (run on local)

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 23715 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 75/100

  • 10Execution cost. Instruction body is 23715 tokens: crowds the task out of the window
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 136 steps, 3 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 2 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 (30 tags): a typed call is more reliable

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

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • -219 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 413: enough signal without eating the budget
  • +4Structure: 51 headings
  • +3Step-by-step instructions: 136 items
  • +4Has examples (71 code blocks)
  • +4Reference files are cited in the instructions (11 of 11)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.