CC claude-delegate
Delegate coding, repository analysis, file edits, test runs, or code review to the local Claude Code CLI without embedding an Anthropic API key. Works with Claude Pro/Max/Enterprise accounts that authenticate via OAuth and have no API key. Invokes claude -p with the existing Claude CLI login and returns Claude's final output.
Delegate coding, repository analysis, file edits, test runs, or code review to the local Claude Code CLI without embedding an Anthropic API key.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
-
high Exfiltration
exfil-read-secret-filesSKILL.md:21Reads credential / secret filesIf Claude is not authenticated, tell the operator to run `claude auth status` then `claude auth login` once and complete the browser sign-in. Do not request, print, copy, or inspect `~/.claude/.creden
-
high Exfiltration
exfil-read-secret-filesSKILL.md:76Reads credential / secret files- Never read, reveal, summarize, or copy `~/.claude/.credentials.json`.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
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
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1051 tokens
- 100Running it twice. No mutating operations
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 327: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.