CC talentclaw
Talent advisor skill for AI agents, built by Artemys. Helps your human clarify career direction, build a compelling professional profile, discover relevant opportunities, apply strategically, and communicate with employers. Connects to Coffee Shop, the agent-to-agent talent network, for job discovery, applications, and employer messaging. Use when the user asks about job searching, career opportunities, applying to positions, updating their resume, checking application status, or says "find me a job" or "check my inbox".
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 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.
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
- 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 8
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:26Downloads and executes remote code from an unrecognised host (pipe to shell)curl -fsSL https://skills.sh/i/talentclaw | bash
Medium and low: 7
-
medium Dangerous commands
cmd-pipe-to-shellscripts/setup.sh:52Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo " Option B (fnm): curl -fsSL https://fnm.vercel.app/install | bash && fnm install 22"
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/setup.sh:58Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo " curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -"
code literal -
medium Dangerous commands
cmd-pipe-to-shellscripts/setup.sh:61Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)echo " curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -"
code literal -
medium Dangerous commands
cmd-shell-rcscripts/setup.sh:118Writes to a shell startup fileecho " echo 'export PATH=~/.npm-global/bin:\$PATH' >> ~/.bashrc && source ~/.bashrc"
-
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/setup.sh:51Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)echo " Option A (nvm): curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash && nvm install 22"
code literal -
low Dangerous commands
cmd-privilegescripts/setup.sh:58Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)echo " curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -"
detectorcode literal -
low Dangerous commands
cmd-privilegescripts/setup.sh:61Privilege escalation / world-writable permissions (detector / deny-list definition; string literal in code, not executed)echo " curl -fsSL https://rpm.nodesource.com/setup_22.x | sudo bash -"
detectorcode literal
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5048 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5048 tokens
- 85Steps. 78 steps, 2 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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
- +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
- +5Description quotes 2 example trigger phrases
- +3Description length 526: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.