SKILLEMALL.ai
GitHub ↗ RU Sign in

CD ask-cargo

One agent the whole team @mentions in Slack, sitting on top of your GTM repo and workspace: it answers from context, cadence and live runs, turns change requests into pull requests, captures a thread worth keeping into the cadence log and context, and hands work to the other deployed agents only after a go in the thread. Triggers: "let the team ask our GTM agent from slack", "one agent on top of all the others", "a slack bot that knows our repo", "ask cargo from slack", "orchestrator agent for our GTM stack", "let anyone open a PR from slack", "capture this slack thread into our context". Cargo CDK, defineAgent, harness claudeCode, Slack connector trigger, GitHub, cargo-ai CLI. Skip when: you want the day recapped and posted to Slack on a schedule, which is standup; or you want an answer in this chat right now with nothing deployed.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Cargo v0.2.1 MIT-0 13 files · 7 scripts body ≈ 5 411 tokens Open the sourceclawhub.ai↗ analyzed 7 d ago

One agent the whole team @mentions in Slack, sitting on top of your GTM repo and workspace: it answers from context, cadence and live runs, turns change…

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationSlackGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
82
Quality 40%
79
Run on models
none yet
Process rating
D
49/100
Unfinished process
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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.

Instruction override
If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. 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.
  2. 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 · 1

  • high Instruction override en-ignore-previous skill-card.md:29
    Instruction-override phrase ("ignore previous instructions")
    Risk: Repository instructions could override safety instructions.

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5411 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 49/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 29 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5411 tokens
  • 100Steps. 36 steps
  • 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
  • low The response is described with custom markup (4 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 844: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
This skill openly builds a Slack agent for repo and workspace work, but its channel reach and instruction precedence create review-worthy risk before installation.
LLM: suspicious (high) · 8 Oct 2026