AB huly
Drive a self-hosted Huly workspace through the `huly` CLI when the user names a Huly-specific entity or action — tracker issue, project, channel, DM, calendar event, planner action/todo, time entry, notification, or approval. Use it for project tracking, time management, and workspace automation against a self-hosted Huly instance. Do not invoke on unconfirmed intent; if the user is ambiguous about whether to persist, ASK first.
Drive a self-hosted Huly workspace through the huly CLI when the user names a Huly-specific entity or action — tracker issue, project, channel, DM, calendar…
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/spaces-types-and-relations.md:290Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Disabling RBAC** is a global, workspace-wide privilege escalation. The CLI does not expose the toggle (server-side only: Settings → General → disable RBAC for the whole workspace). Anyone with any
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10971 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 84 mutating operations with no state check
- 40Execution cost. Instruction body is 10971 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 85Steps. 37 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 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
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (22 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
- +4Description does not say when NOT to use the skill (false activations)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 432: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.