AC release-feature-watcher
Use when the user wants to monitor a technical feature, bugfix, model/API update, changelog, release, package version, or PR and be notified only when a specific actionable condition is met.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
IntegrationInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 190 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 60/100
- 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
- 30Running it twice. 16 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 109 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Execution cost. Instruction body is 3237 tokens
- low 17 top-level sections: this looks like several domains in one skill
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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 190: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 109 items
- +4Has examples (19 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.
External checks
ClawHub: clean
This skill is a disclosed release-monitoring helper that creates user-directed watchers and does not show hidden data collection or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026