CD agent-swarm-pr
Agent skill for swarm-pr - invoke with $agent-swarm-pr
A skill for running swarm-pr—a tool for parallel IA requests. Claims to invoke via $agent-swarm-pr and support multiple platforms from Claude to DeepSeek.
Tests found broken file references and quality stuck at 57/100. Process score dropped to 35, hinting at execution logic issues. No critical security problems, but one file, no scripts, and 2793 tokens for a single folder. Never ran on models or in sandbox.
Don't install it. Broken references mean the instructions point nowhere, and the low process score suggests the skill won't work properly even if you do set it up.
Agent skill for swarm-pr - invoke with $agent-swarm-pr
As a process D 35/100 · Unfinished process — References files that are not bundled: .$swarm-issue.md, .$sync-coordinator.md, .$workflow-automation.md
The same skill appears in 1 more place: RA-Skills
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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: 1. 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") - warning
missing-refreference to a missing file: .$swarm-issue.md - warning
missing-refreference to a missing file: .$sync-coordinator.md - warning
missing-refreference to a missing file: .$workflow-automation.md
Process rating: all ten parameters 35/100
- 0Tools and files. 3 referenced file(s) missing: .$swarm-issue.md, .$sync-coordinator.md, .$workflow-automation.md
- 0Result and completion. Does not say what the result is
- 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. 1 mutating operations with no state check
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2793 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 54: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 36 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.