SKILLEMALL.ai
GitHub ↗ RU Sign in

BC comfyui

Generate images, video, and audio via diffusion workflows.

nousresearch/hermes-agent Hermes author: nousresearch MIT 33 files · 17 scripts body ≈ 5 658 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Generate images, video, and audio via diffusion workflows.

As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

ProcedureGitHubAI and agentsMedia and videotype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
75
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: comfyui (NousResearch/hermes-agent)

How to improve

  1. 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 · 0

✓ No critical or high findings

Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5658 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "prerequisites"
  • note frontmatter-key unknown frontmatter key "setup"
  • note edit-residue the text marks something as outdated (lines 103): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 51/100

  • 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
  • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
  • 60Steps. 51 steps, 4 vague phrases
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5658 tokens
  • 100Failures and branches. 2 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • low 12 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 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)
  • +3Description length 58: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 51 items
  • +4Has examples (22 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 11 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

In the sandbox The scripts write outside their folder

The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.

Запущено 11 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.

Из них 9 не дошли до работы, и об их поведении мы ничего не узнали.

scripts/_common.pyничего за пределами своей папки
scripts/auto_fix_deps.pyне запустился: auto_fix_deps.py: error: the following arguments are required: workflow
scripts/check_deps.pyне запустился: check_deps.py: error: the following arguments are required: workflow
scripts/comfyui_setup.shпишет или удаляет вне своей папки (~/.hermes/cache/scratch/comfyui_setup.692.log); завершился с кодом 2
scripts/extract_schema.pyне запустился: extract_schema.py: error: the following arguments are required: workflow
scripts/fetch_logs.pyне запустился: Error: prompt_id is required (or use --tail-queue)
scripts/hardware_check.pyне запустился: • CPU-only ComfyUI works but is unusably slow for modern models — use Comfy Cloud.
scripts/health_check.pyзаглядывает в ~/.netrc — так делает библиотека HTTP, когда ищет логин для сайта; не запустился: "error": "HTTPConnectionPool(host='127.0.0.1', port=8188): Max retries exceeded with url: /system_stats (Caused by NewConnectionError('<urll
scripts/run_batch.pyне запустился: run_batch.py: error: the following arguments are required: --workflow
scripts/run_workflow.pyне запустился: run_workflow.py: error: the following arguments are required: --workflow
scripts/ws_monitor.pyне запустился: {"error": "websocket-client not installed", "install": "pip install websocket-client"}

6 Oct 2026