ai-skills

24 cross-platform agent skills for Claude Code, Cursor, Codex & Gemini CLI, databases, messaging, research, TTS, DevOps, and Google Workspace

Runs with mockssource: GitHubhomepagePythonApache-2.0commit 281d88df1993

Python, Apache-2.0 licensed. The project labels itself: agent skills, ai skills, atlassian, azure devops, claude code, claude skills, codex and cursor.

ai-skills runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.

All Python deps install and the full pytest suite passes (11 passed, 1 skipped); Outline, Telegram, Google TTS, ElevenLabs, Imagen, and NotebookLM E2E smoke are verified working against local mocks with production defaults preserved, while real-database skills and credential-gated third-party skills remain unverified inside the container.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 86.3 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
86.3 / 100
cost of the verifying run
$0.81 (measured)
recorded runs
1
last tested
stars
458
forks
53
open issues
4
watchers
1
size
0 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing ai-skills, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • outline.py crashed on real API payload shape (documents.search/collections.list/list.documents data nesting, auth.info team shape)25 minutes
  • pymssql TDS wire mock: login accepted by FreeTDS but token stream rejected (189-20002 errors), no real SQL Server in container18 minutes
  • hero network TLS: eleven/google-tts terminals hardcoded real hostnames; verified via env-overridable base URLs + local mocks (audio mp3 decoded clean with ffmpeg)12 minutes
  • repo test binary uses /usr/bin/python3 without project deps; smoke test crashed importing playwright10 minutes
  • no DB servers inside container; postgres/mysql/mssql scripts need real servers6 minutes
  • notebooklm smoke required playwright chromium binary per README3 minutes
Install time
5 minutes
Cold machine to finish
40 minutes
Errors hit and fixed
7 hit, 5 fixed with no human help
How the result was proved
python -m pytest skills/notebooklm/tests => 11 passed 1 skipped; NOTEBOOKLM_E2E=1 smoke => 1 passed (173s); outline auth-info/search/list-collections => rc=0; telegram.sh send => rc=0; google-tts tts + ffmpeg -f null => 0; elevenlabs voices/tts + ffmpeg => 0; imagen gen + ffmpeg decode => 0; every command observed end-to-end with local mocks
Model tokens used
3,897,596
Exact commit tested
281d88df1993
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

         raise AssertionError(f"Command failed ({proc.returncode}): {' '.join(command)}\n{proc.stdo…
exec
/bin/sh -lc 'date -u +%Y-%m-%dT%H:%M:%SZ; git -C /work/repo log --oneline -1 2>/dev/null' in /work/…
 succeeded in 0ms:
2026-10-21T07:01:03Z
281d88d feat(google-chat): add edit/delete/react, media, threads, and optional aliases (#23)
I've completed the work. Here is my report.
**ARGUSIC_RESULT**: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5, "er…
tokens used
3,897,596
I've completed the work. Here is my report.
**ARGUSIC_RESULT**: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 5, "er…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Licensed Apache-2.0, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 5 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.
  • Hit 7 errors during setup, 2 of which were not solved.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 128 agent-skills projects Argusic has installed and timed, ai-skills was the 86th fastest to reach a running state, and 96 of 128 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks86.290.81

Topics (from GitHub)

agent-skillsai-skillsatlassianazure-devopsclaude-codeclaude-skillscodexcursordeep-researchelevenlabsgemini-cligoogle-workspaceimagenmcpmysqlnotebooklmpostgresqltelegramtext-to-speechwhatsapp

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/ai-skills.svg)](https://argusic.com/subject/ai-skills)

Questions

Does ai-skills run?
ai-skills runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test ai-skills?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 281d88df1993. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test ai-skills?
The run that produced this verdict cost $0.81: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does ai-skills take to install?
5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does ai-skills need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ai-skills?
7 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does ai-skills compare with the alternatives?
Of the 128 agent-skills projects Argusic has installed and timed, ai-skills was the 86th fastest to reach a running state, and 96 of 128 reached one at all.
Where is the evidence for ai-skills?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion