SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Runssource: GitHubhomepagePythonMITcommit 79124b37e9a6
Python, MIT licensed. The project labels itself: agent skills and self evolving agents.
SkillOpt runs. An Argusic agent installed it in 8 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
SkillOpt 0.2.0 installed from source in a PEP 668 venv; all 1496 tests pass; all three CLI entry points respond; the Sleep mock backend cycles without credentials
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 100 of 100 (the mean of this project's run scores).
At a glance
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.
- Install time
- 8 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- python -m pytest tests/ -q exited 0, 1496 passed, 12 skipped in 25.1s; pip install -e . succeeded; skillopt-train --help, skillopt-eval --help, skillopt-sleep --help all printed usage; python -c 'import skillopt; print("SkillOpt ready!")' succeeded; skillopt-sleep dry-run --backend mock completed without credentials
- Model tokens used
- 67,216
- Exact commit tested
- 79124b37e9a6
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- **Install**: `pip install -e ".[dev]"` into a venv succeeded. All CLI entry points (`skillopt-tra… - **Tests**: `python -m pytest tests/ -q` — **1496 passed, 12 skipped, 0 failed** in 25.1 seconds. - **Sleep mock path**: `skillopt-sleep status` and `skillopt-sleep dry-run --backend mock` both com… - **No errors** encountered. tokens used 67,216 All systems verified. Let me compile the final report. **Result summary:** - **Install**: `pip install -e ".[dev]"` into a venv succeeded. All CLI entry points (`skillopt-tra… - **Tests**: `python -m pytest tests/ -q` — **1496 passed, 12 skipped, 0 failed** in 25.1 seconds. - **Sleep mock path**: `skillopt-sleep status` and `skillopt-sleep dry-run --backend mock` both com… - **No errors** encountered.
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
- Reached a running state on a clean machine, with the session recorded.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 8 minutes to install, slower than the median of the 13 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 14 agent-skills projects Argusic has installed and timed, SkillOpt was the 12th fastest to reach a running state, and 11 of 14 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 8 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/skillopt)Questions
- Does SkillOpt run?
- Yes. SkillOpt runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test SkillOpt?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 79124b37e9a6. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test SkillOpt?
- The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does SkillOpt take to install?
- 8 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 SkillOpt need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing SkillOpt?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does SkillOpt compare with the alternatives?
- Of the 14 agent-skills projects Argusic has installed and timed, SkillOpt was the 12th fastest to reach a running state, and 11 of 14 reached one at all.
- Where is the evidence for SkillOpt?
- 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.