skill-conductor
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.
Runs with mockssource: GitHubhomepagePythonMITcommit 3c21d2f19c33
Python, MIT licensed. The project labels itself: agent skills, ai agents, anthropic, claude code, claude plugin, claude skill, knowledge management and llm.
skill-conductor runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 13 Python scripts in skill-conductor successfully parse and run: smoke tests pass (12/12), structural eval passes (22/22, score 10/10), skill init creates valid structure, packaging produces valid .skill zip, and scripts requiring LLM access (run_eval, improve_description, run_loop) parse their args correctly but need ANTHROPIC_API_KEY to execute real evaluations.
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 92 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- from scripts.utils import parse_skill_md fails under uv run — scripts/ is not a package2 minutes
- improve_description.py and run_loop.py missing inline dependency header for anthropic1 minute
- Install time
- 1 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- uv run scripts/test_smoke.py exited 0, 12/12 passed; uv run scripts/eval_skill.py . returned 22/22 passed, score 10/10; all 11 CLI scripts respond to --help/usage
- Model tokens used
- 255,210
- Exact commit tested
- 3c21d2f19c33
- 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.
| Error | Fix | Time | |-------|-----|------| | 3 scripts (`run_eval.py`, `improve_description.py`, `run_loop.py`) used `from scripts.utils impor… | `improve_description.py` and `run_loop.py` lacked inline `# /// script` dependency headers for `a… **Verification**: - `uv run scripts/test_smoke.py` → 12/12 passed - `uv run scripts/eval_skill.py .` → 22/22 passed, score 10/10 - `uv run scripts/eval_skill.py . --json` → 17 deterministic records, all pass (5 critical) - `uv run scripts/init_skill.py` → creates valid skill structure - `uv run scripts/package_skill.py` → creates valid `.skill` zip - All 11 scripts with CLIs respond to `--help` or usage - Scripts requiring `claude` CLI or `ANTHROPIC_API_KEY` (`run_eval.py`, `improve_description.py`, `…
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
- Installed in 1 minute, faster than the median of the 104 comparable projects Argusic has measured.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 105 agent-skills projects Argusic has installed and timed, skill-conductor was the 20th fastest to reach a running state, and 75 of 105 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Topics (from GitHub)
agent-skillsai-agentsanthropicclaude-codeclaude-pluginclaude-skillknowledge-managementllmobsidianpersonal-assistantproductivityprompt-engineeringsecond-brainskill-authoringskillstdd
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/skill-conductor)Questions
- Does skill-conductor run?
- skill-conductor runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test skill-conductor?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3c21d2f19c33. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test skill-conductor?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does skill-conductor take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does skill-conductor need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing skill-conductor?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does skill-conductor compare with the alternatives?
- Of the 105 agent-skills projects Argusic has installed and timed, skill-conductor was the 20th fastest to reach a running state, and 75 of 105 reached one at all.
- Where is the evidence for skill-conductor?
- 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.