distilly
Distilly, Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
Runssource: GitHubPythonMITcommit b830d3dcbde0
Python, MIT licensed. The project labels itself: agent skills, agentic ai, ai agent, ai agents, ai assistants, ai persona, claude code and claude skills.
distilly runs. An Argusic agent installed it in 27 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The full test suite passes (73/73, plus 9 subtests), the Node.js CLI installs the distilly skill to any target path, and every Python tool in tools/ prints correct usage on --help.
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 96 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
- 27 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/ --tb=short -q: 73 passed, 9 subtests passed, 0 failed; node bin/distilly.mjs --version returned 1.0.0; node bin/distilly.mjs install --path /tmp/test-install/distilly --force wrote SKILL.md + all payload files; all 12 Python tools (skill_writer, feishu_parser, slack_auto_collector, email_parser, srt_to_transcript, merge_research, quality_check, xquik_public_posts, install_hermes_skill, install_openclaw_skill, install_codex_skill, install_generated_skill) responded to --help with correct usage.
- Model tokens used
- 33,967
- Exact commit tested
- b830d3dcbde0
- 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.
Everything installed and verified cleanly. Here's my report: The repository has no install errors — Python dependencies installed into a venv (required due to P… exec /bin/sh -lc 'cd /work/repo && /work/repo/venv/bin/python -m pytest tests/ --tb=short -q 2>&1 | tail… succeeded in 1652ms: ............................................................... [ 86%] .......... [100%] 73 passed, 9 subtests passed in 1.53s All 73 tests pass (no errors, no fixes needed). The project installed cleanly and every tool and CL… tokens used 33,967 All 73 tests pass (no errors, no fixes needed). The project installed cleanly and every tool and CL…
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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 27 minutes to install, slower than the median of the 118 comparable projects Argusic has measured.
Of the 119 agent-skills projects Argusic has installed and timed, distilly was the 111th fastest to reach a running state, and 90 of 119 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.
- Following its own README: the documented path worked with nothing to fix.
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 | 2/3 | Runs | 100.00 | 0.03 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.02 |
Topics (from GitHub)
agent-skillsagentic-aiai-agentai-agentsai-assistantsai-personaclaude-codeclaude-skillscodexcodex-skillsdeepseek-harnessdigital-humandsh-pluginhermes-agentknowledge-distillationllm-agentmeta-skillopenclawpersonal-agent
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/distilly)Questions
- Does distilly run?
- Yes. distilly runs. Argusic installed and launched it on a clean machine in 27 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test distilly?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b830d3dcbde0. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test distilly?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does distilly take to install?
- 27 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 distilly need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing distilly?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does distilly compare with the alternatives?
- Of the 119 agent-skills projects Argusic has installed and timed, distilly was the 111th fastest to reach a running state, and 90 of 119 reached one at all.
- Where is the evidence for distilly?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.