You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 20a42af
Browse filesBrowse the repository at this point in the historyBrowse files
Open a new session and type `/skills` in MiniMax Code to see it.
66
+
`mcode plugin add` installs from the official catalog only; it does not take
67
+
a GitHub URL or a local path.
92
68
93
69
The skills use the common `SKILL.md` format, so most of them also work in
94
70
other agents that support skills.
95
71
96
-
### Install a whole stack as a plugin
72
+
</details>
97
73
98
-
Every stack is also a MiniMax Code plugin package. Find your local plugin
99
-
directory:
74
+
## What's inside
100
75
101
-
```bash
102
-
mcode plugin marketplace list
103
-
```
76
+
<palign="center">
77
+
<imgsrc="docs/assets/skills-map.png"alt="The 15 skills in stacks/ronny, grouped by moment in the day"width="100%">
78
+
</p>
104
79
105
-
Copy the whole `stacks/ronny` directory into that directory, then open
106
-
`/plugins` in MiniMax Code and press `Ctrl+R` to refresh. A local plugin is
107
-
installed as soon as it is in that directory; press Space in the panel to
108
-
enable or disable it.
80
+
| When | Skill | What it does |
81
+
| --- | --- | --- |
82
+
| Plan & split |[`subagent-split-check`](stacks/ronny/skills/subagent-split-check/SKILL.md)| Decide whether work goes to a subagent or stays in the main loop |
83
+
||[`engineering-small-prs`](stacks/ronny/skills/engineering-small-prs/SKILL.md)| Split large features, refactors and migrations into small reviewable PRs |
84
+
||[`engineering-change-descriptions`](stacks/ronny/skills/engineering-change-descriptions/SKILL.md)| Write PR and commit descriptions that say what changed and why |
85
+
| Context & tools |[`tool-budget-audit`](stacks/ronny/skills/tool-budget-audit/SKILL.md)| Measure what tools cost in context; trim, tool search or programmatic tool calling |
86
+
||[`context-tax-audit`](stacks/ronny/skills/context-tax-audit/SKILL.md)| What gets injected into every request, and what it does to the prompt cache |
87
+
| Long sessions & commands |[`long-session-check`](stacks/ronny/skills/long-session-check/SKILL.md)| Drop, summarize or write to file; compact or start fresh; memory scoping |
88
+
||[`handoff-doc`](stacks/ronny/skills/handoff-doc/SKILL.md)| A hand-off doc so a new session can pick up the work |
89
+
||[`long-command-check`](stacks/ronny/skills/long-command-check/SKILL.md)| Ten-point audit of long shell commands and background tasks |
90
+
| Review |[`independent-review`](stacks/ronny/skills/independent-review/SKILL.md)| Review a diff from a clean context: only diff, requirement and test results |
91
+
||[`engineering-code-review`](stacks/ronny/skills/engineering-code-review/SKILL.md)| Review a change for code health: design, functionality, complexity, tests, approval risk |
92
+
||[`engineering-review-comments`](stacks/ronny/skills/engineering-review-comments/SKILL.md)| Write clear, severity-labeled review comments that explain the reasoning |
93
+
||[`engineering-review-feedback`](stacks/ronny/skills/engineering-review-feedback/SKILL.md)| Handle reviewer comments as the author: fix, clarify, resolve disagreements |
94
+
| Experiments & hotfixes |[`harness-experiment`](stacks/ronny/skills/harness-experiment/SKILL.md)| Small eval, one change at a time, repeated runs, look at flipped tasks |
95
+
||[`trajectory-review`](stacks/ronny/skills/trajectory-review/SKILL.md)| Look at how the agent got its result, not only whether it passed |
96
+
||[`engineering-emergency-changes`](stacks/ronny/skills/engineering-emergency-changes/SKILL.md)| Decide whether a hotfix is a real emergency and run expedited review safely |
109
97
110
-
`mcode plugin add` installs from the official catalog only; it does not take
111
-
a GitHub URL or a local path.
98
+
A stack usually has three kinds of things:
99
+
100
+
| Kind | What it is | How to use it |
101
+
| --- | --- | --- |
102
+
| Skill | A directory with a `SKILL.md`| Invoke it in MiniMax Code with `/<skill-name>`, or let the agent load it from its description |
103
+
| Checklist | Also a skill: the agent walks your project item by item. A plain-text copy lives in `checklists/`| Same as above, or just read it |
104
+
| Workflow | A `WORKFLOW.md` describing how this person works with MiniMax Code every day | Read it |
105
+
106
+
## How it works
107
+
108
+
<palign="center">
109
+
<imgsrc="docs/assets/how-it-works.png"alt="From an Engineering Notes article to a skill, installed into MiniMax Code and run on your project"width="100%">
110
+
</p>
111
+
112
+
AI writes code faster every month. What separates results now is the layer
113
+
of engineering habits around the agent: when to make it stop and check its
114
+
own work, who reviews, where state lives, what counts as a real experiment.
115
+
Those habits are hard to follow from an article, so we turned them into
116
+
skills and checklists. They pair with our *MCode Engineering Notes* column:
117
+
the article explains the idea, this repository makes it runnable.
118
+
119
+
We also believe harness engineering is a craft that moves forward by
120
+
experiment. Everything here will keep changing as we learn. Take it, change
0 commit comments