academic-army 0.3.6 → 0.3.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +11 -11
- package/README.zh-CN.md +10 -10
- package/package.json +2 -2
- package/skills/academic-army-literate-latex-writing/SKILL.md +5 -0
package/README.md
CHANGED
|
@@ -103,7 +103,7 @@ npm run evolve-skill
|
|
|
103
103
|
|
|
104
104
|
For the shared CLI and pipeline structure, see [`src/README.md`](src/README.md).
|
|
105
105
|
|
|
106
|
-
For `developing` and `developing-skill`, update the file passed to `--goal-path` when you want to run a new task focus. The prepared wrappers use `output/goal.md`.
|
|
106
|
+
For `developing` and `developing-skill`, update the file passed to `--goal-path` when you want to run a new task focus. The prepared wrappers use `output/goal.md`. The base development loop comes from `developing-agent-forge`; this repository provides the `developing-skill` trajectory optimizer locally.
|
|
107
107
|
|
|
108
108
|
### Call MCP Tools
|
|
109
109
|
|
|
@@ -121,16 +121,16 @@ Find the closest papers to this research idea, compare their methods, and return
|
|
|
121
121
|
|
|
122
122
|
## Project Structure
|
|
123
123
|
|
|
124
|
-
| Path | Purpose
|
|
125
|
-
| ------------------ |
|
|
126
|
-
| `agent-forge.yaml` | Agent and team wiring.
|
|
127
|
-
| `install_mcp.py` | Installs the project MCP server into Codex for direct skill runs.
|
|
124
|
+
| Path | Purpose |
|
|
125
|
+
| ------------------ | -------------------------------------------------------------------------------- |
|
|
126
|
+
| `agent-forge.yaml` | Agent and team wiring. |
|
|
127
|
+
| `install_mcp.py` | Installs the project MCP server into Codex for direct skill runs. |
|
|
128
128
|
| `mcp-server/` | Local stdio MCP implementation that exposes `deepresearch` and `writing_master`. |
|
|
129
|
-
| `skills/` | Prepared AcademicArmy skills.
|
|
130
|
-
| `metaskills/` | Matching metaskill design/evolution files.
|
|
131
|
-
| `runs/` | Convenience wrappers around TypeScript pipelines.
|
|
132
|
-
| `src/` | TypeScript pipeline structure and implementation notes.
|
|
133
|
-
| `output/` | Generated planning artifacts, codebase output, and archives.
|
|
129
|
+
| `skills/` | Prepared AcademicArmy skills. |
|
|
130
|
+
| `metaskills/` | Matching metaskill design/evolution files. |
|
|
131
|
+
| `runs/` | Convenience wrappers around TypeScript pipelines. |
|
|
132
|
+
| `src/` | TypeScript pipeline structure and implementation notes. |
|
|
133
|
+
| `output/` | Generated planning artifacts, codebase output, and archives. |
|
|
134
134
|
|
|
135
135
|
Agent and team wiring lives in [`agent-forge.yaml`](agent-forge.yaml). The local TypeScript agents are implemented under [`src/evolve-skill/agents`](src/evolve-skill/agents); developing agents come from `developing-agent-forge`.
|
|
136
136
|
|
|
@@ -140,7 +140,7 @@ Prepared AcademicArmy skills live under [`skills/`](skills/), and their matching
|
|
|
140
140
|
|
|
141
141
|
| File or variable | Required for | Notes |
|
|
142
142
|
| ------------------------- | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
143
|
-
| `.env` / `OPENAI_API_KEY` | AcademicArmy MCP
|
|
143
|
+
| `.env` / `OPENAI_API_KEY` | AcademicArmy MCP | Read by the MCP server and by `install_mcp.py`. |
|
|
144
144
|
| `agent-forge.yaml` | Project pipelines | Launches `academic_army_mcp_tools` as `python -m mcp-server` with `PYTHONPATH=.` and `cwd=.`. |
|
|
145
145
|
| `secret.yaml` | Prepared shell scripts | Local ignored config overlay used by the prepared wrappers. It may contain passwords, API keys, runtime credentials, or other private values that must not be committed or uploaded to GitHub. |
|
|
146
146
|
|
package/README.zh-CN.md
CHANGED
|
@@ -103,7 +103,7 @@ npm run evolve-skill
|
|
|
103
103
|
|
|
104
104
|
TypeScript pipeline 的目录结构和实现说明见 [`src/README.zh-CN.md`](src/README.zh-CN.md)。
|
|
105
105
|
|
|
106
|
-
对于 `developing` 和 `developing-skill`,每次想切换到新的任务重点时,更新传给 `--goal-path` 的文件即可。预设 wrappers 使用的是 `output/goal.md
|
|
106
|
+
对于 `developing` 和 `developing-skill`,每次想切换到新的任务重点时,更新传给 `--goal-path` 的文件即可。预设 wrappers 使用的是 `output/goal.md`。基础开发循环来自 `developing-agent-forge`;本仓库在本地提供 `developing-skill` trajectory optimizer。
|
|
107
107
|
|
|
108
108
|
### 调用 MCP 工具
|
|
109
109
|
|
|
@@ -121,16 +121,16 @@ Find the closest papers to this research idea, compare their methods, and return
|
|
|
121
121
|
|
|
122
122
|
## 项目结构
|
|
123
123
|
|
|
124
|
-
| 路径 | 用途
|
|
125
|
-
| ------------------ |
|
|
126
|
-
| `agent-forge.yaml` | Agent 和团队 wiring。
|
|
127
|
-
| `install_mcp.py` | 把项目 MCP server 安装到 Codex,供直接运行 skill 时使用。
|
|
124
|
+
| 路径 | 用途 |
|
|
125
|
+
| ------------------ | -------------------------------------------------------------- |
|
|
126
|
+
| `agent-forge.yaml` | Agent 和团队 wiring。 |
|
|
127
|
+
| `install_mcp.py` | 把项目 MCP server 安装到 Codex,供直接运行 skill 时使用。 |
|
|
128
128
|
| `mcp-server/` | 本地 stdio MCP 实现,暴露 `deepresearch` 和 `writing_master`。 |
|
|
129
|
-
| `skills/` | 已准备的 AcademicArmy skills。
|
|
130
|
-
| `metaskills/` | 对应的 metaskill 设计与 evolution 文件。
|
|
131
|
-
| `runs/` | TypeScript pipelines 的便捷 wrappers。
|
|
132
|
-
| `src/` | TypeScript pipeline 的目录结构和实现说明。
|
|
133
|
-
| `output/` | 生成的规划产物、代码库输出和归档。
|
|
129
|
+
| `skills/` | 已准备的 AcademicArmy skills。 |
|
|
130
|
+
| `metaskills/` | 对应的 metaskill 设计与 evolution 文件。 |
|
|
131
|
+
| `runs/` | TypeScript pipelines 的便捷 wrappers。 |
|
|
132
|
+
| `src/` | TypeScript pipeline 的目录结构和实现说明。 |
|
|
133
|
+
| `output/` | 生成的规划产物、代码库输出和归档。 |
|
|
134
134
|
|
|
135
135
|
Agent 和团队 wiring 位于 [`agent-forge.yaml`](agent-forge.yaml)。本仓库内的 TypeScript agents 实现于 [`src/evolve-skill/agents`](src/evolve-skill/agents);developing agents 来自 `developing-agent-forge`。
|
|
136
136
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "academic-army",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.8",
|
|
4
4
|
"description": "Agent workflows and skills for AcademicArmy.",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"repository": {
|
|
@@ -48,7 +48,7 @@
|
|
|
48
48
|
},
|
|
49
49
|
"dependencies": {
|
|
50
50
|
"coding-agent-forge": ">=1.3.5",
|
|
51
|
-
"developing-agent-forge": ">=2.
|
|
51
|
+
"developing-agent-forge": ">=2.7.3"
|
|
52
52
|
},
|
|
53
53
|
"devDependencies": {
|
|
54
54
|
"@eslint/js": "^10.0.1",
|
|
@@ -27,6 +27,11 @@ For normal prose, use one `latex` block per manuscript sentence.
|
|
|
27
27
|
|
|
28
28
|
After each block, explain why the sentence is here, how it connects to nearby context, what it prepares next, and any useful cross-section connection by content.
|
|
29
29
|
|
|
30
|
+
## Preserve Reasoning
|
|
31
|
+
When modifying explanations, notes, or other local records of thinking in `.lit.md`, do not lose information. Respect the existing content and preserve already-understood reasoning.
|
|
32
|
+
|
|
33
|
+
Prefer adding new logical points and updating outdated parts of existing points. Do not directly delete prior reasoning unless it is truly wrong or obsolete; when removing or replacing it, carry forward any still-useful information into the updated text.
|
|
34
|
+
|
|
30
35
|
## Workflow
|
|
31
36
|
Draft, revise, move, and delete text in `.lit.md`.
|
|
32
37
|
|