@gonrocca/zero-pi 0.1.43 → 0.1.45
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 +7 -1
- package/assets/preview.png +0 -0
- package/package.json +4 -2
- package/skills/skill-loop/SKILL.md +0 -33
package/README.md
CHANGED
|
@@ -13,7 +13,13 @@
|
|
|
13
13
|
|
|
14
14
|
**The zero spec-driven development workflow, packaged for [pi](https://pi.dev).**
|
|
15
15
|
|
|
16
|
-
[](https://www.npmjs.com/package/@gonrocca/zero-pi) [](https://github.com/gonzalonicolasr/zero-pi) [](./LICENSE) [](https://nodejs.org)
|
|
16
|
+
[](https://www.npmjs.com/package/@gonrocca/zero-pi) [](https://github.com/gonzalonicolasr/zero-pi) [](https://discord.gg/aNFCZBZVT3) [](./LICENSE) [](https://nodejs.org)
|
|
17
|
+
|
|
18
|
+
### 💬 Join the community
|
|
19
|
+
|
|
20
|
+
Questions, ideas, or want to debate workflow design? Come hang out:
|
|
21
|
+
|
|
22
|
+
[](https://discord.gg/aNFCZBZVT3)
|
|
17
23
|
|
|
18
24
|
</div>
|
|
19
25
|
|
|
Binary file
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@gonrocca/zero-pi",
|
|
3
|
-
"version": "0.1.
|
|
4
|
-
"description": "zero-pi — an installable layer for pi (pi.dev): the zero spec-driven development workflow
|
|
3
|
+
"version": "0.1.45",
|
|
4
|
+
"description": "zero-pi — an installable layer for pi (pi.dev): the zero spec-driven development workflow (explore → plan → build → veredicto) with per-phase model autotune and token-efficient batched builds. Adds capability to pi without modifying pi.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"keywords": [
|
|
7
7
|
"pi",
|
|
@@ -22,6 +22,7 @@
|
|
|
22
22
|
"themes": [
|
|
23
23
|
"./themes"
|
|
24
24
|
],
|
|
25
|
+
"image": "https://raw.githubusercontent.com/gonzalonicolasr/zero-pi/main/assets/preview.png",
|
|
25
26
|
"extensions": [
|
|
26
27
|
"./extensions/zero-banner.ts",
|
|
27
28
|
"./extensions/zero-statusline.ts",
|
|
@@ -39,6 +40,7 @@
|
|
|
39
40
|
"prompts",
|
|
40
41
|
"skills",
|
|
41
42
|
"themes",
|
|
43
|
+
"assets/preview.png",
|
|
42
44
|
"extensions/zero-banner.ts",
|
|
43
45
|
"extensions/zero-statusline.ts",
|
|
44
46
|
"extensions/working-phrases.ts",
|
|
@@ -1,33 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: skill-loop
|
|
3
|
-
description: zero's skill auto-learning loop — distill, store, surface, and refine reusable skills
|
|
4
|
-
---
|
|
5
|
-
|
|
6
|
-
# zero — Skill Auto-Learning
|
|
7
|
-
|
|
8
|
-
zero gives the agent a closed learning loop so solutions are reused, not
|
|
9
|
-
re-derived.
|
|
10
|
-
|
|
11
|
-
## Distill
|
|
12
|
-
|
|
13
|
-
When a substantial task completes, **distill** a reusable skill from it: capture
|
|
14
|
-
the solution pattern, the ordered steps, and the non-obvious gotchas into a
|
|
15
|
-
single skill document. If the task did only routine or one-off work with no
|
|
16
|
-
reusable pattern, do not create a skill.
|
|
17
|
-
|
|
18
|
-
## Store
|
|
19
|
-
|
|
20
|
-
Store each learned skill in the per-user skill library so it persists across
|
|
21
|
-
sessions and is available to every agent zero has configured.
|
|
22
|
-
|
|
23
|
-
## Surface
|
|
24
|
-
|
|
25
|
-
When a new task begins, surface the stored skills relevant to it — match by the
|
|
26
|
-
skill's subject and description — so the agent consults a known solution before
|
|
27
|
-
re-deriving one. Surface nothing when no stored skill is relevant.
|
|
28
|
-
|
|
29
|
-
## Refine
|
|
30
|
-
|
|
31
|
-
When a run re-applies an existing skill, **refine** that skill rather than
|
|
32
|
-
create a duplicate: merge new gotchas and steps without repeating what is
|
|
33
|
-
already there, and prefer the newer learning when it contradicts the old.
|