pi-anchorloop 2.0.0 → 2.0.1
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/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-anchorloop",
|
|
3
|
-
"version": "2.0.
|
|
3
|
+
"version": "2.0.1",
|
|
4
4
|
"description": "Agent workflow skills for pi: one entry skill per task type, each with playbooks, over a shared Align → Anchor → Act → Verify loop, plus loop extensions (anchor gate, decision trail tool, Jev second thought, skill validator, stream rules).",
|
|
5
5
|
"author": "Wei Hung",
|
|
6
6
|
"license": "MIT",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: anchorloop
|
|
3
|
-
description: Use when a task
|
|
3
|
+
description: Use when a task fits no entry skill, and as the shared loop every entry skill runs; its playbooks cover unattended runs, pauses, and resuming a prior run.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# Anchor Loop
|
package/skills/writing/SKILL.md
CHANGED
|
@@ -7,7 +7,7 @@ description: Use when writing or revising documentation, a README, an article, a
|
|
|
7
7
|
|
|
8
8
|
Run the loop in [../anchorloop/SKILL.md](../anchorloop/SKILL.md). The anchor is a reader without the conversation's context: hand the text to a fresh subagent and check it can say what the text asks of its reader. Comment-only work also keeps the project's tests green.
|
|
9
9
|
|
|
10
|
-
Short declarative sentences; each claim carries its evidence or reads as an estimate.
|
|
10
|
+
Short declarative sentences; each claim carries its evidence or reads as an estimate.
|
|
11
11
|
|
|
12
12
|
## Playbooks
|
|
13
13
|
|