capyai 0.5.1 → 0.5.2

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.
Files changed (2) hide show
  1. package/AGENTS.md +24 -11
  2. package/package.json +1 -1
package/AGENTS.md CHANGED
@@ -50,15 +50,34 @@ Verify: `capy status --json` should return `{ "threads": [...], "tasks": [...] }
50
50
 
51
51
  If it returns `{ "error": ... }`, the API key or project ID is wrong. Ask the user.
52
52
 
53
- ## Step 4: Install skill
53
+ ## Step 4: Load the operating manual
54
54
 
55
+ The file `skills/capy/SKILL.md` in this repo is the full operating manual. It has everything: object model, decision trees, workflows, guardrails, command reference. You need it in your context to use Capy well.
56
+
57
+ Pick whichever method works for your setup:
58
+
59
+ **Option A: skills.sh (if supported)**
55
60
  ```bash
56
61
  npx skills add yazcaleb/capy-cli
57
62
  ```
58
63
 
59
- This adds the `capy` skill to your skills directory so you have the full command reference available in context.
64
+ **Option B: Copy to your skills/memory folder**
65
+ If you have a persistent skills directory or memory system, copy the file directly:
66
+ ```bash
67
+ # Example paths — adjust to your agent's conventions
68
+ cp skills/capy/SKILL.md ~/.claude/skills/capy/SKILL.md
69
+ cp skills/capy/SKILL.md .cursor/skills/capy.md
70
+ cp skills/capy/SKILL.md /path/to/your/agent/memory/capy-skill.md
71
+ ```
72
+
73
+ **Option C: Just read it**
74
+ If none of the above work, read `skills/capy/SKILL.md` from this repo at the start of every session. It's ~275 lines. That's your entire operating manual.
75
+
76
+ ## Step 5: MCP server or CLI
60
77
 
61
- ## Step 5: MCP server (if you support MCP)
78
+ Choose MCP if your agent supports it (structured tool calls, no shell parsing). Choose CLI if you run shell commands. Both have full API parity.
79
+
80
+ **If you prefer MCP** (Cursor, Claude Desktop, agents with MCP support):
62
81
 
63
82
  Add this to your MCP configuration:
64
83
 
@@ -113,7 +132,7 @@ Config file locations:
113
132
 
114
133
  Tools with predictable outputs (`capy_captain`, `capy_build`, `capy_review`, `capy_approve`, `capy_retry`) declare `outputSchema` for typed structured content per the 2025-03-26 MCP spec.
115
134
 
116
- If you don't support MCP, skip this step. The CLI works everywhere.
135
+ **If you prefer CLI** (any agent that runs shell commands): skip this step. The CLI is already installed from Step 2. Every command supports `--json` for structured output.
117
136
 
118
137
  ## Step 6: Verify everything
119
138
 
@@ -129,10 +148,4 @@ You are now fully configured.
129
148
 
130
149
  ## Usage
131
150
 
132
- For the full operating manual (commands, workflows, decision trees, guardrails), install the capy skill:
133
-
134
- ```bash
135
- npx skills add yazcaleb/capy-cli
136
- ```
137
-
138
- This loads `skills/capy/SKILL.md` into your context with everything you need to orchestrate Capy agents.
151
+ Read `skills/capy/SKILL.md`. That's it. Everything you need to orchestrate Capy agents is in that file.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "capyai",
3
- "version": "0.5.1",
3
+ "version": "0.5.2",
4
4
  "type": "module",
5
5
  "description": "Unofficial Capy.ai CLI for agent orchestration with quality gates",
6
6
  "bin": {