agent-skillboard 0.2.16 → 0.2.17

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 (3) hide show
  1. package/CHANGELOG.md +14 -0
  2. package/README.md +38 -9
  3. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -2,6 +2,20 @@
2
2
 
3
3
  ## Unreleased
4
4
 
5
+ ## 0.2.17 — 2026-07-07
6
+
7
+ ### Changed
8
+
9
+ - Reworked the README opening and quick start so developers using multiple
10
+ agents, skill packs, plugins, MCP tools, or marketplaces can understand
11
+ SkillBoard's purpose and try the CLI with read-only `npm exec` commands before
12
+ installing it globally.
13
+
14
+ ### Fixed
15
+
16
+ - Kept packaged npm smoke tests compatible with Node 20 release checks that run
17
+ inside an outer `npx -p node@20 -c ...` invocation.
18
+
5
19
  ## 0.2.16 — 2026-07-06
6
20
 
7
21
  ### Changed
package/README.md CHANGED
@@ -2,6 +2,12 @@
2
2
 
3
3
  Keep AI-agent skills broadly available, then route overlaps consistently.
4
4
 
5
+ If you use more than one coding agent, skill pack, plugin, MCP tool, or
6
+ marketplace, SkillBoard answers the practical questions before you install
7
+ anything or change workflow policy: which skills are usable now, which one
8
+ should win when skills overlap, which external skills need review, and how
9
+ Codex, Claude, OpenCode, and Hermes can follow the same policy.
10
+
5
11
  Ask your AI normal work requests: "write tests before implementation",
6
12
  "review this plan and point out weak assumptions", "help me refine this UX
7
13
  flow", or explicit control requests like "use the Codex test-first skill in
@@ -12,7 +18,8 @@ when similar skills overlap, and a short disclosure of what was used.
12
18
 
13
19
  The burden stays low:
14
20
 
15
- - No global install is required; use `npx --yes --package agent-skillboard`.
21
+ - No global install is required for a trial; use
22
+ `npm exec --yes --package agent-skillboard@latest -- skillboard`.
16
23
  - Most use is read-only: `brief`, `route`, `doctor`, and `guard use` answer
17
24
  what can run now and which route fits the request.
18
25
  - Nothing changes until you approve a policy action.
@@ -59,12 +66,25 @@ Names you may see in setup and logs:
59
66
  - `agent-skillboard`: the npm package.
60
67
  - `skillboard`: the CLI binary.
61
68
 
62
- Use SkillBoard when your agent setup has grown beyond one trusted skill folder
63
- and you want workflow-scoped control without turning skill governance into a
64
- manual checklist. If you are changing routing, brief, bridge, policy, or
65
- workflow UX, read [AI Skill Routing Goal](docs/ai-skill-routing-goal.md) first;
66
- it defines the non-blocking `observe → route → work → explain briefly → ask
67
- after remember policy` loop that development should preserve.
69
+ ## Who This Is For
70
+
71
+ Use SkillBoard if you use more than one coding agent, skill pack, plugin, MCP
72
+ tool, or marketplace and want one answer to:
73
+
74
+ - Which skills can this agent use right now?
75
+ - Which skill should win when several match the same task?
76
+ - Which external or plugin skills are reviewed, blocked, or waiting for approval?
77
+ - How can Codex, Claude, OpenCode, and Hermes follow the same skill policy?
78
+
79
+ If you use one agent with a few hand-written local skills, you probably do not
80
+ need SkillBoard yet. SkillBoard is for setups that have grown beyond one trusted
81
+ skill folder and need workflow-scoped control without turning skill governance
82
+ into a manual checklist.
83
+
84
+ If you are changing routing, brief, bridge, policy, or workflow UX, read
85
+ [AI Skill Routing Goal](docs/ai-skill-routing-goal.md) first; it defines the
86
+ non-blocking `observe → route → work → explain briefly → ask after → remember
87
+ policy` loop that development should preserve.
68
88
 
69
89
  <p align="center">
70
90
  <img src="https://raw.githubusercontent.com/NyXXiR/skillboard/main/skillboard.png" alt="SkillBoard architecture diagram: sources, inventory scanner, SkillBoard model, policy engine, and user and agent surfaces." width="100%">
@@ -95,8 +115,17 @@ See [Tested Value Proof](#tested-value-proof) for the executable proof.
95
115
 
96
116
  ## 5-Minute Quick Start
97
117
 
98
- Install the CLI. On a normal global install, SkillBoard auto-connects the
99
- agent layer for detected Codex, Claude, OpenCode, and Hermes user skill roots:
118
+ Try it without a global install. These read-only commands download the latest
119
+ package for one run and do not create project files:
120
+
121
+ ```bash
122
+ npm exec --yes --package agent-skillboard@latest -- skillboard --version
123
+ npm exec --yes --package agent-skillboard@latest -- skillboard help brief
124
+ ```
125
+
126
+ Install the CLI when you want SkillBoard connected to your agent layer. On a
127
+ normal global install, SkillBoard auto-connects the agent layer for detected
128
+ Codex, Claude, OpenCode, and Hermes user skill roots:
100
129
 
101
130
  AI/automation/operator details:
102
131
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-skillboard",
3
- "version": "0.2.16",
3
+ "version": "0.2.17",
4
4
  "description": "Keep agent skills broadly available while routing overlaps consistently.",
5
5
  "keywords": [
6
6
  "ai-agent",