You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
feat: add TanStack Intent library and blog post header image
- Add Intent as a new library in the sidebar with landing page
- Add header image to the "From Docs to Agents" blog post
- Fix relative SVG image paths in blog post to use absolute paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: src/blog/from-docs-to-agents.md
+5-3Lines changed: 5 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,6 +6,8 @@ authors:
6
6
- Kyle Matthews
7
7
---
8
8
9
+

10
+
9
11
Your docs are good. Your types are solid. Your agent still gets it wrong.
10
12
11
13
Not because it's dumb — because there's no pipeline between what you know about your tool and what agents know about your tool. Docs are written for humans who browse. Types check individual API calls but can't encode intent. Training data is a snapshot of the ecosystem as it *was*, mixing versions without flagging which one applies. The knowledge gap between your tool and agents using your tool isn't a content problem. It's a lifecycle problem.
@@ -74,7 +76,7 @@ npx intent setup
74
76
75
77
This matters because the alternative is hoping model providers eventually re-train on your latest docs. That's not a strategy. Training data has a permanent version-mixing problem: once a breaking change ships, models contain *both* versions forever with no mechanism to disambiguate. Skills bypass this entirely. They're versioned with your package, and `npm update` brings the latest knowledge with the latest code.
76
78
77
-

79
+

78
80
79
81
## The dependency graph does the discovery
80
82
@@ -84,7 +86,7 @@ When a developer runs `intent init`, the CLI discovers every intent-enabled pack
84
86
npx intent init
85
87
```
86
88
87
-

89
+

88
90
89
91
No manual setup per-library. No hunting for rules files. Install the package, run `intent init`, and the agent understands the tool. Update the package, and the skills update with it. Knowledge travels through the same channel as code.
90
92
@@ -122,7 +124,7 @@ npx intent stale --json # Machine-readable for CI
122
124
123
125
Run it in CI and you get a failing check when source material has changed. The skill becomes part of your release checklist — not something you remember to update, something your pipeline catches.
124
126
125
-

127
+

126
128
127
129
The feedback loop runs both directions. `intent feedback` lets users submit structured reports when a skill produces incorrect output — which skill was active, which version, what went wrong. That context flows back to you as a maintainer, and the fix ships to everyone on the next `npm update`.
'Ship compositional knowledge for AI coding agents alongside your npm packages',
594
+
description:
595
+
'A toolkit for generating, discovering, and maintaining skills — knowledge encoded for AI coding agents — shipped as npm packages that travel with your code.',
0 commit comments