Skip to content

Commit 74beb89

Browse files
KyleAMathewsclaude
andcommitted
add overview docs page
Single overview page for tanstack.com/intent docs, covering the problem, skills concept, consumer/maintainer workflows, and CLI reference. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1 parent 1c1b5c0 commit 74beb89

2 files changed

Lines changed: 84 additions & 8 deletions

File tree

docs/config.json

Lines changed: 0 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -12,14 +12,6 @@
1212
{
1313
"label": "Overview",
1414
"to": "overview"
15-
},
16-
{
17-
"label": "Installation",
18-
"to": "installation"
19-
},
20-
{
21-
"label": "Quick Start",
22-
"to": "quick-start"
2315
}
2416
]
2517
}

docs/overview.md

Lines changed: 84 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,84 @@
1+
---
2+
title: Overview
3+
---
4+
5+
`@tanstack/intent` is a CLI for library maintainers to generate, validate, and ship [Agent Skills](https://agentskills.io) alongside their npm packages.
6+
7+
## The problem
8+
9+
Your docs are good. Your types are solid. Your agent still gets it wrong.
10+
11+
Docs target humans who browse. Types check individual API calls but can't encode intent. Training data snapshots the ecosystem as it _was_, mixing versions with no way to tell which applies. Once a breaking change ships, models develop a permanent split-brain — training data contains _both_ versions forever with no way to disambiguate.
12+
13+
The ecosystem already moves toward agent-readable knowledge — Cursor rules, CLAUDE.md files, skills directories. But delivery is stuck in copy-paste: hunt for a community-maintained rules file, paste it into your config, repeat for every tool. No versioning, no update path, no staleness signal.
14+
15+
## Skills: versioned knowledge in npm
16+
17+
A skill is a short, versioned document that tells agents how to use a specific capability of your library — correct patterns, common mistakes, and when to apply them. Skills ship inside your npm package and travel with the tool via `npm update` — not the model's training cutoff, not community-maintained rules files, not prompt snippets in READMEs. Versioned knowledge the maintainer owns, updated when the package updates.
18+
19+
Each skill declares its source docs. When those docs change, the CLI flags the skill for review. One source of truth, one derived artifact that stays in sync.
20+
21+
The [Agent Skills spec](https://agentskills.io) is an open standard already adopted by VS Code, GitHub Copilot, OpenAI Codex, Cursor, Claude Code, Goose, Amp, and others.
22+
23+
## For library consumers
24+
25+
Set up skill-to-task mappings in your project's agent config files (CLAUDE.md, .cursorrules, etc.):
26+
27+
```bash
28+
npx @tanstack/intent install
29+
```
30+
31+
No per-library setup. No hunting for rules files. Install the package, run `npx @tanstack/intent install`, and the agent understands the tool. Update the package, and skills update too.
32+
33+
List available skills from installed packages:
34+
35+
```bash
36+
npx @tanstack/intent list
37+
```
38+
39+
## For library maintainers
40+
41+
Generate skills for your library by telling your AI coding agent to run:
42+
43+
```bash
44+
npx @tanstack/intent scaffold
45+
```
46+
47+
This walks the agent through domain discovery, skill tree generation, and skill creation — one step at a time with your review at each stage.
48+
49+
Validate your skill files:
50+
51+
```bash
52+
npx @tanstack/intent validate
53+
```
54+
55+
Check for skills that have fallen behind their sources:
56+
57+
```bash
58+
npx @tanstack/intent stale
59+
```
60+
61+
Copy CI workflow templates into your repo so validation and staleness checks run on every push:
62+
63+
```bash
64+
npx @tanstack/intent setup-github-actions
65+
```
66+
67+
## Keeping skills current
68+
69+
The real risk with any derived artifact is staleness. `npx @tanstack/intent stale` flags skills whose source docs have changed, and CI templates catch drift before it ships.
70+
71+
The feedback loop runs both directions. `npx @tanstack/intent feedback` lets users submit structured reports when a skill produces wrong output — which skill, which version, what broke. That context flows back to the maintainer, and the fix ships to everyone on the next `npm update`. Every support interaction produces an artifact that prevents the same class of problem for all future users — not just the one who reported it.
72+
73+
## CLI Commands
74+
75+
| Command | Description |
76+
| --- | --- |
77+
| `npx @tanstack/intent install` | Set up skill-to-task mappings in agent config files |
78+
| `npx @tanstack/intent list [--json]` | Discover intent-enabled packages |
79+
| `npx @tanstack/intent meta` | List meta-skills for library maintainers |
80+
| `npx @tanstack/intent scaffold` | Print the guided skill generation prompt |
81+
| `npx @tanstack/intent validate [dir]` | Validate SKILL.md files |
82+
| `npx @tanstack/intent setup-github-actions` | Copy CI templates into your repo |
83+
| `npx @tanstack/intent stale [--json]` | Check skills for version drift |
84+
| `npx @tanstack/intent feedback` | Submit skill feedback |

0 commit comments

Comments
 (0)