Skip to content

docs: document article mode in agent skill #862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ryanfowler merged 1 commit into from
Jul 13, 2026
Merged

docs: document article mode in agent skill #862

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 22 additions & 4 deletions skills/fetch/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,10 @@
name: fetch
description: >
Use the fetch CLI to call and debug HTTP APIs, inspect JSON responses,
test authentication, diagnose DNS and TLS, measure request timing, call
gRPC services, and interact with WebSockets. Prefer this skill when a task
requires making or troubleshooting a network request from the terminal.
test authentication, diagnose DNS and TLS, measure request timing, extract
readable articles, call gRPC services, and interact with WebSockets. Prefer
this skill when a task requires making or troubleshooting a network request
from the terminal.
license: MIT
compatibility: Requires the fetch executable and network access.
metadata:
Expand All @@ -14,7 +15,8 @@ metadata:

# fetch

Use `fetch` for terminal-native HTTP, API, DNS/TLS, gRPC, and WebSocket work.
Use `fetch` for terminal-native HTTP, API, article extraction, DNS/TLS, gRPC,
and WebSocket work.

## Agent-safe defaults

Expand Down Expand Up @@ -55,6 +57,9 @@ fetch --dry-run -vv -j @request.json https://api.example.com/items
# Save a large or binary response
fetch --pager off -o response.bin https://example.com/download

# Extract a readable article as raw Markdown
fetch --article --pager off --color off --format off https://example.com/post >post.md

# Diagnose the connection
fetch --inspect-dns example.com
fetch --inspect-tls https://example.com
Expand All @@ -73,6 +78,19 @@ Read [HTTP recipes](references/http.md), [diagnostics](references/diagnostics.md
[gRPC](references/grpc.md), or [WebSockets](references/websocket.md) only when the
task needs that detail.

## Article extraction

Use `--article` for a readable HTML or Markdown article. HTML is reduced to its
main content, converted to Markdown, and prefixed with available metadata and
the final response URL. Existing Markdown is preserved and receives only the
final URL as frontmatter. Relative HTML links are resolved against the final URL
after redirects.

Article extraction buffers the decoded response and has a 16 MiB limit. Use
`--format off` when piping or redirecting raw Markdown; `-o FILE` also writes raw,
uncolored Markdown. This mode does not render JavaScript, so use a browser for
client-rendered pages.

## Security

- Never invent or print credentials. Prefer existing environment variables,
Expand Down
Loading