reading
Use when the user's primary intent is to have an article, paper, transcript, or note read and discussed: a supplied URL or wikilink is the main payload, or…
Skill by mhxie
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mhxie-reading
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, research, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/reading
What's inside
- Skill name
reading- Description
- Use when the user's primary intent is to have an article, paper, transcript, or note read and discussed: a supplied URL or wikilink is the main payload, or the user explicitly asks to read or discuss attached content. Incidental links in capture, inbox triage, save-for-later, or cited questions do not trigger this skill. Forwards into the canonical Atelier `/hi` router.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Reading (Atelier entry hint) Forward the user's input verbatim into `/hi <user-text>`. The router in `skills/hi/SKILL.md` selects the row and follows its procedure; reading dispatch is defined there, not here. Trigger only when the URL, wikilink, or "read this" phrase is the request itself. URLs appear inside many other intents; these stay with the router: - Capture with a link (`5/4 看了 https://... 觉得有意思`): the URL is content. - Curate or inbox triage (`triage my inbox`, `curate readwise`), even with URLs. - Save for later (`save this <url>`): Scribe records the URL verbatim. - A question that cites a link: the question is the request. - A meal record with a restaurant link: dine. - Wikilinks inside structured notes (`see also [[Foo]]`). Do not bypass `/hi` or call Reader directly; a reading-shaped phrase that is really about "this week" or feeling "burnt out" belongs to weekly or energy-audit, and only the router sees the whole catalog. The entry-hint contract lives in `protocols/runtime-adapters.md` → Runtime Surfaces. When the reading concept changes in `harness/intents.toml`, update this description to match; lint checks structure, not trigger phrasing.
From mhxie/Atelier, MIT.
More from mhxie/Atelier
- 0.614score
autoevo-review
mhxie
Run the Atelier `/autoevo-review` workflow in Codex using the canonical public skill.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
digest
mhxie
Run the Atelier `/digest` workflow in Codex using the canonical public skill.
SkillAFreshness: A★ 5Claude Code +9 - 0.612score
atelier
mhxie
Run or modify Atelier skills, routines, agents, tools, intent routing, and harness portability in this repo.
SkillAFreshness: A★ 5Claude Code +9 - 0.574score
lint
mhxie
Run the Atelier `/lint` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
push
mhxie
Run the Atelier `/push` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
decision
mhxie
Run the Atelier `/decision` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
dine
mhxie
Run the Atelier `/dine` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
hi
mhxie
Run the Atelier `/hi` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
prm
mhxie
Run the Atelier `/prm` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
read
mhxie
Run the Atelier `/read` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
reflect
mhxie
Run the Atelier `/reflect` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
review
mhxie
Run the Atelier `/review` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mhxie/Atelier
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mhxie
- 0.614score
autoevo-review
mhxie
Run the Atelier `/autoevo-review` workflow in Codex using the canonical public skill.
SkillAFreshness: A★ 5Claude Code +9 - 0.614score
digest
mhxie
Run the Atelier `/digest` workflow in Codex using the canonical public skill.
SkillAFreshness: A★ 5Claude Code +9 - 0.612score
atelier
mhxie
Run or modify Atelier skills, routines, agents, tools, intent routing, and harness portability in this repo.
SkillAFreshness: A★ 5Claude Code +9 - 0.574score
push
mhxie
Run the Atelier `/push` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
lint
mhxie
Run the Atelier `/lint` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9 - 0.574score
introspect
mhxie
Run the Atelier `/introspect` workflow in Codex using the canonical public skill.
SkillBFreshness: B★ 5Claude Code +9
Cite this page
reading skill. Agent Mart. https://agentmart.dev/skills/mhxie-reading (last updated 2026-10-24)