xiaohongshu-skill
AGENTS.md43 starsChanged 3 months agoApache-2.0View on GitHub
xiaohongshu-skill is a Xiaohongshu browser toolkit and Agent Skill. SKILL.md is the agent entry point; public product and technical documentation lives in README.md and docs/. Use the JSON CLI instead of importing action modules directly: Use --profile <name> for account isolation. Identifiers and xsec_token values should come from the current browser session. When changing selectors, use scripts/selectors.py as the source of truth and run tests/test_selectors.py. When changing JSON fields or statuses, update scripts/output_contracts.py and its tests. See docs/ARCHITECTURE.md for boundaries…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- chrisopal/skillsword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- chrisopal/skills★ 11100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- site/llms-full.txtllms.txt
- site/llms.txtllms.txt
- xiaohongshu-skillSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Read-only commands: search, feed, user, me, explore, check-login, profiles, selectors, contracts.
- Distinctive: line 9
Stop on captcha, login, or security-verification pages.
- Distinctive: line 10
Never expose local account state, authentication values, QR codes, or complete security parameters.
- Distinctive: line 15
Use the JSON CLI instead of importing action modules directly:
- Very specific: line 21
Use --profile <name> for account isolation.
- Very specific: line 32
When changing selectors, use scripts/selectors.py as the source of truth and run tests/test_selectors.py.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
xiaohongshu-skill is a Xiaohongshu browser toolkit and Agent Skill. SKILL.md is the agent entry point; public product and technical documentation lives in README.md and docs/.
Safety
- Read-only commands:
search,feed,user,me,explore,check-login,profiles,selectors,contracts. - Account-changing commands require explicit user confirmation before execution.
- Stop on captcha, login, or security-verification pages.
- Never expose local account state, authentication values, QR codes, or complete security parameters.
submitted_unconfirmedis not success and must not be retried automatically.
Execution
Use the JSON CLI instead of importing action modules directly:
uv run python -m scripts <command>Use --profile <name> for account isolation. Identifiers and xsec_token values should come from the current browser session.
Development
- Python 3.10 to 3.12.
- Dependencies:
pyproject.tomland committeduv.lock. - Default gate:
uv run python -m scripts.quality check. - Live tests are opt-in with
XHS_LIVE_TEST=1and should use a dedicated account. - New public behavior requires tests.
- Use Conventional Commits.
When changing selectors, use scripts/selectors.py as the source of truth and run tests/test_selectors.py. When changing JSON fields or statuses, update scripts/output_contracts.py and its tests.
Architecture
- CLI adapter:
scripts/__main__.py - Browser session and local state:
scripts/client.py,scripts/profiles.py,scripts/session_store.py - Actions: login, search, feed, user, publish, comment, interact, explore
- Contracts:
scripts/selectors.py,scripts/output_contracts.py - Workflows: templates, strategy, SOP
See docs/ARCHITECTURE.md for boundaries and compatibility policy.
Public repository boundary
Public files must contain only product behavior, public APIs, generic examples, and source attribution. Do not add private infrastructure, local workspace paths, internal operator notes, or credentials.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.