Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ailiheizi/workflow-to-skill --skill social-media-operatorgit clone --depth 1 https://github.com/ailiheizi/workflow-to-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ailiheizi/workflow-to-skill/social-media-operator)<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/social-media-operator"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/social-media-operator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/social-media-operator"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/social-media-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.03975 |
| Opus 5.5 | $0.00036 | $0.01590 |
| Sonnet 5.5 | $0.00018 | $0.00795 |
| Haiku 4.5 | $0.00009 | $0.00398 |
Grade A, and why
xiaohongshu-zhihu-content-operator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohongshu And Zhihu Content Operator
Turn a content goal into researched, platform-specific material and, when authorized, a verified platform result. The Skill owns the method and decision boundaries. Existing CLI, browser, MCP, or API bindings perform every real search, upload, account, and publishing operation.
Establish The Request
Identify:
- the campaign goal, audience, topic, and factual source material;
- whether the request covers Xiaohongshu, Zhihu, or both;
- the requested outcome: research, draft, local validation, dry-run, scheduled publication, live publication, or result inspection;
- the authorized account for each platform;
- required media, links, topics, disclosures, timing, and success criteria;
- whether execution requires review or has an explicit unattended scope.
Default to Xiaohongshu research followed by a draft and local dry-run. Do not infer a publishing account, fabricate uploaded-resource identifiers, or turn a draft request into live publication. Account choice, final public content, media, declarations, schedule, and live publication are material decisions.
Harmless formatting, equivalent read-only queries, and low-risk wording adjustments may be decided by the Agent. Ask for review when an unknown changes the audience, claim, account, platform, public side effect, cost, authority, or meaning of success.
Required Capabilities And Bindings
Confirm bindings before doing work. This reference was exercised with:
redbook0.8.1 for existing-browser-login checks and Xiaohongshusearchandreadoperations;- the official Zhihu Data Open Platform docs, which provide Zhihu Search through a Skill, API, or MCP binding;
yxer3.2.12 plus its matching officialschemas/directory for payload templates, platform fields, local validation, and publishing dry-runs;- an ordinary Agent Harness for reasoning, review, tool invocation, and final result delivery.
Treat those names as bindings for this Harness, not a universal protocol. An equivalent browser, MCP server, API, or CLI may be used only after its real commands, permissions, result shape, and cancellation behavior are inspected.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 334 lines · 89 tokens per session scan A 553005b9a9b5
xiaohongshu-zhihu-content-operator is a skill published in the GitHub repository ailiheizi/workflow-to-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 3,975 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-16.
Other skills, from other repositories
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
aiwg-language-map
AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
steward
Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.