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 anneheartrecord/charles-skill --skill xhs-keyword-strategygit clone --depth 1 https://github.com/anneheartrecord/charles-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/anneheartrecord/charles-skill/xhs-keyword-strategy)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/xhs-keyword-strategy"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/xhs-keyword-strategy/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/anneheartrecord/charles-skill/xhs-keyword-strategy"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/xhs-keyword-strategy.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 | $0.00080 | $0.00865 |
| Opus 5 | $0.00040 | $0.00432 |
| Sonnet 5 | $0.00016 | $0.00173 |
| Haiku 4.5 | $0.00008 | $0.00086 |
Grade A, and why
xhs-keyword-strategy 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 11d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohongshu Keyword Strategy
Create a keyword plan that helps the platform and a new reader understand what the post is about.
Use Chinese by default.
Inputs
Work with any of these inputs:
- A topic or rough idea
- A finished or unfinished draft
- A product or service description
- An account direction
- A video transcript
Use the user's stated goal when available: search discovery, audience growth, or conversion. If the goal or account type is missing, make a reasonable assumption and state it briefly.
Workflow
1. Identify search intent
Summarize:
- Who the post is for
- What question or decision it helps with
- What phrase that person might type into search
Prefer ordinary reader language over internal terminology.
2. Select one primary keyword
Choose one phrase that best matches the post's actual promise.
Check that it is:
- Specific enough to express the topic
- Broad enough to sound natural
- Supported by the content
- Appropriate for the account's current positioning
Do not select a keyword only because it sounds popular.
3. Select supporting terms
Choose a small set of related phrases that add useful context, such as:
- Audience or experience level
- Problem or desired outcome
- Use case or situation
- Product or service category
- Location, when the service is genuinely local
Avoid unrelated trending terms, misleading brand names, and repetitive synonyms.
4. Align the post
Place the primary keyword naturally in the most useful locations:
- Title
- Cover copy
- Opening paragraph
- Relevant examples, subheads, or list items
- Topic tags
Keep the title and body readable. Never turn them into a list of search terms.
5. Review the promise
Confirm that:
- The title and cover describe the same topic
- The opening quickly tells the reader what the post will help with
- The body delivers what the keyword implies
- The terms fit the account and intended audience
Default Output
Return:
定位判断: audience, intent, and assumed goal主关键词: one phrase and the reason for choosing it辅助关键词: a short list with the role of each phrase标题方案: several natural title options封面文案: a few concise options正文调整: a revised opening plus suggested placement points话题标签: a focused set of relevant tags判断依据: a short explanation of why the plan is coherent
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.
- 11d ago First seen · 127 lines · 80 tokens per session scan A ce58435b231c
xhs-keyword-strategy is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 865 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.
linker
Discovers missing cross-domain connections between knowledge documents and creates/updates connection wiki articles.