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 maxdeng007/Jimeng-Geek-Skill --skill jimeng-geek-skillgit clone --depth 1 https://github.com/maxdeng007/Jimeng-Geek-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/maxdeng007/jimeng-geek-skill/jimeng-geek-skill)<a href="https://agentmods.dev/skills/maxdeng007/jimeng-geek-skill/jimeng-geek-skill"><img src="https://agentmods.dev/badge/skills/maxdeng007/jimeng-geek-skill/jimeng-geek-skill/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/maxdeng007/jimeng-geek-skill/jimeng-geek-skill"><img src="https://agentmods.dev/badge/skills/maxdeng007/jimeng-geek-skill/jimeng-geek-skill.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 | $0.00049 | $0.02012 |
| Opus 5.5 | $0.00020 | $0.00805 |
| Sonnet 5.5 | $0.00010 | $0.00402 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
jimeng-geek-skill scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jimeng Geek Skill: Free CLI Image/Video Generation
Your browser session IS your API key.
Use 即梦AI (jimeng.jianying.com / dreamina.capcut.com) image and video generation from CLI — for free — with a standard membership account. No paid API. No 高级会员. Works with any AI agent (Hermes, Claude, Codex, etc.).
The Method
即梦 provides a generous free tier through its web UI, but charges for official API access. The trick is simple: extract your browser session cookie, then call the same HTTP endpoints the browser uses. The server can't tell the difference.
1. You have a 即梦 account (even 标准会员 works)
2. Login in browser normally
3. Extract sessionid cookie
4. Call the web API directly from CLI
5. Free image/video generation, no API key needed
This pattern works because the web frontend and the "official API" hit the same backend. The only difference is how you authenticate.
Prerequisites
- A 即梦/Dreamina account (free or 标准会员)
- Node.js 18+ (for jimeng-cli)
- Chrome browser (for cookie extraction)
- Python 3 (for auto cookie extraction script, optional)
Step 1: Install jimeng-cli
npm install -g jimeng-cli
jimeng-cli is a third-party CLI that wraps the jimeng web API. It handles request construction, response parsing, and file downloading.
GitHub: https://github.com/Algovate/jimeng-cli
Step 2: Get Your Session Cookie
You have 3 options, from most automated to manual:
Option A: Auto-extract from Chrome (Recommended)
Use the provided script to extract the cookie from a running Chrome instance:
# Start Chrome with remote debugging enabled (if not already running)
# macOS:
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9333 &
# Linux:
google-chrome --remote-debugging-port=9333 &
# Then run the extraction script:
python3 scripts/extract_session.py
The script connects to Chrome via CDP, finds the sessionid cookie for jimeng.jianying.com, and outputs it. Works for any logged-in session.
What ships with it
2 files 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 · 269 lines · 49 tokens per session scan A a826226e383c
jimeng-geek-skill is a skill published in the GitHub repository maxdeng007/Jimeng-Geek-Skill (2 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 2,012 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
stable-diffusion-image-generation
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
pysam
Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.