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 tranfu-labs/tranfu-skills --skill draft-contentgit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/draft-content)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/draft-content"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/draft-content/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/tranfu-labs/tranfu-skills/draft-content"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/draft-content.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 | $0.00127 | $0.03142 |
| Opus 5 | $0.00063 | $0.01571 |
| Sonnet 5 | $0.00025 | $0.00628 |
| Haiku 4.5 | $0.00013 | $0.00314 |
Grade A, and why
draft-content 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 10d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Content
Turn an approved topic and authorized materials into one approved outline, two platform-neutral masters, and ten complete platform drafts. End at READY_FOR_PROOFREAD; never publish or silently perform downstream proofreading.
Ownership And Invariants
- Write only inside
WORKDIR/03-内容创作/<run-id>/. Treat the containing directory of this file asSKILL_ROOTand the current working directory asWORKDIR. - Preserve upstream files byte-for-byte. Snapshot inputs into the run before using them.
- Require exactly one shared outline, two masters, and five platforms by two variants.
- Keep facts, safety, the approved outline, audience, shared policies, platform rules, runtime model, and exposed generation settings equal across A/B. The only additional file input for B is the bundled style snapshot.
- Never read
references/style-b.mdor the run's00-input/style-b.mdwhile producing A. The initialization script may copy its bytes without exposing its content to the drafting Agent. - Allow A/B to choose different hooks, authorized examples, argument order, and expansion because only the shared outline is fixed. Never add facts, broaden claims, remove limitations, or change the topic.
- Treat platform references as shared adaptation contracts, not as author style.
- Never search, fetch, fact-check, generate title pools, proofread, humanize, plan images, insert image placeholders, format HTML, or publish.
Rule priority is fixed:
facts and safety > approved outline > platform contract > audience > B style
Orchestrated Provider Route
Contract marker: content-production-provider: drafting-v1.
Before starting the independent workflow, inspect any supplied structured request. If it contains any provider marker (contract: content-production-provider/v2, capability: drafting, provider_contract: drafting-v1, or content-production-provider: drafting-v1), immediately follow references/orchestrated-provider.md and use scripts/provider-contract.mjs; validation still requires the complete matching tuple. The provider route is stateless: do not initialize a nested run, create an independent outline gate, ask the user questions, or write the independent 03-内容创作/ tree. An invalid or partial provider request must return its structured failure and must never fall through to the independent workflow.
What ships with it
26 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.
- agents/openai.yaml 436 B
- assets/icon.png 806 B
- assets/icon.svg 613 B
- LICENSE 1.0 KB
- NOTICE 722 B
- README.md 2.5 KB
- README.zh.md 2.2 KB
- references/ab-policy.md 5.3 KB
- references/editorial-policy.md 1.7 KB
- references/input-contract.md 3.3 KB
- references/orchestrated-provider.md 5.3 KB
- references/outline-contract.md 2.6 KB
- references/output-contract.md 3.8 KB
- references/platform-toutiao.md 2.0 KB
- references/platform-wechat.md 1.9 KB
- references/platform-weibo.md 1.7 KB
- references/platform-xiaohongshu.md 2.1 KB
- references/platform-zhihu.md 1.8 KB
- references/style-application-policy.md 1.7 KB
- references/style-b.md 4.3 KB
- scripts/_lib.mjs 16 KB runs code
- scripts/init-run.mjs 22 KB runs code
- scripts/inspect-run.mjs 3.2 KB runs code
- scripts/provider-contract.mjs 45 KB runs code
- scripts/set-outline-gate.mjs 8.5 KB runs code
- scripts/verify-run.mjs 11 KB runs code
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.
- 10d ago First seen · 204 lines · 127 tokens per session scan A 0bc6a4573f30
draft-content is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 3,142 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…