Borrowing it
Nothing to install: this file belongs to techtankto/techtank-site. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/techtankto/techtank-site/main/.agents/skills/writing/SKILL.mdgit clone --depth 1 https://github.com/techtankto/techtank-siteWrote 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/techtankto/techtank-site/writing)<a href="https://agentmods.dev/skills/techtankto/techtank-site/writing"><img src="https://agentmods.dev/badge/skills/techtankto/techtank-site/writing.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00713 |
| Opus 5 | $0.00032 | $0.00357 |
| Sonnet 5 | $0.00013 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
writing 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 6d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing
How project prose reads: docs, the plan, PR and commit bodies. This skill owns the sentences, not where facts live. Product or site copy is out of scope, since its voice is the design's.
Voice
- Declarative, present tense. State what is and what wins, not what should ideally happen. No hedging, no marketing filler.
- Every sentence is load-bearing. A sentence earns its place by adding a fact, a rule, or a reason; otherwise cut it. Conciseness comes from selecting what to say, not compressing how it's said: full sentences stay, whole points go.
- Rationale rides along. A rule carries its why in the same sentence, attached with a colon, semicolon, or parenthetical; never a separate paragraph of justification.
- One line of personality. A doc's opening line may carry an aphorism; everything after it is working prose.
Structure
- Open with ownership. A doc's first lines state what it owns and hand neighboring topics to their owners ("what the metadata contains is seo's concern"), then get to work. No table of contents, no preview of what the doc is about to say.
- Bold-lead rules. Rule lists are numbered; each item opens with a bold lead naming the rule, then the detail.
- Tables carry enumerable facts (tokens, stages, routes). Reasoning stays in the surrounding prose, never in cells.
- Headings name what the section owns, in sentence case, with a colon gloss only when the bare name is opaque ("Milestones: the human gates").
Economy
- Summarize and point, never restate. A neighboring doc's fact appears only as a pointer or a one-line summary; this is the prose form of the one-owning-doc rule.
- Standards name the surrounding docs by role, not by link. "The design contract's concern," not a hardcoded path; standards stay standalone and portable. Standards may link standards; project docs link each other freely.
- Link once. A doc or term links at first mention; after that, plain text.
Section references use
§Section, in-doc and across docs alike.
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.
- 6d ago First seen · 60 lines · 63 tokens per session scan A 8da110b1ade4
writing is a skill published in the GitHub repository techtankto/techtank-site (5 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 713 once invoked, about $0.0003 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…