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 skyciv/skyciv-ai-skills --skill skill-writergit clone --depth 1 https://github.com/skyciv/skyciv-ai-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/skyciv/skyciv-ai-skills/skill-writer)<a href="https://agentmods.dev/skills/skyciv/skyciv-ai-skills/skill-writer"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/skill-writer/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/skyciv/skyciv-ai-skills/skill-writer"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/skill-writer.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 | $0.00169 | $0.03463 |
| Opus 5.5 | $0.00068 | $0.01385 |
| Sonnet 5.5 | $0.00034 | $0.00693 |
| Haiku 4.5 | $0.00017 | $0.00346 |
Grade A, and why
skill-writer 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Writer
Meta-skill for authoring and auditing agent skills — SKILL.md files (+ optional scripts/, references/, assets/) per the Agent Skills spec. Encodes the spec's normative rules, the best-practice patterns from agentskills.io, and (when working inside this repo) the SkyCiv-skill-library house style from the root CLAUDE.md.
Full detail lives in references/ — this file is the workflow and the rules you must never skip. Load a reference file only when you reach the step that needs it.
Mode A — writing a new skill from scratch
- Get real expertise, not vibes. A skill generated purely from an LLM's general knowledge produces generic filler ("handle errors appropriately"). Ask the user for: a transcript of a real task they did with an agent (steps that worked, corrections they made), or existing project artifacts (runbooks, API specs, code review comments, past incident fixes). See
references/best-practices.md#start-from-real-expertise. - Scope it as one coherent unit — like a function. Not so narrow that a task needs five skills loaded at once; not so broad it can't trigger precisely. See
references/best-practices.md#design-coherent-units. - Pick
name— must equal the parent directory name and pass the naming rules in Frontmatter rules below. - Draft
descriptionusing the checklist in Writing the description — this is the single field that decides whether the skill ever gets used. - Decide the layout: single
SKILL.mdif the whole thing is under ~500 lines / ~5000 tokens; otherwise split detail intoreferences/*.md, put runnable helpers inscripts/, and templates/schemas/lookup data inassets/. Seereferences/frontmatter-reference.md#optional-directories. - Write the body calibrating prescriptiveness to fragility (freeform guidance where approaches vary, exact command sequences where they don't), favoring procedures over one-off answers, and including a gotchas section for anything that defies a reasonable guess. See
references/best-practices.md. - If this skill lives in this repo (
<skill>/SKILL.mdat repo root, part of the SkyCiv pipeline), also applyreferences/repo-conventions.md— README table update, prerequisite statement, tables for params, worked example, cross-links, explicit units. - Validate and self-check — run
python scripts/validate_skill.py <path-to-skill>and work through the Audit checklist before calling it done.
What ships with it
7 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 · 178 lines · 169 tokens per session scan A 51091722284f
skill-writer is a skill published in the GitHub repository skyciv/skyciv-ai-skills (11 stars, last pushed 15d ago), licensed MIT. It adds 169 tokens to every session and 3,463 once invoked, about $0.0007 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 2026-09-22.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…