Borrowing it
Nothing to install: this file belongs to extra-org/extra. 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/extra-org/extra/main/.claude/skills/skill-authoring/SKILL.mdgit clone --depth 1 https://github.com/extra-org/extraWrote 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/extra-org/extra/skill-authoring)<a href="https://agentmods.dev/skills/extra-org/extra/skill-authoring"><img src="https://agentmods.dev/badge/skills/extra-org/extra/skill-authoring/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/extra-org/extra/skill-authoring"><img src="https://agentmods.dev/badge/skills/extra-org/extra/skill-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.01064 |
| Opus 5.5 | $0.00017 | $0.00426 |
| Sonnet 5.5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
skill-authoring 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 2mo 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.
Skill: Skill Authoring
Purpose
Define how to create new skill files so the .ai/skills/ system stays
consistent, operational, and trustworthy. A skill is a short, repeatable
playbook — not an essay.
When to Use This Skill
- Creating a new skill file in
.ai/skills/. - Substantially restructuring an existing skill.
- Reviewing a proposed skill for quality and consistency.
Files to Read First
AGENTS.md(skills system + architecture rules a skill must not contradict)..ai/README.md(the index a new skill must be added to).- An existing high-quality skill as a model (e.g.
.ai/skills/code-review.md). - Any
docs//ADR the new skill will reference.
Core Principles
- Operational, not academic. A skill tells an agent what to do, step by step. No long prose.
- Task-oriented and repeatable. Focus on behavior an agent will repeat.
- Consistent structure. Every skill uses the standard section set (below).
- Must include when to use it, files to read first, rules, process, checklist, and common mistakes.
- Never contradicts
AGENTS.md, the docs, or ADRs. If it would, you need an ADR/doc change first, not a skill that diverges. - References, not duplicates. Link to the authoritative doc/ADR rather than
copying its content (which will drift). This is also why skills live only in
.ai/— never copy them into tool-specific folders. - Short enough to be used. If it's too long to read before a task, trim it.
- Includes validation commands (e.g.
make check).
Process
- Confirm the gap. Ensure no existing skill already covers the area; prefer improving one over adding a near-duplicate.
- Copy the template below into
.ai/skills/<name>.md. - Fill every section with concrete, project-specific instructions (mention real layers, files, and commands — not generic advice).
- Cross-check against
AGENTS.md/ADRs for contradictions. - Add it to
.ai/README.mdindex and, if it maps to a task type, to theAGENTS.mdskills mapping. - Validate formatting with
make check(Markdown only → still run it).
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.
- 2mo ago First seen · 127 lines · 42 tokens per session scan A 1d9b86da68d3
skill-authoring is a skill published in the GitHub repository extra-org/extra (117 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,064 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
skill-writing-plans
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.
argent-tv-interact
Control and inspect TV apps via argent, Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.
Swift Performance Optimization Skill
Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…
06-product-brief
Produces a concise Product Brief before requirements. Use when the user wants to frame or revisit a product opportunity and how it will be validated. Not for requirements, technical design, or planning.
issue-resolve
Use when an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG) has localized, verifiable scope and should be driven to a fix. Mutating and gated: it works in an isolated worktree, fixes test-first, and opens a DRAFT PR for human review. Built to run autonomously (hermes-ops) within a strict action envelope…