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 pproenca/dot-skills --skill skill-authoringgit clone --depth 1 https://github.com/pproenca/dot-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/pproenca/dot-skills/skill-authoring)<a href="https://agentmods.dev/skills/pproenca/dot-skills/skill-authoring"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/skill-authoring.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 3 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00091 | $0.01674 |
| Opus 5 | $0.00046 | $0.00837 |
| Sonnet 5 | $0.00018 | $0.00335 |
| Haiku 4.5 | $0.00009 | $0.00167 |
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 8d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Skills Best Practices
Design and development guide for AI agent skills, including Claude Code skills and MCP tools. Contains 46 rules across 8 categories, prioritized by impact to guide skill creation, review, and optimization.
When to Apply
- Creating new Claude Code skills or MCP tools
- Writing or reviewing SKILL.md metadata and descriptions
- Optimizing skill trigger reliability
- Structuring content for progressive disclosure
- Testing skill activation and behavior
- Designing tool interfaces for agent workflows
Core Principles
1. Descriptions drive activation. Claude selects skills based on description matching against user intent. Include specific capabilities, trigger keywords, and negative cases. A skill with a vague description activates inconsistently or never.
2. Front-load critical instructions. Claude may truncate long content. Place non-negotiable rules in the first 100 lines. Bury important constraints at the end and they get ignored.
3. Progressive disclosure saves tokens. Load detailed content only when needed. A 2000-line skill wastes context on every activation. Structure as: SKILL.md (overview) → references/ (details) → scripts/ (execution).
4. Test activation, not just execution. A skill that works perfectly but never triggers provides zero value. Test with real user phrases, synonyms, and edge cases before deployment.
5. One skill per domain. Overlapping skills create activation conflicts. Split by clear boundaries (language, framework, workflow stage) with distinct trigger keywords.
Rule Categories
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Skill Metadata Design | CRITICAL | meta- |
| 2 | Description Engineering | CRITICAL | desc- |
| 3 | Content Structure | HIGH | struct- |
| 4 | Trigger Optimization | HIGH | trigger- |
| 5 | Progressive Disclosure | MEDIUM-HIGH | prog- |
| 6 | MCP Tool Design | MEDIUM | mcp- |
| 7 | Testing and Validation | MEDIUM | test- |
| 8 | Maintenance and Distribution | LOW-MEDIUM | maint- |
What ships with it
51 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.md 213 B
- assets/templates/_template.md 663 B
- metadata.json 1.1 KB
- references/_sections.md 1.8 KB
- references/desc-avoid-vague-terms.md 1.6 KB
- references/desc-differentiate-similar-skills.md 1.8 KB
- references/desc-include-negative-cases.md 1.7 KB
- references/desc-length-optimization.md 2.5 KB
- references/desc-specific-capabilities.md 1.5 KB
- references/desc-third-person-voice.md 1.4 KB
- references/desc-trigger-keywords.md 1.4 KB
- references/maint-audit-security.md 1.9 KB
- references/maint-changelog.md 1.8 KB
- references/maint-plugin-packaging.md 1.6 KB
- references/maint-semantic-versioning.md 1.5 KB
- references/mcp-allowed-tools.md 1.6 KB
- references/mcp-error-messages.md 1.6 KB
- references/mcp-idempotent-operations.md 1.8 KB
- references/mcp-parameter-descriptions.md 1.8 KB
- references/mcp-tool-naming.md 1.6 KB
- references/mcp-tool-scope.md 2.2 KB
- references/meta-allowed-frontmatter-fields.md 2.0 KB
- references/meta-directory-match.md 1.4 KB
- references/meta-frontmatter-yaml-syntax.md 1.3 KB
- references/meta-name-format.md 1.4 KB
- references/meta-name-hyphen-boundaries.md 1.4 KB
- references/meta-name-length.md 1.5 KB
- references/meta-name-no-consecutive-hyphens.md 1.6 KB
- references/meta-name-uniqueness.md 1.2 KB
- references/meta-required-frontmatter.md 1.5 KB
- references/prog-lazy-load-examples.md 1.8 KB
- references/prog-mutual-exclusion.md 1.7 KB
- references/prog-one-level-deep-links.md 1.7 KB
- references/prog-scripts-execute-not-read.md 1.8 KB
- references/prog-three-level-disclosure.md 2.0 KB
- references/project-conventions.md 2.3 KB
- references/struct-code-blocks-with-language.md 1.4 KB
- references/struct-header-hierarchy.md 1.3 KB
- references/struct-imperative-instructions.md 1.6 KB
- references/struct-instructions-first.md 1.6 KB
- references/struct-line-limit.md 1.6 KB
- references/struct-single-responsibility.md 1.6 KB
- references/test-edge-cases.md 1.9 KB
- references/test-instruction-clarity.md 1.8 KB
- references/test-negative-scenarios.md 2.1 KB
- references/test-trigger-phrases.md 1.9 KB
- references/trigger-error-patterns.md 1.5 KB
- references/trigger-file-type-patterns.md 1.5 KB
- references/trigger-slash-command-aliases.md 1.4 KB
- references/trigger-synonym-coverage.md 1.6 KB
- references/trigger-workflow-stages.md 1.6 KB
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.
- 8d ago First seen · 141 lines · 91 tokens per session scan A d205ddd3ed97
skill-authoring is a skill published in the GitHub repository pproenca/dot-skills (203 stars, last pushed 23d ago), licensed MIT. It adds 91 tokens to every session and 1,674 once invoked, about $0.0005 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 2026-08-30.
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…