Create and test AI agent skills using test-driven development methodology.
npx skills add https://github.com/Amorim33/.agents --skill writing-skills-amorim33
Please help me install this Agent Skill. Skill: writing-skills Source: https://github.com/Amorim33/.agents/tree/main/skills/writing-skills Command: npx skills add https://github.com/Amorim33/.agents --skill writing-skills-amorim33
name and description frontmatter, keyword coverage, and token-efficient structure so agents actually find the skill. - Rationalization bulletproofing: Techniques like rationalization tables, red-flag lists, and explicit loophole closing for discipline-enforcing skills. - Use Case: You want to create a new skill enforcing a code-review workflow. Use this Skill to first run a baseline scenario without the skill, capture the agent's excuses verbatim, then write and iteratively harden the skill until agents comply under pressure. ## Quick Start Ask the agent to help you create a new skill using the writing-skills TDD process, starting with a baseline pressure scenario.High-intent search queries and answers about installing and using this skill.
A SKILL.md needs YAML frontmatter with only name and description fields, followed by a Markdown body with an overview, when-to-use triggers, core patterns, and a quick reference. The description should start with "Use when..." and describe triggering conditions only, never the workflow.
Test skills by running pressure scenarios with subagents: first without the skill to capture baseline failures and rationalizations, then with the skill to verify compliance. Iterate by closing loopholes agents discover until the skill holds under combined pressures like time and sunk cost.
The description should only state when to use the skill, starting with "Use when..." plus concrete symptoms and situations. Never summarize the skill's process, because agents may follow the description shortcut instead of reading the full skill body.
Skip skill creation for one-off solutions, well-documented standard practices, project-specific conventions that belong in CLAUDE.md, and mechanical constraints that can be enforced with regex or validation automation instead of documentation.
Agents rationalize around rules under pressure from time constraints, sunk cost, or authority claims. Counter this with explicit loophole closing, rationalization tables built from baseline testing, and red-flag checklists that make violations easy to self-detect.
bostonaholicEnforce the RED-GREEN-REFACTOR cycle for test-driven development.
OmniNode-aiGuide users through contributing skills via GitHub CLI pull requests.
guanyangCreate and test agent skills using TDD-style pressure scenarios and rationalization bulletproofing.
ThedouglerAutomate recurring rule violations into hooks, permissions, and lint rules.