Build Tested AI Skills
AI skills can fail when instructions are vague or untested. This skill guides test-driven skill writing with pressure scenarios and verification loops.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "writing-skills" from https://skillstore.io/skills/obra-writing-skills.md and its manifest at https://skillstore.io/api/skills/obra-writing-skills/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "writing-skills". A request to create a skill for flaky async tests.
Expected outcome:
Using "writing-skills". A draft skill that agents keep ignoring under deadline pressure.
Expected outcome:
Using "writing-skills". A team wants to standardize several skill documents.
Expected outcome:
Static analysis flagged many command, filesystem, and reconnaissance patterns, but review found them to be documentation examples or constrained local helper behavior. No prompt injection, data exfiltration, credential access, or malicious execution intent was found in the reviewed files.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/obra-writing-skills/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/obra-writing-skills?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/obra-writing-skills?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/obra-writing-skills/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/obra-writing-skills.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>obra. (2026). writing-skills security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/obra-writing-skills/audits/8@techreport{obra-obra-writing-skills-2026,
author = {obra},
title = {writing-skills security audit report (audit version 8)},
institution = {Skillstore},
year = {2026},
number = {8},
url = {https://skillstore.io/skills/obra-writing-skills/audits/8},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "writing-skills security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
- name: "obra"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/obra-writing-skills/audits/8"
identifiers:
- type: other
value: "skillstore:obra-writing-skills:audit:8"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
obra-writing-skills
2026-08-21
codingcossack-writing-skills
2026-08-21
dimon94-writing-skills
2026-08-21
dyai2025-writing-skills
2026-08-21
sickn33-writing-skills
2026-08-21
zhanlincui-writing-skills
2026-08-21
davila7-writing-skills
2026-08-21
cycleaddict-writing-skills
2026-08-21
cygnusfear-writing-skills
2026-08-21
Use the TDD workflow to define triggers, write focused instructions, and verify agent behavior before deployment.
Use pressure scenarios to find where agents rationalize around rules, then revise the skill to close gaps.
Apply structure, naming, discovery, and testing checks before adding skills to a shared repository.
Help me plan a new AI skill for this situation. Identify the trigger, intended user behavior, and the first pressure scenario to test.
Create three pressure scenarios for this skill. Include time pressure, sunk cost, authority pressure, and clear success criteria.
Review this skill description and SKILL.md outline. Make the trigger clearer without summarizing the full workflow.
Evaluate this skill using the RED-GREEN-REFACTOR checklist. Identify missing tests, unclear rules, rationalization gaps, and release blockers.
Author
obraLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
62e2a730c5cd74eab4c7164309d810de660fcea3
Maintenance freshness
7/18/2026
Usage
9 downloads · 197 views
Create Detailed Implementation Plans
Complex work is risky when requirements are not broken into clear steps. This skill turns specs into test-focused implementation plans for Claude, Codex, and Claude Code.
Execute Implementation Plans with Checkpoints
Implementation plans can lose focus when work moves into a separate AI session. This skill guides Claude, Codex, and Claude Code through batch execution, verification, and review checkpoints.
Evaluate Code Review Feedback
Code review feedback can be unclear, incorrect, or incomplete. This skill helps Claude, Codex, and Claude Code verify suggestions, ask precise questions, and implement reviewed changes carefully.
Plan Features Through Guided Brainstorming
Feature ideas often move to implementation before goals and constraints are clear. This skill guides Claude, Codex, and Claude Code through questions, trade-offs, and validated design notes.
Execute Plans with Subagent Reviews
Complex implementation plans lose quality when one context handles every task. This skill coordinates fresh subagents for implementation, spec checks, and code quality reviews.
Request Code Reviews Before Merge
Unreviewed changes can ship bugs, regressions, or incomplete requirements. This skill guides Claude, Codex, and Claude Code to request structured review before merge.
Plan Software Projects With Structured Documents
by Dwsy
Software projects often fail when requirements, design choices, and tasks are unclear. This skill turns project ideas into structured planning documents for Claude, Codex, and Claude Code workflows.
Generate Bilingual GitHub Release READMEs
by ZhanlinCui
Release notes and README updates can take time before each GitHub release. This skill generates bilingual release documentation and guides review, commit, and push steps.
Visualize Service Architecture
by AstraBit-CPT
Distributed services are hard to understand when metadata is spread across repositories. This skill aggregates catalog metadata and creates diagrams, tables, and summaries for architecture review.
Create Human-Ready AI Documentation
by Brownbull
Detailed AI context files are often too long for quick human review. This skill turns them into summaries, quick starts, and Mermaid visual guides.
Create Effective AI Skills
by notedit
Teams need repeatable guidance to build useful AI skills without adding unnecessary context. This skill provides a structured process for planning, writing, validating, and packaging skills.
Create FlowGram Component Docs
by bytedance
FlowGram material components need consistent docs, runnable Story examples, API tables, and bilingual review steps. This skill gives Claude, Codex, and Claude Code a structured workflow for producing those assets.