Pitfalls Check
Testing & Qualitypitfalls-checkPitfalls Check is an Agent Skill for testing & quality published in the strapi/documentation repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Audit a documentation file against the known-pitfalls list: common mistakes, outdated patterns, deprecated APIs.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/strapi/documentation/blob/HEAD/claude-plugins/inki/skills/pitfalls-check/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/pitfalls-check, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
/inki:pitfalls-check: known pitfalls audit
Step 1: Read the target file
$ARGUMENTS is a relative path.
Logging: unless --no-log is passed, write this skill's report to the run log per ../../references/logging.md (--log-dir <path> and --short-log are also accepted). When invoked as part of an orchestrator (e.g. /inki:review), write into that run's existing directory instead of creating a new one.
Step 2: Load the known-pitfalls catalog
Read ../../references/prompts/integrity-known-pitfalls.md. This file is a reference catalog of documented hallucination patterns (organized by category, with tables mapping the wrong pattern to the correct one and a short context note). For each entry, check whether the target file matches the hallucinated pattern.
Step 3: Report
Target: <path>
Pitfalls found:
- <pitfall name>: <line or section reference>: <suggested fix>