Younsang Codex Skills

Plugin younsang-codex-plugin in nayounsang/younsang-codex-plugin. Commands read from the repo's manifest — 1 month ago.

Skills (14)

• angry-insight

  Analyze newly collected prompts and research ways to prevent mistakes from recurring, but only when the user explicitly invokes `$angry-insight`. Do not activate from frustration, questions about Angry Insight, or mentions of previous prompts.

• api-scenario-forge

  Control MSW HTTP and WebSocket scenarios from an AI agent, then verify the resulting browser or Node application behavior end to end. Use when external API availability must be removed from development or when loading, failure, malformed, edge-case, or alternative API responses need to be exercised.

• dev-docs-review

  Audit developer documentation against a repository's implementation, public contracts, user journeys, and authoritative ecosystem sources, reporting evidence-backed findings and actionable rewrites without editing files.

• install-complex-prompt

  Install or update Codex Complex Prompt for Codex CLI when the user asks to set it up.

• install-plannotator

  Install Plannotator and its Codex integration on macOS, Linux, WSL, or Windows when the user explicitly asks to install it.

• skill-evaluation

  Evaluate a Codex skill's routing accuracy and task quality with a human-approved, isolated workflow. Run only when the user explicitly invokes $younsang-codex-plugin:skill-evaluation; do not start from an implicit request to evaluate a skill.

• strict-review

  Perform an explicit, read-only, high-recall review of a code change for concrete defects, security, performance, reachability and defense proportionality, public contract compatibility, UI accessibility, readability, maintainability, structural refactoring, semantic naming, dependency reuse candidat

• write-pr-content

  Index the focused Markdown fragment skills used to document pull request changes; invoke a child skill for the requested fragment instead of using this package as a standalone PR writer.

• benchmark-results

  Format evidence-backed performance results with only the software, dependency, device, browser, and physical environment dimensions relevant to the measured workload.

• bug-reproduction

  Reconstruct evidence-backed bug reproduction steps for an underspecified bug fix when regression tests, commands, and the diff provide enough detail.

• change-diagram

  Create a scoped Markdown diagram of externally observable change behavior, showing only the named target and its direct level-1 interactions.

• functional-change-spec

  Write a pull request Markdown fragment describing observable functional behavior when the diff and tests provide sufficient evidence.

• reference-links

  Return a pull request Markdown fragment of related references that were actually used to understand or implement the change.

• visual-evidence

  Add a pull request Markdown screenshot fragment for a UI change, or report which capability is missing when evidence cannot be captured.

MCP servers (1)

• chrome-devtools

  runs: npx -y [email protected] --browser-url=http://127.0.0.1:9222

Hooks (2)

• SessionStart

  python3 "${PLUGIN_ROOT}/skills/angry-insight/scripts/queue.py" session-start

• UserPromptSubmit

  python3 "${PLUGIN_ROOT}/skills/angry-insight/scripts/queue.py" capture

Similar plugins