shellck
Shellck
Overview
Provide a fast, repeatable shellcheck pass for repo scripts. Use this skill after editing shell scripts or when a script fails unexpectedly.
Workflow
- Ensure
shellcheckis installed. - From the repo root, run the helper script.
Quick start
Run against the default scripts/ directory:
$CODEX_HOME/skills/shellck/scripts/run_shellck.sh
Run against specific files or directories:
$CODEX_HOME/skills/shellck/scripts/run_shellck.sh scripts/perf-profiler
$CODEX_HOME/skills/shellck/scripts/run_shellck.sh scripts/ other/dir/some.sh
Behavior
- If no paths are provided, it scans
scripts/for shell scripts. - If paths are provided, it accepts files or directories and filters to shell scripts by extension or shebang.
- Exits non-zero on shellcheck failures.
Resources
scripts/
run_shellck.sh: shellcheck runner with sensible defaults and directory filtering.
More from regenrek/agent-skills
hard-cut
Enforce a hard-cut cleanup policy: keep one canonical implementation and delete compatibility, migration, fallback, adapter, coercion, and dual-shape code. Use for pre-release or internal-draft refactors where the goal is one final shape, especially when changing schemas, contracts, persisted state, routing, configuration, feature flags, enum/value sets, or architecture.
14root-cause-finder
Performs root-cause-first debugging and review by tracing expected behavior to the first unintended side effect before changing contracts, parsing, or types. Use when debugging protocol errors, deserialization failures, null payloads, missing fields, restore or hydration issues, state-ownership bugs, unexpected requests, background mutations, or reviewing junior-created code where the visible failure may be downstream noise.
7consolidate-test-suites
Decide exactly where bug-fix test coverage belongs. Use before adding, moving, or deleting tests after a bug fix or architectural change. Select one owning layer, reuse existing canonical suites, block redundant or weakly placed tests, and remove weaker duplicates.
7git-safe-workflow
Safely inspect, stage, commit, and (only if asked) push changes made by an AI agent. Use for commit/push requests, end-of-task checkpoints, merge conflict resolution, worktree safety checks, or deciding whether to use git commit --amend.
4codex-analysis
Run Codex CLI for deep code analysis and second-opinion reviews. Use when the user explicitly asks for Codex analysis, Codex help, or wants a second opinion from Codex on code, architecture, or debugging questions.
3pr-commiter
Agentic PR committer with deterministic commits, enforced branch/PR workflow, and explicit paths (no git add .).
3