Remediate GitHub Actions action findings identified by the action-audit skill. Applies the appropriate fix per action type — @main ref for internal bitwarden/ actions, full SHA with inline version comment for external actions, or full replacement — across selected repos and creates draft PRs. Run the action-audit skill first to identify findings before using this skill.
EnglishAnalyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.
EnglishCommit work with feature-branch + PR discipline and enforce commit-message rules via git hooks. Use when committing code, opening a PR, or setting up a new repo's commit hygiene. Installs three git hooks (commit-msg subject rules, pre-commit auto-checks, pre-push protect-main), creates a feature branch from main if needed, runs the project's lint/format/test before commit, generates a conformant commit message (capital start, ≤72 chars, no trailing period, no Co-Authored-By, one logical change per commit), pushes, opens a PR via gh pr create, and prunes merged branches. Never pushes to main, never merges PRs, never force-pushes. Co-activates with shell-discipline and engineering-philosophy.
EnglishLocates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
EnglishUse when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.
EnglishReviews Claude configuration files for security, structure, and prompt engineering quality.
EnglishFive-phase umbrella playbook for an initiative shepherd. Dispatches to phase-deep skills (Research, PoC, Scoping, Implementation) at the right moment.
EnglishRead and inspect Figma designs via the Dev Mode MCP server — selects the right tool, parses Figma URLs into fileKey and nodeId, and turns design context into useful input for critique, copy review, handoff prep, and Design System work.
EnglishApply fixes for workflow linter findings identified by the workflow-audit skill. Applies mechanical fixes automatically, pauses for judgment calls, verifies with a re-lint, and creates draft PRs. Run the workflow-audit skill first to identify findings before using this skill.
English
AGENT SKILLS ATLASIncludes Action Remediate, Analyzing Git Sessions, Committing Changes, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Action Remediate
Remediate GitHub Actions action findings identified by the action-audit skill. Applies the appropriate fix per action type — @main ref for internal bitwarden/ actions, full SHA with inline version comment for external actions, or full replacement — across selected repos and creates draft PRs. Run the action-audit skill first to identify findings before using this skill.
Analyzing Git Sessions
Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.
Committing Changes
Commit work with feature-branch + PR discipline and enforce commit-message rules via git hooks. Use when committing code, opening a PR, or setting up a new repo's commit hygiene. Installs three git hooks (commit-msg subject rules, pre-commit auto-checks, pre-push protect-main), creates a feature branch from main if needed, runs the project's lint/format/test before commit, generates a conformant commit message (capital start, ≤72 chars, no trailing period, no Co-Authored-By, one logical change per commit), pushes, opens a PR via gh pr create, and prunes merged branches. Never pushes to main, never merges PRs, never force-pushes. Co-activates with shell-discipline and engineering-philosophy.
Extracting Session Data
Locates, lists, filters, and extracts structured data from Claude Code native session logs. Supports both single and multiple session analysis.
Posting Review Summary
Use when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.
Reviewing Claude Config
Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes to CLAUDE.md files (project-level or .claude/), ski
Shepherding an Initiative
Five-phase umbrella playbook for an initiative shepherd. Dispatches to phase-deep skills (Research, PoC, Scoping, Implementation) at the right moment.
Using Figma
Read and inspect Figma designs via the Dev Mode MCP server — selects the right tool, parses Figma URLs into fileKey and nodeId, and turns design context into useful input for critique, copy review, handoff prep, and Design System work.
Workflow Fix
Apply fixes for workflow linter findings identified by the workflow-audit skill. Applies mechanical fixes automatically, pauses for judgment calls, verifies with a re-lint, and creates draft PRs. Run the workflow-audit skill first to identify findings before using this skill.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Action Remediate skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: NOASSERTION. The author’s terms apply.