Skill Claude CodeCodex
Walk every unresolved review thread on a PR, triage each one, reply with a rationale of whether or not the comment will be acted upon, make the code change if warranted, and mark the thread resolved. Use when the user asks to address only the open PR comments without re-running CI, respond to review feedback, resolve…
Skill Claude CodeCodex
Amend the last git commit with a useful, descriptive message. Use when you want to rewrite a commit message, amend commit description, or improve the last commit message.
Skill Claude CodeCodex
Archive the current Argus task so it moves to the Archive section of the task list. Use at the end of a session when the work is done.
Skill Claude CodeCodex
Manage recurring or one-shot tasks in the local Argus daemon via its HTTP API. Use when the user wants to schedule a task locally in argus, create a cron-driven task, fire X every weekday/hour/morning, fire something once at a specific future time or "in N minutes" (one-shot via runonceat), set up an agent that needs…
Skill Claude CodeCodex
Safely add a directory to Claude Code's Bash tool PATH. Use when a binary runs in your terminal but is "command not found" inside Claude Code's Bash tool, when adding a directory to PATH for Claude Code, when configuring CLAUDEENVFILE, or when settings.json env.PATH did not work. Explains why env.PATH replaces rather…
Skill Claude CodeCodex
Find which commit introduced a bug using git bisect with automatic test verification. Use when tracking down which commit introduced a bug.
Skill Claude CodeCodex
Generate an intelligent changelog from recent commits. Use for release notes, version history, or documenting what changed.
Skill Claude CodeCodex
Investigate flaky CI failures across multiple workflow runs to identify patterns, categorize root causes, and propose fixes. Use when asked to investigate CI failures, find flaky tests, diagnose test flakiness, or understand why CI is failing repeatedly.
Skill Claude CodeCodex
Compare two competing PRs implementing the same feature, identify strengths of each, and combine the best parts into a single branch. Use when comparing PRs, combining implementations, cherry-picking between PRs, or resolving competing approaches.
Skill Claude CodeCodex
Mark the current Argus task as complete. Use when the work for the current worktree is done and the user wants the task to transition to the "complete" status.
Skill Claude CodeCodex
Competing implementations with judge evaluation. Use when comparing multiple approaches, picking the best solution, or running a bake-off.
Skill Claude CodeCodex
Set up cross-agent skill infrastructure so skills work across Claude Code, OpenAI Codex, and GitHub Copilot. Use for multi-agent compatibility, skill migration, cross-agent sync.
Skill Claude CodeCodex
Multi-agent competing hypotheses debugging. Use when stuck on a bug, need root cause analysis, or want competing debug theories.
Skill Claude CodeCodex
Audit every commit pending between a base branch and a deployed branch/tag for deploy risk (migrations, config/secret wiring completeness, feature-flag defaults, schema parity), then open the GitHub compare diff. Use when asked to audit pending commits, check deploy risk, review what is about to ship, or before…
Skill Claude CodeCodex
Validate a deploy after it lands — CI status, rollout health, error tracking, and monitoring/alerting — correlating every finding against the deploy's start time to separate genuine regressions from pre-existing noise. Use when asked to validate a deploy, check post-deploy health, confirm a production rollout is…
Skill Claude CodeCodex
Deploy latest master to production with a version tag. Use when releasing to production or tagging a deploy.
Skill Claude CodeCodex
Audit outdated dependencies, check for vulnerabilities, and upgrade with test verification. Use for dependency audits, security checks, or upgrading packages.
Skill Claude CodeCodex
Multi-agent iterative development with parallel testing and code review. Use for building features, implementing changes, or coding tasks that need testing and review.
Skill Claude CodeCodex
Execute the /devils-advocate workflow shared across Codex, Claude Code, and Copilot in this repository. Use when you want to stress-test ideas, challenge assumptions, or play devil's advocate.
Skill Claude CodeCodex
Scheduled KB maintenance — ingest yesterday's meetings + session captures, synthesize raw notes into existing topical docs (decisions, people changes, conventions), resolve conflicts, age out stale entries, fix frontmatter and links. Translates raw data into knowledge. Runs unattended; never asks for confirmation. Use…
Skill Claude CodeCodex
Explain any topic in the simplest possible terms using analogies and everyday examples. Use when the user says "explain like I'm 5", "eli5", "explain simply", "dumb it down", or "explain in simple terms".
Skill Claude CodeCodex
Search and read Gmail messages. Use when looking up emails, reading email threads, or checking inbox labels.
Skill Claude CodeCodex
Analyze a spec, PRD, or codebase to identify missing skills and agents, propose them, then write them. Use for skill gap analysis, agent gap analysis, bootstrapping agent capabilities from a spec, or equipping a project with skills.
Skill Claude CodeCodex
Multi-agent parallel research with peer-challenged synthesis. Use for deep research, codebase exploration, or investigating how something works.