A ralph harness for long-running AI coding tasks — a generator-evaluator loop that orchestrates Claude Code, OpenAI Codex & GitHub Copilot across repositories 🍩
Skill Claude CodeCodex
Draft the ralphctl CHANGELOG.md ## [Unreleased] section from the commits since the last release tag — grouping conventional-commit subjects into Keep-a-Changelog sections (Breaking / Added / Changed / Fixed / Removed) and flagging internal churn to omit. Use this whenever you're updating the changelog, preparing…
Skill Claude CodeCodex
Low-level AI CLI spawn mechanics used by ralphctl's provider adapters — headless / interactive spawn, the file-based contract (signals.json + sessionId files), idle-stdout watchdog, exponential rate-limit backoff, and session resume for in-flight recovery. Use when modifying…
Skill Claude CodeCodex
Audit the ralphctl .claude/ setup (the 7 subagents, the in-repo skills, the .claude/docs/ modules) and CLAUDE.md for DRIFT against the real src/ — stale version stamps, renamed/dead paths, removed symbols, unshipped env vars, and fabricated references. Use this whenever someone asks to "audit / refresh / clean up /…
Skill Claude CodeCodex
Check the chain-flow step-traces documented in .claude/docs/ (KERNEL-DESIGN.md examples, the diagrams/, REQUIREMENTS step lists) against the REAL element-name sequence each flow runs, and fix the drift. Use this after changing a flow's element list (adding/removing/reordering a leaf/sequential/guard/loop, renaming an…
Skill Claude CodeCodex
Article-grounded reference for the three Anthropic harness articles. Use when designing or auditing an agent harness, reasoning about long-running-agent state / memory / progress handoff, deciding how much scaffolding a flow needs, pruning components on a model bump, or designing a generator / evaluator split. The…
Skill Claude CodeCodex
Auto-triggers on structural harness decisions: new chain primitive, new flow, remove evaluator, wrap evaluator, redesign harness, scaffolding, load-bearing, model upgrade, harness audit, refactor flow, sub-agent. Also triggers on file mentions of src/application/chain/, src/application/flows/…
Skill Claude CodeCodex
Land an open PR on this repo — wait for CI to finish, then merge with a merge commit using admin bypass. Use whenever the user says "merge this PR", "/merge-pr", "ship the PR", "land the PR", or asks to merge a specific PR number. Defaults to the PR opened from the current branch.
Skill Claude CodeCodex
End-to-end release flow for lukas-grigis/ralphctl. Mirrors the established release pattern: branch → bump → changelog → PR → CI → merge → tag → workflow.
Skill Claude CodeCodex
Run the project's full verification gate — typecheck, lint, tests — in one go. Use after any code change before committing, or when the user asks "is it green?" / "can I ship this?" / "verify" / "run checks".
Skill Claude CodeCodex
Cross-phase skill — design the shape of the change (entities, boundaries, seams) before generating code, tasks, or acceptance criteria. Failure mode is "big blob" output that obscures the core change.
Skill Claude CodeCodex
Cross-phase skill — establish a shared understanding of what will and will not be done before producing output. Restate the input back to the user, surface assumptions, name non-goals, and agree before you write. For an input that is still a raw, unshaped idea needing multiple candidate directions before one is…
Skill Claude CodeCodex
Session-discipline skill — settle the plan before touching code, work in small verified increments with a feedback loop that proves each change works, and record corrections so the same mistake is not repeated. Use when executing multi-step coding tasks where batching unverified work would compound risk; bundles…
Skill Claude CodeCodex
Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…
Skill Claude CodeCodex
Systematic root-cause debugging. Use when tests fail, builds break, or behaviour does not match expectations. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the reproduction and regression steps follow the same red-green discipline as…
Skill Claude CodeCodex
Domain-modelling skill — align code with the business domain through ubiquitous language, bounded contexts, small aggregates, domain events, and core-domain focus. Use when naming concepts, drawing module or service boundaries, deciding entity vs value object, integrating external systems, or when the code no longer…
Skill Claude CodeCodex
Ideation skill — refine a raw, unshaped idea into a sharp, buildable concept through divergent expansion (variation lenses like inversion, simplification, audience shift) followed by convergent stress-testing (user value, feasibility, differentiation), ending in a one-pager with explicit assumptions and a "Not Doing"…
Skill Claude CodeCodex
Cross-phase skill — treat AI output as a controlled feedback loop, not a one-shot generation. Run the cheap check after each meaningful change; re-read your own output before signalling completion. For the fuller session workflow — plan-first sequencing plus durable learning capture — see the opt-in…
Skill Claude CodeCodex
Behavioural guardrails against four empirical LLM coding failure modes — silent assumptions, over-complication, orthogonal damage to code you don't fully understand, and declaring done without verification. Use when writing, reviewing, or refactoring code to surface assumptions early, keep changes proportionate to the…
Skill Claude CodeCodex
Cross-phase skill — question every piece of AI-workflow scaffolding on every model upgrade; remove non-load-bearing pieces one at a time with measurement. Complexity drifts upward by default; subtraction requires discipline. Governs scaffolding built around AI usage (prompts, wrapper scripts, guardrails, validation…
Skill Claude CodeCodex
Anti-over-engineering ladder for choosing HOW to implement something — before writing custom code, climb the rungs in order and stop at the first that holds. Does this need to exist at all (YAGNI) → already in the codebase → standard library → native platform feature → already-installed dependency → one line → minimum…
Skill Claude CodeCodex
Execute-phase scope-containment checklist — write the minimum code the task needs and touch only the files and lines the task requires; surface out-of-scope findings as notes rather than fixing them inline. Governs the footprint of a change whose approach is already decided; for choosing that implementation approach…
Skill Claude CodeCodex
Execute-phase skill — write the failing test before the code that makes it pass; for bug fixes, this is the reproduction test itself. Use for any logic change, bug fix, or behavioural modification; for the full root-cause triage pipeline around an unexpected failure, see ralphctl-debugging-and-error-recovery.