Explorar skills

TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop.

Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF path / arXiv URL / pasted text), maps claims to codebase, emits verification table with match status

Query the codemap structural index — central, coupled, deps, rdeps, import path, symbol-level source extraction, and function-level call graph (fn-deps, fn-rdeps, fn-central, fn-blast). TRIGGER when: user asks about module relationships, dependency graph, callers/callees, or blast radius; phrases: "what depends on", "who calls", "imports of", "dependency graph", "blast radius of". SKIP: codemap in

Minimal codex-native audit loop. Use to scan codex configuration/workflow drift and emit ranked gaps with measurable gates.

Minimal codex-native investigation loop. Use for unknown failures and root-cause narrowing with measurable gates.

Session parking lot — automatically parks diverging ideas and unanswered questions to project-scoped memory; /session resume shows pending items, /session archive closes them, /session summary gives a session digest TRIGGER when: user asks "what was I working on", "any pending items", "what''s in the parking lot", "remind me where we left off", "what did we defer"; resume intent clear from context

Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.

Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file.

Multi-agent code review of GitHub Pull Requests (Python source, documentation (Markdown/RST), and CI/CD config PRs) covering architecture, tests, performance, docs, lint, security, and API design.

Minimal codex-native develop loop. Use for implementation tasks with linear plan-build-verify flow and measurable quality gates.

Minimal codex-native optimization loop. Use for metric-driven improvements with guardrails and measurable gates.

Full-sweep quality audit of .claude/ config — cross-references, permissions, inventory drift, model tiers, docs freshness. Scope tokens select what to audit; --upgrade applies docs-sourced improvements; --adversarial runs foundry:challenger + Codex adversarial review; --efficiency sweeps model tiers, token bloat, spawn patterns, boilerplate duplication, and bin/ extraction candidates (extraction p