stark-ai-de/agent-skills
Public Codex-ready skills and clearly separated incubator candidates,
generated directly from repository SKILL.md files.
npx skills@latest add stark-ai-de/agent-skills --listPromoted catalog
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
npx skills add https://github.com/stark-ai-de/agent-skills --skill codegraph-ast-grep -g -a codexAudit, review, clean up, and prune Codex memories. Use when the user asks about ~/.codex/memories, stale or noisy memories, memory pollution, cross-repo rule leakage, sensitive memory contents, memory config tuning, cleanup plans, or whether entries belong in memory, AGENTS.md, repo docs, skills, config, or deletion. Do not use for ordinary repo docs cleanup.
npx skills add https://github.com/stark-ai-de/agent-skills --skill codex-memory-curator -g -a codexInterview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
npx skills add https://github.com/stark-ai-de/agent-skills --skill codex-spec-interviewer -g -a codexCandidate catalog
Incubator pages are marked as candidate/internal and are not presented as promoted public catalog entries.
Source of truth
Skill names, descriptions, categories, metadata, source links, and proof links are read at build time from the repo tree.