MintedKenny

MintedKenny/skills

Instructions file CodexOpenCode

Instructions for MintedKenny/skills: Agent Skills for coding agents (Claude Code, Codex, and other Agent Skills–compatible hosts). One skill per folder.

MintedKenny/skills

Skill Claude CodeCodex

Critically audit the changes on a branch — verdict, design audit, strategic implications, and ranked recommendations. Use before merging or when reviewing a diff.

MintedKenny/skills

Skill Claude CodeCodex

Cross-audit an existing list of findings or recommendations — pressure-test each, stabilize modified/new ones, surface what was missed. Use after a review produces findings.

MintedKenny/skills

Skill Claude CodeCodex

Evaluate external content (article, repo, tweet, docs) for ideas worth borrowing into your system — verdict per idea, ranked. Exploratory, no commitments.

MintedKenny/skills

Skill Claude CodeCodex

PR-grade investigation of an issue or request — deep dive, options, and a ranked recommendation, no implementation. Use to scope a bug or feature before writing code.

MintedKenny/skills

Skill Claude CodeCodex

Decompose findings into well-scoped Linear issue drafts (one issue = one PR), preview them, and ask before filing. Never files without explicit confirmation.

MintedKenny/skills

Skill Claude CodeCodex

Run public-safe Parallel.ai research from the terminal and write a cited Markdown report for dev, architecture, standards, and prior-art questions.

MintedKenny/skills

Skill Claude CodeCodex

Set up an architecture-decision archive, agent-context index, and hard-rules table in a repo that lacks them, seeded from choices the code already embodies.