bren-skills

Plugin bren-skills from marketplace bren-skills in brenbuilds1/skills. Commands read from the repo's manifest — 1 month ago.

Skills (9)

• engineering-review

  Code review stance for serious engineering changes. Use when asked to review a diff, PR, commit, branch, patch, architecture change, migration, implementation, or test plan for bugs, regressions, missing tests, operational risk, security/privacy issues, and maintainability problems that could actual

• loop-referee

  Referee for loops between coding agents where one produces and another judges in rounds: Claude Code writing while Codex reviews, or the reverse. Use when running or setting up a cross-model review loop, a test-fix loop, a doc-review loop, or any "loop until clean" workflow. Sets the loop contract u

• memory-audit

  Fact-check an agent's persistent memory against the repo it describes. Use when an agent acts on outdated notes, when inheriting a project with existing CLAUDE.md / AGENTS.md / rules files, after a large refactor, or periodically on any long-lived project. Inventories every memory and instruction fi

• render-critic

  Runs a blind critic loop on agent-built 3D: screenshots from fixed cameras, scored 0 to 10 by a fresh critic agent, against photos when the scene is a real place, with a stop rule when rounds stop improving. Use when agent-built 3D looks flat, sloppy, or AI-made, or when a scene of a real place does

• skill-auditor

  Audit a third-party agent skill (Claude Code / Codex / Gemini CLI SKILL.md packages) before installing it. Use when asked to audit, vet, review, or security-check a skill, plugin, or marketplace package, or before installing one from GitHub or a marketplace. Clones the package read-only, runs supply

• slop-audit

  Audits a site or app UI for the AI-generated tells that independent sources agree on, and reports each finding as a tell, smell or choice with a file and line receipt. Never rewrites. Use when a site or app UI might read as AI-generated or vibe-coded: before shipping a landing page, after an agent b

• ste-audit

  Check output against the machine-checkable ASD-STE100 rules: sentence length caps, noun cluster limits, allowed verb forms, -ing restrictions, passive voice, paragraph limits. Use after adding an STE memory line, CLAUDE.md rule, or writer skill, or when replies drift wordy again. Violations table wi

• trust-ladder

  Audits a coding-agent setup against the trust ladder: the environment that makes agent output trustworthy enough to stop micromanaging and scale up. Use when the user supervises one agent all day, ferries bug reports or context into agent chats by hand, reviews every agent diff, wants more agents ru

• unclebob

  A do-not-read-the-code workflow for delegating implementation to a coding agent. Use when handing an agent a feature, a fix, or a refactor with a defined outcome that the user does not intend to review line by line. Not for throwaway scripts or exploratory spikes. The agent turns the request into hu