dev-skills

Plugin dev-skills from marketplace cc-toolkit in aeghnnsw/cc-toolkit. Commands read from the repo's manifest — 2 days ago.

Skills (12)

• doc-update

  Use when the user asks to update docs, refresh documentation, fix stale README content, audit documentation quality, remove outdated prose, or bring existing documentation in line with current project truth.

• goal-rubric

  Use when the user wants a measurable /goal rubric, success criteria, acceptance criteria, or completion condition, or when a /goal loop will not close because the criteria are not observable or binary.

• grill-with-research

  Research the project, then grill the user only on decisions that research cannot settle; records glossary terms and ADRs. Use when the user asks to grill or stress-test a plan, design, or issue in the current project.

• lean-tests

  This skill should be used when the user asks to "check the test suite", "audit the tests", "find out why the tests are slow", "make the tests faster", "remove redundant tests", or "review the tests in this change", or asks which pytest tests are flaky, order-dependent, redundant, or check nothing. I

• matt-automode

  Run the Matt planning-to-merge workflow with code review and a navigation retrospective when the user delegates a task fully to the agent without human checkpoints. Requires Matt Pocock's skills plugin.

• pressure-test

  Use when a design, plan, rubric, PR, failure diagnosis, or decision needs independent adversarial review before conclusion, including when another skill needs its decisions reviewed by an independent critic. A read-only Claude critic, run through the Claude Code CLI, supplies the pressure.

• repo-cleanup

  Clean merged worktrees and branches, reconcile completed issues, delete their planning folders, and update the Default Branch.

• sci-project-layout

  This skill should be used when the user asks to set up or adopt the layout of a scientific Python research project, such as a computational chemistry or drug discovery project, or asks where datasets, experiment runs, results, or scratch files go in such a project.

• step-workflow

  Use when the user requests step-based file naming and folder organization for a new feature, including sequential numbered prefixes, sub-step notation, and plan tracking across scripts, outputs, tests, or documentation.

• discord-setup

  This skill should be used when the user asks to "set up discord", "configure discord bot", "install discord plugin dependencies", or wants to set up the prerequisites for the Claude Code Discord channel plugin including bun installation and shell alias configuration.

• pr-feedback

  This skill should be used when the user asks to "gather PR feedback", "review and fix PR issues", "run pr-feedback", "address reviewer comments", or wants to run a structured review-fix-push cycle on the current pull request. Orchestrates self-review, external review collection, issue investigation,

• project-eval

  This skill should be used when the user asks to "evaluate the project", "run a deep eval", "evaluate the auth module", "evaluate this design doc", "find issues in this feature", or "check the running app for UX issues", or wants a broad evaluation of a feature, a design document or plan, a running w

Subagents (2)

• finding-verifier

  Neutral verifier that the project-eval skill dispatches. It checks each finding of a project evaluation against the current project and returns one verdict for each finding ID. Use it only through the project-eval skill.

• project-evaluator

  Skeptical evaluator that the project-eval skill dispatches. It searches a target or a whole project along its assigned dimensions, one angle at a time, until its deadline or until two angles in a row find nothing new. It returns its findings as text. Use it only through the project-eval skill.

Similar plugins