mthines/agent-skills

1

init-claude Initialize Claude Code configuration for a project by analyzing directory structure, detecting tech stack, and genera…

mthines/agent-skills

8

2

documentation Authors, audits, and maintains project documentation across CLAUDE.md / .claude/rules/, AGENTS.md, README.md, and Diá…

mthines/agent-skills

5

3

create-plan Create a comprehensive implementation plan artifact (plan.md) in `.agent/{branch}/` from the current conversation con…

mthines/agent-skills

3

4

create-walkthrough Generate a walkthrough artifact (walkthrough.md) in `.agent/{branch}/` summarizing completed work for PR delivery. Ga…

mthines/agent-skills

3

5

eval-iterate Iterates on a failing AI/LLM eval (an L2 suite, a golden-set / judge eval, or any eval gating a PR) until it is green…

mthines/agent-skills

3

6

preview-spec Makes a UI pull request autonomously verifiable. `author` generates a step-by-step UI verification spec for the PR's …

mthines/agent-skills

3

7

pr-review One-shot read-only review of a GitHub PR — dispatches the `pr-reviewer` agent and reports its verdict and findings wi…

mthines/agent-skills

2

8

review-quality-gate Self-check quality gate for review findings. Validates that each finding is actionable, evidence-backed, correctly lo…

mthines/agent-skills

2

9

linear-planning Plans and creates well-structured Linear projects, milestones, and tickets from a rough idea or a meeting transcript …

mthines/agent-skills

1

10

meeting-notes Turn a meeting transcript into tight, scannable notes — the essence, not a wall of text. Source-agnostic: works on pa…

mthines/agent-skills

1

11

test-autofix Diagnoses failing tests across any project, classifies each failure as a test-bug, prod-bug, or unsure, confidence-ga…

mthines/agent-skills

1