SteveVitali

10 mods across 1 repository, 9 stars between them.

agent-skills

02

SteveVitali/agent-skills

Plugin Claude Code

Rigorous engineering process for AI coding agents: implement-spec, decompose-spec, orchestrate-build, self-review, review-pr, address-pr-comments, agent-docs, refresh-repo-docs.

9 5d ago A tokens not measured original MIT

address-pr-comments

03

SteveVitali/agent-skills

Skill Claude CodeCodex

Work through unresolved review comments on your PR as the author: triage every thread, implement fixes where the reviewer is right, push back with rationale where they aren't, answer questions, commit + push, and reply to every thread with what happened. Use when asked to address, respond to, or resolve PR review…

9 5d ago A 68 tokens original MIT

agent-docs

04

SteveVitali/agent-skills

Skill Claude CodeCodex

Create or converge agent documentation (AGENTS.md hierarchy) for a codebase — bootstrap mode generates docs from scratch, refresh mode detects and fixes drift.

9 5d ago A 33 tokens original MIT

decompose-spec

05

SteveVitali/agent-skills

Skill Claude CodeCodex

Turn one large spec into an optimally-partitioned, dependency-ordered ticket plan — the fewest self-contained tickets that each fit one fresh-context implementation run — and seed a durable build ledger. The planning half of a multi-session build; pairs with orchestrate-build.

9 5d ago A 59 tokens original MIT

implement-spec

06

SteveVitali/agent-skills

Skill Claude CodeCodex

Spec-driven, autonomous end-to-end: branch → plan + test matrix → implement (tests alongside) → self-review → gap-analysis vs spec → close gaps → rigorous downstream verification → PR + evidence report.

9 5d ago A 43 tokens original MIT

orchestrate-build

07

SteveVitali/agent-skills

Skill Claude CodeCodex

Drive a decomposed spec to completion across fresh contexts: SETUP a dedicated worktree, run each ticket end-to-end through implement-spec in a fresh context, update the durable ledger, report progress, pause for intervention at ticket boundaries, and finish with a whole-build capstone verification. The execution half…

9 5d ago A 77 tokens original MIT

refresh-repo-docs

08

SteveVitali/agent-skills

Skill Claude CodeCodex

Audit and sync a repo's human-facing documentation (README, docs/, CHANGELOG, CONTRIBUTING, examples) against the actual code — detect drift deterministically, fix stale claims, remove cruft, fill gaps, and verify every claim written. Use when docs are outdated, after major feature work, or on a periodic docs-hygiene…

9 5d ago A 76 tokens original MIT

review-pr

09

SteveVitali/agent-skills

Skill Claude CodeCodex

Review someone else's GitHub PR as a Staff Engineer and post a high-precision review — mechanical grounding (CI, local verification), focused design + security passes, calibrated severity labels, inline comments with suggestion blocks. Use when asked to review a PR, give feedback on a PR, or act as a code reviewer.

9 5d ago A 66 tokens original MIT

self-review

10

SteveVitali/agent-skills

Skill Claude CodeCodex

Two-pass self-review of the current branch: mechanical verification (build/test/lint + checklists) then a Staff Engineer design critique.

9 5d ago A 29 tokens original MIT