mirror of https://github.com/secondsky/claude-skills.git synced 2026-09-18 19:54:22 +08:00

Files

T

History

secondsky 292c93845e feat(humanize-writing): add skill plugin, lockstep 3.9.0

- Rewrites AI-sounding text to read human; 8 editing passes + review-only mode
- Adapted from jpeggdev/humanize-writing (MIT); npm installer scaffolding dropped
- Frontmatter condensed to 238 chars (sync enforces 250 max for single-skill plugins)
- Lockstep bump 3.8.0 -> 3.9.0: all 145 plugins, both marketplaces, package.json
- CHANGELOG entry for 3.9.0

2026-09-09 17:02:38 +02:00

.claude-plugin

feat(humanize-writing): add skill plugin, lockstep 3.9.0

2026-09-09 17:02:38 +02:00

.codex-plugin

feat(humanize-writing): add skill plugin, lockstep 3.9.0

2026-09-09 17:02:38 +02:00

skills/code-review

fix: add license: MIT to 92 skills, correct Nitro preset naming

2026-04-02 19:49:06 +02:00

README.md

refactor: Flatten plugin structure to fix skill discovery (v3.2.0)

2025-12-24 02:03:18 +01:00

README.md

Code Review Skill

Technical rigor and evidence-based practices for code review workflows.

Overview

This skill guides proper code review practices emphasizing technical correctness over social comfort, evidence-based claims, and verification before completion. It covers receiving feedback, requesting reviews, and implementing verification gates.

Core Practices

Receiving Feedback - Technical evaluation over performative agreement
Requesting Reviews - Systematic review via code-reviewer subagent
Verification Gates - Evidence before any completion claims

When to Use

Receiving code review comments (unclear or technically questionable)
Completing tasks or major features requiring review
Before making any completion/success claims
Before committing, pushing, or creating PRs
Subagent-driven development workflows

Key Principles

NO performative agreement - No "Great point!" or "You're absolutely right!"
Verify before implementing - Check suggestions against codebase reality
Evidence before claims - Run verification commands, read output, THEN claim
Push back when wrong - Technical correctness over social comfort

Reference Files

references/code-review-reception.md - Receiving feedback protocol
references/requesting-code-review.md - How to request reviews
references/verification-before-completion.md - Verification gates

Auto-Trigger Keywords

code review
pull request review
technical feedback
verification gates
completion claims
subagent review
merge requirements
evidence-based development

Source

Adapted from mrgoonie/claudekit-skills