← All creators

ymd38

User

Claude Code skills & full project harness for AI-assisted development — continuous improvement cycle (evaluate → issue → plan → resolve → verify), strict CI + security gates (gitleaks/semgrep/trivy), guard hooks, and score-aligned coding rules. Harness engineering / loop engineering.

10 indexed · 0 Featured · 4 stars · avg score 77
Prolific

Categories

Indexed Skills (10)

AI & Automation Listed

yds-setup

Install the full dev-skills harness into the current project through a short interview: CLAUDE.md, hooks, .claude/settings.json, rules, and skill wiring. Asks — never auto-detects — the languages (Go / Python / TypeScript / JavaScript) and commands, then writes files only after an approved summary. Use when the user asks to set up / install / bootstrap dev-skills, the harness, or the continuous improvement cycle. Triggers: セットアップして, ハーネスを入れて, harnessを入れて, dev-skillsを導入して, プロジェクトを初期化して, '/yds-setup', 'set up the harness', 'install dev-skills', 'bootstrap this project'.

4 Updated 3 days ago
ymd38
Data & Documents Listed

yds-data-validation

Inspect a project's data for correctness and produce a read-only validation report — record counts, NULL rates, value distribution, uniqueness, referential integrity, format validity, and sampled evidence rows. Data is read only from the project's own test fixtures/seed data or from an explicitly configured connection; never from a guessed or production source. Triggers on requests like "validate the data", "check data quality", "データ検証", "データの妥当性を確認", "NULL率を調べて", "件数がおかしい", "/yds-data-validation", or when `yds-gh-issue-resolver` verifies a data-related change. Does NOT modify any data or code — read-only inspection only. Produces no JSON.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-gh-issue-drafter

Turn a rough, hand-written intent into a well-scoped GitHub Issue before planning starts. Takes a loose 'what I want' from the user, proposes the missing structure (Done definition, Out of scope, Design constraints), gets the user's approval, and creates the Issue via the gh CLI with a scoped-issue marker so yds-gh-issue-planner can pick it up. This is the human-authored counterpart to yds-report-to-issues (which registers machine-generated findings). Use when the user wants to file a new Issue from a rough idea, is about to write an Issue by hand, or asks to turn a note/thought into an Issue. Triggers include requests like Issueを起こして / Issueを作って / ざっくり書くのでIssueにして, 'draft an issue', 'create an issue for', 'turn this into an issue', 'file an issue'. Does NOT plan or implement — hand off to yds-gh-issue-planner for the response plan, then yds-gh-issue-resolver for implementation.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-gh-issue-planner

Fetch a GitHub Issue by ID using the gh CLI, investigate related code, propose a structured response plan (policy, impact scope, implementation steps), and post the agreed plan as a comment on the issue. Implementation/PR creation is out of scope — use yds-gh-issue-resolver for that. Use when the user provides a GitHub Issue ID or asks to investigate/analyze/plan a GitHub Issue. Triggers include issue IDs like #42 or 'issue 42', requests such as Issueを調査して / Issueの対応方針を立てて, analyze issue #N, plan issue #N, investigate issue, look at issue.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-gh-issue-resolver

Implement and verify a fix for a GitHub Issue whose response plan has already been posted as a comment by yds-gh-issue-planner. Creates a feature branch, applies the agreed plan, runs tests, and opens a Pull Request. Use when the user asks to implement/fix/resolve a planned GitHub Issue. Triggers include requests such as Issueを実装して / Issueを修正して / Issueを対応して, implement issue #N, fix issue #N, resolve issue #N, work on issue #N. Prerequisite: an agreed plan comment must exist on the issue (run yds-gh-issue-planner first if not).

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-progress-dashboard

Generate an interactive HTML dashboard that visualizes improvement progress from yds-software-evaluation and yds-vulnerability-scan reports over time. Reads JSON summary files from docs/evaluation/ and docs/security-audit/, then produces a single self-contained HTML file with charts and trend analysis. Triggers on requests like "generate dashboard", "show progress", "visualize improvements", "/yds-progress-dashboard", or when asked to see quality or security trends.

4 Updated 3 days ago
ymd38
Data & Documents Listed

yds-report-to-issues

Parses reports generated by the yds-software-evaluation or yds-vulnerability-scan skills and interactively registers selected tasks as GitHub Issues using the `gh` CLI. Use when the user wants to convert an evaluation report (docs/evaluation/*.md) or security audit report (docs/security-audit/*.md) into GitHub Issues. Triggers on requests like "create issues from report", "register tasks to GitHub", "convert report to issues", or when pointing at a specific report file.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-software-evaluation

Evaluate code quality across five pillars (Architecture, Reliability, Observability, Security, DX) and produce a 1-10 scorecard with a strategic improvement roadmap. Use when you want a comprehensive quality review of a directory or module. Triggers on requests like "evaluate code quality", "review architecture", "score my code", "code audit", "/yds-software-evaluation", or when asked for a quality assessment of a directory from a CTO or architect perspective.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-spec-doc

Generate or sync a "Living Specification" (docs/spec.md) from source code to eliminate doc-code drift. Use when creating, updating, or reviewing architecture documentation for a directory or module. Triggers on requests like "generate spec", "create spec.md", "sync documentation", "update architecture docs", "/yds-spec-doc", or when asked to document a codebase directory.

4 Updated 3 days ago
ymd38
AI & Automation Listed

yds-vulnerability-scan

Run an offensive security audit (OWASP-based) using Semgrep and produce a read-only vulnerability report. Use before committing code to detect Broken Access Control, Injection (SQL/NoSQL/OS/Template), Frontend Security issues (XSS/CSP/HSTS), SSRF, and hardcoded secrets or PII exposure. Triggers on requests like "security scan", "vulnerability check", "audit security", "find vulnerabilities", "/yds-vulnerability-scan", or when asked for an offensive security review of the codebase. Does NOT modify any code — read-only inspection only.

4 Updated 3 days ago
ymd38

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.