skills/remy-changelog/SKILL.md
--- name: remy-changelog description: Generate a temporary change log recording code modifications. Paired with /remy-audit: generate log, rewind AI context (preserving code changes), then run blind audit. argument-hint: "[task_id] [status]" allowed-tools: Bash, Read, Write disable-model-invocation: true --- # Change Log Generation Protocol You must generate a change log file at `.claude/temp_log/_temp_{task_id}_{timestamp}.md`. All content MUST be in the language specified by the `REMY_LANG`
npx skillsauth add till-crazy-tears-us-apart/claude-code-engineering-suite skills/remy-changelogInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You must generate a change log file at .claude/temp_log/_temp_{task_id}_{timestamp}.md.
All content MUST be in the language specified by the REMY_LANG environment variable (zh-CN → Chinese, en → English).
Path Convention: All paths below are relative to
~/.claude/. UseRead("~/.claude/skills/remy-changelog/...")to access them — they are NOT in the project working directory.
| File | Purpose |
| :--- | :--- |
| skills/remy-changelog/output_schema.json | Context dict structure definition. Populate all required fields. |
| skills/remy-changelog/render.py | Template rendering helper. Uses Jinja2 when available, falls back to str formatting. |
| skills/remy-changelog/templates/changelog.md.j2 | Jinja2 template for the change log output. |
render.py attempts import jinja2. If unavailable, all templates are rendered via built-in string formatting (functionally equivalent, but templates are not externally editable in fallback mode). Jinja2 can be installed via install.py (optional step).
git diff --staged --stat (summary) AND !git diff --staged (details)Build a context dict matching output_schema.json. The dict MUST contain:
{
"task_id": "...",
"status": "...",
"date": "YYYY-MM-DD",
"qa_pairs": [
{"question": "...", "answer": "...", "decision": "..."}
],
"file_modifications": [
{
"file_path": "...",
"summary": "...",
"reason": "...",
"role": "...",
"ripple_effects": ["..."],
"logic_explanation": "L42-L58: ..."
}
],
"systemic_impact": {
"data_flow": "...",
"functional_hierarchy": "...",
"framework_impact": "...",
"api_consistency": "...",
"performance": "..."
},
"verification_status": {
"tests_passed": ["..."],
"manual_checks": ["..."]
}
}
Use render.save_changelog(project_root, context) to generate and persist the change log to .claude/temp_log/.
You MUST adhere to the following 4 rules when writing the log:
Subject + Verb + Object). STRICTLY PROHIBIT unnecessary Adjectives, Adverbs, and Metaphors.You MUST read ~/.claude/skills/remy-changelog/output_schema.json to understand the required verification depth.
Do NOT output the JSON block. Populate the context dict to satisfy the schema's rigor.
data-ai
Deep repository analysis with multi-agent parallel perspectives. Requires /init + /remy-index as prerequisites. Produces structured research reports.
tools
Analyze CI/CD failure logs to diagnose build, test, and gate failures. Supports GitHub Actions (gh CLI), local log files, and pasted logs. Produces evidence packets for /remy-patch.
development
Generate persistent unit tests for existing or stub code. Supports post-hoc testing (default) and TDD mode (--tdd). Multi-angle agent analysis at medium/high effort levels.
tools
--- name: remy-secure description: Review branch changes for security vulnerabilities. Multi-stage: regex pre-scan, parallel agents, and false-positive filtering. allowed-tools: Read, Grep, Glob, Bash, AskUserQuestion, Agent argument-hint: "[low|medium|high] [diff_range (optional, e.g. HEAD~3...HEAD)]" disable-model-invocation: true --- # Security Audit Protocol Security-focused review of code changes on the current branch. Identifies exploitable vulnerabilities with high confidence (≥ 8/10),