till-crazy-tears-us-apart
34 verified skills844 total stars
remy-index
Scan source files (Python, C/C++, TypeScript) and generate semantic logic index via LLM. Index is injected into CLAUDE.md and used by hooks/skills for dependency analysis. Run after repo init or major changes.
development27
remy-testgen
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.
development27
remy-insight
Deep repository analysis with multi-agent parallel perspectives. Requires /init + /remy-index as prerequisites. Produces structured research reports.
data-ai27
skills/remy-secure
--- 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),
tools27
skills/remy-reposcout
--- name: remy-reposcout description: Analyze a GitHub repository in two stages: metadata assessment via GH CLI, then sandboxed deep inspection upon confirmation. disable-model-invocation: true allowed-tools: Bash, Glob, Grep, Read --- # Repository Audit Skill This skill allows you to safely inspect GitHub repositories without polluting your main workspace. It operates in two stages to prevent unnecessary cloning of massive repositories. **Requirements**: - `git` - `gh` (GitHub CLI) - Must be
tools27
skills/remy-audit
--- name: remy-audit description: Verify code changes via Intent/Log/Code triangulation. Independent blind audit without prior session context. Paired with /remy-changelog: generate log, rewind context, then audit. allowed-tools: Read, Grep, Glob, Bash argument-hint: "[log_file_path] [task_packet_file (optional)] [git_diff_range (optional)]" disable-model-invocation: true --- # Auditor Protocol (Blind Verification) You are an **Adversarial Code Auditor**. You have just been spawned and have ZE
tools27
remy-inspect
Discover and run tests after code modification. Supports multi-angle defect prediction and coverage analysis. Recommended after large-scale edits or accumulated working tree changes.
development27
remy-ci
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.
tools27
code-modification
Use this skill when modifying, refactoring, or optimizing code. Enforces strict engineering standards and project-specific constraints.
development26
skills/remy-changelog
--- 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`
tools26
remy-lookup
Display the current logic index tree (.claude/logic_tree.md) without regenerating.
tools26
remy-patch
Apply code modifications under engineering constraints. Accepts plan packets from /remy-plan as argument, or use standalone with a modification request.
development26
remy-milestone
Record technical decisions and progress as a persistent milestone report. Use before /compact or at task completion.
testing26
remy-debug
Diagnose bugs via hypothesis loop with circuit breaker. Diagnosis only — produces evidence packets for /remy-patch without modifying code.
development26
remy-tree
Refresh the project directory tree snapshot (.claude/project_tree.md). Use after file operations that alter structure.
tools26
remy-plan
Audit architecture for risks, side effects, and ambiguities before writing code. Produces evidence packets for /remy-patch. Recommended for large or complex tasks.
development26
update-logic-index
Update the semantic logic index (.claude/logic_tree.md) using LLM AST analysis.
data-ai26
security-audit
Security-focused code review of branch changes. Identifies high-confidence vulnerabilities via regex pre-scan, parallel category agents, and independent false-positive filtering.
development26
auditor
Independent code auditor performing triangulation verification (Intent/Log/Code) without prior context.
development26
deep-plan
Use when an implementation plan is proposed but requires a deep architectural audit for risks, side effects, and ambiguities before writing any code.
development26
post-verify
Use after code modification to discover/create tests, run them, assess coverage, and fix failures. Supports multi-angle defect prediction and semantic audit via parallel agents.
development26
milestone
Use BEFORE running /compact or when a significant task milestone is reached to document technical decisions, experiments, and progress.
testing25
read-logic-index
Read and display the current logic index tree from .claude/logic_tree.md.
tools25
log-change
Generate a standardized change log for context compression.
tools25
skills/repo-audit
--- name: repo-audit description: Analyzes a GitHub repository. Stage 1: Fetches metadata (README, Size) using GH CLI to assess complexity. Stage 2: Clones to a temporary sandbox for deep inspection upon user confirmation. disable-model-invocation: true allowed-tools: Bash, Glob, Grep, Read --- # Repository Audit Skill This skill allows you to safely inspect GitHub repositories without polluting your main workspace. It operates in two stages to prevent unnecessary cloning of massive repositori
tools25
update-tree
Manually update the project tree snapshot (.claude/project_tree.md).
tools25
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
development25
git-workflow
Use this skill for all version control tasks, including committing, branching, pushing, and reviewing history.
tools20
doc-updater
Update core documentation based on code changes referenced in CLAUDE.md
development20
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
development20
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
testing20
file-ops
Use this skill for any file system operations, including reading, writing, editing, moving, or deleting files. Enforces strict safety protocols.
tools20
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
development20
tool-guide
Use this skill to determine which MCP tool or service to use for a specific task (search, documentation, browser automation).
tools20