Skill Creator

rjmurillo

33 published skills · 110 GitHub stars across the catalog. View on GitHub ↗

prompt-engineer

rjmurillo's avatarfrom rjmurillo★ 4

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

doc-sync

rjmurillo's avatarfrom rjmurillo★ 4

Synchronizes CLAUDE.md navigation indexes and README.md architecture docs across a repository. Use when asked to "sync docs", "update CLAUDE.md files", "ensure documentation is in sync", "audit documentation", or when documentation maintenance is needed after code changes.

metrics

rjmurillo's avatarfrom rjmurillo★ 4

Collect and report metrics on agent usage from git history implementing the 8 key metrics defined in agent-metrics.md for measuring agent system health effectiveness and adoption.

skillforge

rjmurillo's avatarfrom rjmurillo★ 4

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.

security-detection

rjmurillo's avatarfrom rjmurillo★ 4

Detect infrastructure and security-critical file changes to trigger security agent review recommendations ensuring proper security oversight for sensitive modifications.

session-qa-eligibility

rjmurillo's avatarfrom rjmurillo★ 4

Check investigation session QA skip eligibility per ADR-034. Validates if staged files qualify for investigation-only exemption by checking against allowed paths (.agents/sessions/, .agents/analysis/, .serena/memories/, etc).

session-init

rjmurillo's avatarfrom rjmurillo★ 4

Create protocol-compliant session logs with verification-based enforcement. Prevents recurring CI validation failures by reading canonical template from SESSION-PROTOCOL.md and validating immediately. Use when starting any new session.

slashcommandcreator

rjmurillo's avatarfrom rjmurillo★ 4

Autonomous meta-skill for creating high-quality custom slash commands using 5-phase workflow with multi-agent validation and quality gates. Use when user requests new slash command, reusable prompt automation, or wants to convert repetitive workflows into documented commands.

session-migration

rjmurillo's avatarfrom rjmurillo★ 4

Migrate session logs from markdown to JSON format. Use when PRs contain markdown session logs that need conversion to the new JSON schema, or when batch-migrating historical sessions.

github-url-intercept

rjmurillo's avatarfrom rjmurillo★ 4

BLOCKING INTERCEPT: When ANY github.com URL appears in user input, STOP and use this skill. Never fetch GitHub HTML pages directly - they are 5-10MB and will exhaust your context window. This skill routes URLs to efficient API calls (1-50KB). Triggers on: pull/, issues/, blob/, tree/, commit/, compare/, discussions/.

session

rjmurillo's avatarfrom rjmurillo★ 4

Session management and protocol compliance skills. Use Test-InvestigationEligibility to check if staged files qualify for investigation-only QA skip per ADR-034 before committing with 'SKIPPED investigation-only' verdict.

adr-review

rjmurillo's avatarfrom rjmurillo★ 3

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.

analyze

rjmurillo's avatarfrom rjmurillo★ 3

Invoke IMMEDIATELY via python script when user requests codebase analysis, architecture review, security assessment, or quality evaluation. Do NOT explore first - the script orchestrates exploration.

decision-critic

rjmurillo's avatarfrom rjmurillo★ 3

(user)

fix-markdown-fences

rjmurillo's avatarfrom rjmurillo★ 3

Repair malformed markdown code fence closings. Use when markdown files have closing fences with language identifiers (```text instead of ```) or when generating markdown with code blocks to ensure proper fence closure.

github

rjmurillo's avatarfrom rjmurillo★ 3

GitHub CLI operations for PRs, Issues, Labels, Milestones, Comments, and Reactions.Unified skill with shared helpers for DRY code.Use when Claude needs to: (1) Get PR context, diff, or changed files, (2) Reply toPR review comments preserving threads, (3) Post idempotent issue comments, (4) Applyor create labels, (5) Assign milestones, (6) Add reactions to comments, (7) Close ormerge PRs, (8) Resolve review threads, (9) Synthesize context for Copilot assignment,(10) Create new issues or PRs with validation.Do NOT use for: raw git operations, GitHub Actions workflow editing, repository settings.

incoherence

rjmurillo's avatarfrom rjmurillo★ 3

Detect and resolve incoherence in documentation, code, specs vs implementation. Includes reconciliation phase for applying user-provided resolutions.

merge-resolver

rjmurillo's avatarfrom rjmurillo★ 3

Resolve merge conflicts intelligently using git history. Fetches PR context, identifies conflicted files, uses git blame and commit history to infer developer intent. Applies resolution strategies based on change type (bugfix, feature, refactor). Auto-resolves session artifacts and templates. Validates session protocol before push.

planner

rjmurillo's avatarfrom rjmurillo★ 3

Interactive planning and execution for complex tasks. Use when breaking down multi-step projects (planning) or executing approved plans through delegation (execution). Planning creates milestones with specifications; execution delegates to specialized agents.

programming-advisor

rjmurillo's avatarfrom rjmurillo★ 3

Anti-reinventing-the-wheel advisor that helps users evaluate build vs buy decisions before vibe coding. Use when users describe something they want to build, create, or develop - especially features, tools, apps, scripts, or systems. Searches for existing solutions, estimates vibe coding costs (tokens, time, complexity), and presents comparison tables to enable informed decisions. Includes total cost of ownership analysis comparing Year 1 vs Year 3 costs for SaaS vs DIY. When user accepts a recommendation, provides complete integration planning with install commands, starter code, and project-specific guidance. Triggers on: "I want to build...", "Help me create...", "Can you code...", "I need a [tool/app/script]...", project planning, feature requests, or any coding task that might have existing solutions.

prompt-optimizer

rjmurillo's avatarfrom rjmurillo★ 3

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

session-log-fixer

rjmurillo's avatarfrom rjmurillo★ 3

Fix session protocol validation failures in GitHub Actions. Use when a PR fails with "Session protocol validation failed", "MUST requirement(s) not met", "NON_COMPLIANT" verdict, or "Aggregate Results" job failure in the Session Protocol Validation workflow. With deterministic validation, failures show exact missing requirements directly in Job Summary - no artifact downloads needed.

steering-matcher

rjmurillo's avatarfrom rjmurillo★ 3

Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator needs to inject context-aware guidance based on files being modified.

serena-code-architecture

rjmurillo's avatarfrom rjmurillo★ 3

Architectural analysis workflow using Serena symbols and Forgetful memory. Use when analyzing project structure, documenting architecture, creating component entities, or building knowledge graphs from code.