Skill Creator
krzemienski
56 published skills · 64 GitHub stars across the catalog. View on GitHub ↗
goal-management
FLEXIBLE skill for North Star goal tracking with Serena MCP persistence.Parses vague goals into measurable criteria, tracks progress percentages,maintains goal history, integrates with wave execution. Prevents goal driftand context loss through structured storage. Essential for multi-session projects.
honest-reflections
Systematic gap analysis for claimed vs actual work completion. Uses 100+ sequential thoughtsto identify assumptions, partial completions, missing components, and rationalization patterns.Validates completion claims against original plans, detects scope deviations, reveals quality gaps.Essential for self-assessment before declaring work complete. Use when: claiming completion,final reviews, quality audits, detecting rationalization patterns in own work.
intelligent-do
Context-aware task execution with Serena MCP backend. First time: Explores project, saves to Serena,runs spec if complex, executes waves. Returning: Loads from Serena (<1s), detects changes, executeswith cached context. Intelligently decides when to research, when to spec, when to prime. One catch-allintelligent execution command. Use when: User wants task executed in any project (new or existing).
mcp-discovery
Intelligent MCP server recommendation engine based on quantitative domain analysis. Maps projectdomains (Frontend %, Backend %, Database %, etc.) to appropriate MCP servers using tier-basedpriority system (Mandatory > Primary > Secondary > Optional). Performs health checking, generatessetup instructions, provides fallback chains. Use when: analyzing project needs, configuring MCPs,checking MCP health, recommending alternatives.
memory-coordination
Coordinates Serena MCP knowledge graph operations for Shannon Framework. Enforces standardizedentity naming (shannon/* namespace), relation creation patterns, search protocols, and observationmanagement. Prevents orphaned entities, naming chaos, and broken context lineage. Use when: storingspecs/waves/goals/checkpoints, querying Shannon history, managing knowledge graph structure,ensuring cross-wave context preservation.
mutation-testing
Verify test quality by injecting mutations into code and measuring catch rate. Calculate mutation score (0.00-1.00) showing test effectiveness. Auto-generate missing tests to improve coverage. Integrate with Serena for continuous mutation tracking. Use when: improving test quality, validating test effectiveness, generating missing test cases, measuring code coverage gaps.
performance-regression-detection
Track performance benchmarks and detect regressions exceeding 10% threshold. Analyze historical trends and alert on degradation. Calculate regression score (0.00-1.00) for performance health. Integrate with Serena for continuous monitoring. Use when: monitoring performance, detecting regressions, analyzing performance trends, optimizing slow components, validating performance fixes.
phase-planning
Generate 5-phase implementation plan with validation gates and resource allocation. Adaptsphase count and timeline based on complexity score. Includes validation gates between phases.Use when: planning implementation, need structured timeline, want validation checkpoints.
project-indexing
Generates SHANNON_INDEX for 94% token reduction (58K → 3K tokens). Compresses large codebasesinto structured summaries with Quick Stats, Tech Stack, Core Modules, Dependencies, Recent Changes,and Key Patterns. Enables fast agent onboarding, efficient multi-agent coordination, and instantcontext switching. Use when: starting project analysis, onboarding new agents, coordinating waves,switching between codebases, or when context window efficiency is critical.
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack with quantitative tracking, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
security-pattern-detection
Detect OWASP Top 10 vulnerabilities via static analysis. Calculate security score (0.00-1.00) for code quality. Auto-generate remediation suggestions with implementation examples. Integrate with Serena for vulnerability tracking and SLA compliance. Use when: securing code, detecting vulnerabilities, improving security posture, validating fixes, enforcing security standards.
shannon-analysis
FLEXIBLE skill orchestrating comprehensive analysis workflows. Adapts to analysis type(codebase, architecture, technical debt, complexity) and automatically invokes appropriatesub-skills (spec-analysis, project-indexing, confidence-check). Applies Shannon patterns(8D framework, waves, NO MOCKS) with Serena historical context. Produces quantitative,actionable results with structured outputs and MCP recommendations.
sitrep-reporting
Military-style SITuation REPort protocol for multi-agent coordination. Enforces structured statusreporting with 🟢🟡🔴 codes, quantitative progress (0-100%), blockers, dependencies, ETAs, andauthorization codes for secure handoffs. Prevents communication failures, lost context, and delayedblocker reporting. Use when: coordinating multiple agents, wave execution, reporting progress,requesting status updates, handing off deliverables.
skill-discovery
Use when needing to discover available skills across project/user directories - automatically scansfor SKILL.md files, parses YAML frontmatter, extracts metadata (name, description, type, MCP requirements),and builds comprehensive skill catalog. Enables intelligent skill selection and auto-invocation.NO competitor has automated skill discovery system.
spec-analysis
8-dimensional quantitative complexity analysis with domain detection. Analyzes specificationsacross structural, cognitive, coordination, temporal, technical, scale, uncertainty, dependencydimensions producing 0.0-1.0 scores. Detects domains (Frontend, Backend, Database, etc.) withpercentages. Use when: analyzing specifications, starting projects, planning implementations,assessing complexity quantitatively.
subagent-driven-development
Use for implementation plans - dispatches fresh subagent per task with quality scoring (0.00-1.00), code review gates, Serena pattern learning, and MCP tracking
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation with quantitative tracking, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
task-automation
Orchestrates Shannon's complete workflow: prime → spec → wave.Automates session preparation, specification analysis, and wave executionin one command. Interactive by default with validation gates, --auto forfull automation, --plan-only for estimation. Use when: user providescomplete task specification and wants end-to-end Shannon workflow.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first using REAL systems (NO MOCKS), watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first and real system integration
testing-anti-patterns
Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior, production pollution with test-only methods, and mocking without understanding dependencies, with quantitative anti-pattern detection scoring
testing-skills-with-subagents
Use before skill deployment to verify pressure resistance via TDD RED-GREEN-REFACTOR cycle with Serena metrics tracking - measures compliance score (0.00-1.00) across pressure scenarios
using-shannon
Use at session start - establishes Shannon Framework workflows including mandatory 8D analysisbefore implementation, NO MOCKS testing enforcement, wave-based execution for complexity >=0.50,and automatic Serena MCP checkpointing. Prevents under-estimation and ensures quantitative rigor.Trigger keywords: shannon, specification, complexity, wave, checkpoint, functional testing.
verification-before-completion
Use when about to claim work is complete, fixed, passing, or successful, before committing or creating PRs - requires running verification commands and confirming output before making ANY success claims; evidence before assertions always, no exceptions
wave-orchestration
True parallel sub-agent coordination with wave-based execution. Analyzes phase dependencies,groups independent phases into waves for parallel execution, allocates agents based on complexityscore. Proven 3.5x speedup for complexity >=0.50. Use when: executing complex projects,need parallel coordination, want to achieve 2-4x speedup.