ai-agent-skills

Multi-agent coordination via SeleneDB context bridge. Check active peers, read shared context, declare work intents, and avoid conflicts when multiple agents work simultaneously.

Commit discipline with graph linking. MERGE GitCommit nodes and link to active milestones, findings, and decisions. Verify before committing, never push unless asked.

Background annotation discipline. All skills auto-annotate graph nodes with rationale, observations, TODOs, and bookmarks as they work. Captures context that feeds into graph-docs documentation generation.

Track and recall context across sessions. Auto-captures rolling summaries as skills complete. Invoke to review session history, search past work, or see what happened recently.

Language-specific standards plus graph-sourced conventions. Reads Convention nodes from SeleneDB, enforces project rules alongside built-in standards. Promotes recurring violations to new conventions.

Structured multi-perspective debate for evaluating decisions. 3-phase methodology: independent generation, adversarial exchange, synthesis. Use when a decision has multiple valid approaches or high stakes.

Systematic debugging: reproduce, hypothesize, isolate, verify. Includes git bisect for regressions, 5 Whys root cause, and hypothesis tracking. Use when encountering bugs, test failures, or unexpected behavior.

Deep code review after completing a feature or implementation phase. Cross-references all changes against the codebase and fixes all findings. Use after finishing a phase, feature, or significant implementation chunk.

Track deferred work items in the graph. Auto-triggers when work is deferred during planning or implementation. Invoke manually to review and triage the deferred list.

Audit dependencies with graph-persisted findings. Checks health metrics, license compatibility, supply chain signals. Writes dependency and SecurityConcern nodes for cross-session supply chain tracking.

Guide feature development from idea through research, design, and implementation planning. Produces phased plans with dependency graphs and complete code. Use when starting a new feature or major initiative.

Generate documentation by traversing the SeleneDB graph: milestones, design decisions, security concerns, and deferred work. Assembles structured docs from graph annotations and relationships.

Structured triage for production issues. Gather symptoms, correlate with recent changes, assess blast radius, guide mitigation, and produce a postmortem. Use when something goes wrong in production.

Track development milestones that group commits, documents, and decisions into named initiatives. Auto-suggests linking commits to active milestones. Use to create, review, or close milestones.

Analyze and restructure codebases into well-organized modules. Identifies splitting candidates, complexity hotspots, and circular dependencies. Scales from conservative (extract functions) to aggressive (full reorg).

Performance investigation: establish baseline, identify hot spots, form hypotheses, optimize, verify no regression. Includes instrumentation guidance. Use when investigating why something is slow.

Verify an implementation plan against the actual codebase before starting implementation. Use when about to execute tasks from a plan document.

Guided onboarding for existing projects. Assesses project state, identifies gaps, and walks through setup one step at a time. Use when first using justin-tools on a new or existing repo.

Structured refactoring: identify smell, plan transformation, execute with verification at each step, confirm no behavioral changes. Includes a Rust-specific refactoring catalog.

Release readiness: changelog generation, semver-checks, version bump suggestion, doc verification, multi-crate ordering. Use when preparing a crate or project for release.

Verify that every requirement has corresponding code and tests. Maps requirements to implementation, identifies untested or unimplemented requirements, and flags code without a traced requirement.

Structured research producing actionable findings documents. Supports technical deep-dives, multi-perspective analysis, competitive landscape, and documentation lookup. Use when investigating before building.

Security auditing with graph-persisted concerns. STRIDE-based threat analysis writing SecurityConcern nodes linked to dependencies, crates, and modules. Enables supply chain and security posture queries.

Find the right skill for a task. Routes via graph queries on skill and workflow_category nodes. Use when unsure which skill applies or to recommend skills the user may not know about.

Test planning and generation: analyze code, identify untested paths, generate test cases with boundary analysis. Includes coverage gap detection and property-based testing guidance.

What this skill does and when to use it. Front-load the key use case. Claude uses this to decide when to apply the skill automatically.