Agent
End-to-end release preparation: changelog, semver-checks, version bump, documentation verification, multi-crate ordering. Use when preparing a crate or project for release.
2 4mo ago A 38 tokens
researcher
26Agent
Structured research producing actionable findings documents. Supports technical deep-dives, multi-perspective analysis, competitive landscape, and documentation lookup. Use when investigating a technology, evaluating alternatives, or looking up current library APIs.
2 4mo ago A 44 tokens
Agent
Security audit using STRIDE threat analysis. Checks auth, input validation, secrets, cryptography, supply chain, and memory safety. Use when performing a codebase security review or when security concerns are raised.
2 4mo ago A 46 tokens
Agent
Test planning and generation: analyze code, identify coverage gaps, generate test cases with boundary analysis and property-based strategies. Use when a module needs tests or test coverage is insufficient.
2 4mo ago A 39 tokens
SessionStart
29Hook
Runs when a session starts, executing session-start.sh via bash. From jscott3201/ai-agent-skills.
2 4mo ago A
tokens not measured
PreToolUse
30Hook
Runs before the agent uses a tool for Bash tool calls, running an inline shell check (5 commands). From jscott3201/ai-agent-skills.
2 4mo ago C
tokens not measured
TeammateIdle
31Hook
Runs on the TeammateIdle event, running an inline shell check. From jscott3201/ai-agent-skills.
2 4mo ago A
tokens not measured
Notification
32Hook
Runs when the agent sends a notification, running osascript -e 'display notification "Claude Code needs your a. From jscott3201/ai-agent-skills.
2 4mo ago A
tokens not measured
skill-name
33Skill Claude CodeCodex
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.
2 4mo ago A 32 tokens
agent-bridge
34Skill Claude CodeCodex
Multi-agent coordination via SeleneDB context bridge. Check active peers, read shared context, declare work intents, and avoid conflicts when multiple agents work simultaneously.
2 4mo ago A 35 tokens
Skill Claude CodeCodex
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.
2 4mo ago A 39 tokens
Skill Claude CodeCodex
Commit discipline with graph linking. MERGE GitCommit nodes and link to active milestones, findings, and decisions. Verify before committing, never push unless asked.
2 4mo ago A 35 tokens
debate
37Skill Claude CodeCodex
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.
2 4mo ago A 38 tokens
debug
38Skill Claude CodeCodex
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.
2 4mo ago A 46 tokens
Skill Claude CodeCodex
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.
2 4mo ago A 36 tokens
dep-audit
40Skill Claude CodeCodex
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.
2 4mo ago A 37 tokens
Skill Claude CodeCodex
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.
2 4mo ago A 38 tokens
graph-docs
42Skill Claude CodeCodex
Generate documentation by traversing the SeleneDB graph: milestones, design decisions, security concerns, and deferred work. Assembles structured docs from graph annotations and relationships.
2 4mo ago A 38 tokens
Skill Claude CodeCodex
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.
2 4mo ago A 40 tokens
Skill Claude CodeCodex
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.
2 4mo ago A 40 tokens
modularize
45Skill Claude CodeCodex
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).
2 4mo ago A 42 tokens
notes
46Skill Claude CodeCodex
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.
2 4mo ago A 40 tokens
perf-profile
47Skill Claude CodeCodex
Performance investigation: establish baseline, identify hot spots, form hypotheses, optimize, verify no regression. Includes instrumentation guidance. Use when investigating why something is slow.
2 4mo ago A 34 tokens
plan-verify
48Skill Claude CodeCodex
Verify an implementation plan against the actual codebase before starting implementation. Use when about to execute tasks from a plan document.
2 4mo ago A 28 tokens