agent-builder
Create custom Claude Code sub-agents with specialized expertise and tool access. Use when you need to build reusable agents for specific tasks like code review, debugging, data analysis, or domain-specific workflows.
hooks-manager
Manage Claude Code hooks for workflow automation. Create, configure, test, and debug hooks that execute at various lifecycle points. Supports all hook events (PreToolUse, PostToolUse, SessionStart, etc.) with examples and best practices.
jira
>
skill-builder
Build efficient, scalable Claude Code skills using progressive disclosure and token optimization. Use when creating new skills, optimizing existing skills, or learning skill development patterns. Provides templates, checklists, and working examples.
story-decomposition
Use to break down large stories into optimally-sized stories (1-3 days). Applies PSP measurement discipline.
strangler-pattern-guide
Use as reference guide for strangler pattern implementation. Provides patterns and best practices for legacy migrations.
strangler-pattern
Use when implementing strangler pattern for legacy migrations. Safely migrates controllers with feature flag control.
test-design
Use to design test strategies and create test specifications. Documents testing approaches for stories.
trace-requirements
Use to trace requirements through implementation. Maps acceptance criteria to code and tests.
create-dev-task
Use to generate development task documents for the Dev agent. Creates specifications describing WHAT needs fixing based on validated issues and investigations.
apply-qa-fixes
Use when Dev agent needs to implement fixes based on QA gate results. Reads QA outputs, creates prioritized fix plans, and applies code/test changes to address identified issues.
byos
Create and manage project-level skills shared via git. Skills with prism: metadata are auto-discovered and injected into every PRISM workflow step. Use when teams need project-specific skills available to all agents throughout the workflow.
calibrate-sizing
Use to improve story sizing accuracy by analyzing historical estimation data. Identifies patterns, updates size definitions, and refines PROBE proxy selections.
correct-course
Use when handling sprint changes or scope adjustments. Analyzes change impacts, re-estimates affected stories, and adjusts sprint capacity using PRISM principles.
shared
Shared reference documentation for PRISM skills. Contains common best practices, command patterns, and examples used across multiple skills.
create-epic
Use when creating new Epic documents. Groups related user stories, includes risk analysis, integration points, and story breakdown with PROBE estimation.
create-failing-test
Use to create failing tests before implementing features (TDD approach). Ensures test-first development workflow.
create-next-story
Use to identify and prepare the next logical story based on project progress. Creates comprehensive story files with full technical context.
create-qa-task
Use to create QA task documents. Generates test specifications and validation requirements for QA team.
create-story-tasks
Use to decompose user stories into individual development tasks. Creates task documents that can be assigned, estimated, and tracked.
document-project
Use to analyze and document any project codebase. Creates comprehensive reference documentation for AI-assisted development including architecture and patterns.
execute-checklist
Use to systematically validate documents, stories, or processes against defined checklists. Ensures quality and completeness.
fetch-jira-issue
Use when user mentions a Jira issue key (e.g., PLAT-123) or needs context from Jira. Retrieves and formats issue details for PRISM agent workflows.
file-first
>
init-context
Initialize PRISM .context folder in current project. Use when starting PRISM work in a new project or setting up context management.
initialize-architecture
Use to create complete architecture documentation structure. Creates all required architecture documents from templates.
initialize-project-memory
[DEPRECATED] PRISM-Memory has been archived. This skill is no longer active.
investigate-root-cause
Use for root cause analysis of bugs or issues. Systematically investigates problems to identify underlying causes.
nfr-assess
Use to assess non-functional requirements (security, performance, reliability, maintainability) through E2E integration testing patterns.
prism-loop
Start PRISM TDD workflow loop using Ralph Wiggum pattern. Auto-progresses through Planning, TDD RED (failing tests), TDD GREEN (implementation), and Review phases. Use when user wants to run the core development cycle.
probe-estimation
Use to apply PROBE (PROxy-Based Estimation) method for story sizing. Uses historical data for accurate effort estimation.
qa-gate
Use to create or update quality gate decision files for stories. Provides clear pass/fail decisions with actionable feedback.
resize-story
Use when a story needs to be resized based on new information. Adjusts estimates and splits/combines stories as needed.
review-story
Use to perform comprehensive test architecture review with quality gate decision. Creates both story updates and detailed gate files.
risk-profile
Use to assess and document risk factors for stories or features. Creates risk profiles with mitigation strategies.
sdlc-handoff
Use for SDLC phase transitions. Ensures proper handoff between development phases with documentation.
validate-all
Run all PRISM documentation quality checks (docs, links, portability). Use before committing to .prism, or to check if anything is broken. Invoked by "validate all", "run all checks", "check prism", or "/validate-all".
validate-issue
Use to validate reported issues. Confirms reproducibility and documents validation evidence.
validate-markdown-refs
Validate markdown file references in .claude and .prism directories. Use to find broken links before committing documentation changes.