kashman001
Community@kashman001
kashman001 provides 36 engineering skills for agent-assisted software development: planning, TDD, code review, decision logging, and multi-session handoffs.
Agent Skills by kashman001
Showing 36 vetted skills indexed across 1 GitHub repositories.
kashman001research
Investigates questions against primary sources and writes cited findings to a Markdown file.
kashman001domain-modeling
Build and maintain project domain glossaries and architecture decision records.
kashman001doc-review
Orchestrates multi-perspective review of technical documents using independent reviewer subagents.
kashman001setup-pre-commit
Configures Husky pre-commit hooks with lint-staged, Prettier, typecheck, and tests.
kashman001checkpoint
Reconciles backlog, memory, and docs, then writes a hand-off doc and catch-up prompt at session boundaries.
kashman001wayfinder
Plan large efforts as decision-ticket maps on an issue tracker.
kashman001setup-matt-pocock-skills
Configures a repository's issue tracker, triage labels, and domain doc layout for engineering skills.
kashman001decision-log
Capture decision rationale in commit trailers, project notes, and promoted ADRs.
kashman001writing-for-agents
Guides writing skills, AGENTS.md, and CLAUDE.md documents for agent consumption.
kashman001wait-what
Re-pitches the previous AI response using simpler language and workspace context.
kashman001handoff
Writes a conversation summary into a handoff document for the next agent session.
kashman001design-for-testability
Interrogates software designs with six testability questions before implementation begins.
kashman001diagnosing-bugs
Diagnose hard bugs and performance regressions through a structured feedback-loop workflow.
kashman001git-guardrails-claude-code
Blocks dangerous git commands in Claude Code using a PreToolUse hook script.
kashman001code-review
Reviews a git diff against documented coding standards and the originating spec in parallel sub-agents.
kashman001to-tickets
Breaks plans and specs into tracer-bullet tickets with declared blocking edges published to a tracker.
kashman001ask-matt
Routes a described situation to the matching skill or workflow in this repository.
kashman001wizard
Generate interactive bash wizards that walk humans through manual setup procedures.
kashman001improve-codebase-architecture
Scan a codebase for module deepening opportunities and render findings as a visual HTML report.
kashman001to-questionnaire
Generates a structured Markdown questionnaire for a recipient to answer asynchronously.
kashman001to-spec
Synthesizes the current conversation into a structured spec and publishes it to the project issue tracker.
kashman001codebase-design
Designs deep modules with small interfaces, clean seams, and testable adapters.
kashman001triage
Move issues and external PRs through a triage state machine with agent-ready briefs.
kashman001prototype
Build throwaway HTML demos or UI variants to answer design questions.
Frequently Asked Questions About kashman001
FAQPage SchemaWhat tasks can I accomplish with kashman001's skills?▼
You can plan large work chunks as decision tickets, run test-driven development, review code against repo standards and specs, diagnose bugs and performance regressions, resolve merge conflicts, record architecture decision records, and hand off work between agent sessions.
Who are these skills designed for?▼
Software engineers and technical leads running agent-assisted development sessions. They suit developers managing multi-session projects, maintaining domain models and ADRs, triaging issue trackers, and enforcing commit-time quality gates with Husky, lint-staged, and Prettier.
How do I set up and start using these skills?▼
Run setup-matt-pocock-skills once to configure the repo's issue tracker, triage label vocabulary, and domain doc layout. Then invoke individual skills by trigger phrase, such as 'checkpoint' at session boundaries or 'grill me' to stress-test a plan.
What prerequisites or dependencies do these skills require?▼
Skills operate inside a repository with an issue tracker and docs layout. Some use Bash, Read, Write, Edit, Grep, and Glob permissions; rlm requires a persistent Python REPL with an llm_query function; setup-pre-commit needs Husky, lint-staged, and Prettier.
How do the skills handle long sessions and context limits?▼
The checkpoint, handoff, and session-rollover skills compact work into handoff documents, reconcile backlogs and project memory, and emit bootstrap prompts so a fresh session resumes cleanly. The rlm skill processes oversized files via chunked programmatic sub-queries.