kisune

Rewrite engineer-to-engineer content for leadership audiences — VPs, directors, PMs, release managers. Shapes for the channel: JIRA comment, Slack post, standup note, email, or meeting talking-points. Use after post-mortem or any technical update that needs to flow up the org.

Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Use after a debug session lands a validated fix, before closing the bug.

Outsider-perspective deep review of a plan, PR, design doc, or code change — questions intent first (should this exist?), then traces the actual code path end-to-end to verify the change does what it claims. Use for serious PR reviews, design audits, or second opinions. Lighter pre-commit checks use `review` instead.

Review feature spec files with 3 focused agents — spec quality (business+correctness+ambiguity), completeness (missing scenarios+safety+testability), and buildability (compatibility+blockers+traceability). Sequential by default.

Systematic debugging framework — opens every session by reciting the 4-mantra block (reproduce, trace the fail path, falsify the hypothesis, cross-reference breadcrumbs), then applies multi-layer investigation. Use when diagnosing bugs, flaky tests, unknown failures, or cross-component issues.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Smart git operations — commit messages, branch management, PR creation with summaries. Use for any git workflow.

Use when about to claim work is complete, fixed, passing, or ready to commit/PR — requires running verification commands and reading fresh output before any success claim. Evidence before assertions, always.

25-point code quality checklist covering structure, errors, security, performance, and testing. Use before commits or when reviewing code.

OWASP Top 10 vulnerability detection. Use PROACTIVELY for code handling user input, auth, APIs, payments, or sensitive data.

Create and edit Claude Code skills with TDD methodology. Use when creating or editing skills. Test with subagents before deployment, iterate until bulletproof.

Execute spec-driven implementation — auto-detects Quick (plan.md) or Full (tasks.md) mode and runs step-by-step with verification. Use when implementing a planned feature or running TDD tasks.

Plan new features using spec-driven workflow — auto-picks Quick (single plan.md) or Full (3-file EARS spec) mode. Use when creating features, writing requirements, or designing architecture.

Convert strategy docs to Python (pandas, framework-agnostic) and TradingView Pine Script v5. Use when translating strategies to code for backtesting.

Use when facing 2+ independent problems (different test files, unrelated bugs, separate subsystems) that can be investigated in parallel without shared state — covers the dispatch decision, the actual Claude Code parallelism mechanism, prompt construction, and integration after agents return

Collaborative refinement of rough ideas into clear requirements/designs through systematic questioning. Use when requirements are vague or exploring architectural options.

Strict RED-GREEN-REFACTOR enforcement with no exceptions. Use when implementing features or fixing bugs. No production code without a failing test first.

Chart pattern identification — head and shoulders, double tops, triangles, flags. Documents pattern library with entry/exit criteria.

Technical analysis with indicators (RSI, MACD, MA), support/resistance, multi-timeframe trends, and sentiment. Use when analyzing markets or interpreting charts.

Systematic trading strategy research — edge hypothesis, statistical validation, and strategy documentation (entry, exit, risk management).