Clear Eyed Reading
Quickly understand and demystify a research paper, review, technical blog, commentary, or other article. Independently reconstruct what the work does, identify its genuine contribution and capability sources, explain how its reported result came about or whether its conclusion is warranted, and give a practical first-screen judgment in plain language. Available only when the user explicitly invok…
Teamwork Review
Use when the user asks to review/check a plan, artifact, diff, implementation, research output, completion claim, strict quality, deslop pass, PR walkthrough, or acceptance evidence.
Teamwork Update
Use when updating Teamwork package version, refreshing installed skills/agents/global policy, checking install freshness, or release metadata.
Grill Me
Use when the user explicitly asks to be grilled, requests question-first plan or design stress-testing, or continues an active grill session; ask zero to three material user-owned decision questions and never manufacture implementation trivia.
Teamwork Init
Use when setting up, auditing, or slimming project agent instructions; integrating Teamwork artifacts, MCP/CodeGraph policy, AGENTS/CODEX/CURSOR/CLAUDE rules, install readiness, or reusable workflow-rule migration.
Teamwork Execute
Use when an accepted plan, checklist, approved scope, or known root-cause fix should be implemented, continued, resumed, or verified with focused action.
Teamwork Goal
Use when the user asks to keep going, run until it passes, fix until green, iterate until done, converge on a verifiable target, or work within an explicit budget.
Clear Eyed Deep Reading
Perform a complete, clear-eyed deep reading of a research paper, review, technical blog, commentary, or other long-form technical work. Independently reconstruct the problem and mechanism, trace capability and knowledge sources, determine the genuine contribution, explain how the reported result came about or whether the conclusion is warranted, and expand the consequential figures, equations, im…
Using Teamwork
Use when Teamwork is explicitly requested, work must cross Teamwork stages, or the correct next stage is unclear; route to native/research/debug/plan/execute/review/goal/init/update.
Teamwork Plan
Use when the user asks for plan/design or a non-trivial research, engineering, or implementation change needs scope, requirements, protected boundaries, verification, dispatch, memory, or acceptance before action.
Teamwork Research
Use when the next safe step is to learn before acting: source-of-truth lookup, current API behavior, repro-surface framing, option comparison, stale-assumption refresh, or risk/evidence gathering before planning/debugging.
Teamwork Debug
Use when the user reports a failure, flaky test, CI error, runtime log, crash, UI symptom, regression, or suspected bug where a repro, hypotheses, instrumentation, browser/CI evidence, or human observation must decide root cause before a fix is safe.