Skill Claude CodeCodexCursor
Produces a conservative agent work receipt after completed work: finished output, time estimates, review burden, risks, and value judgment. Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants to measure agent productivity honestly after a session.
Skill Claude CodeCodexCursor
Act as an AI operations consultant: interview how a business function's workflows actually run, label each step Human-only / AI-assisted / AI-owned, pick the highest-ROI automation tied to money, margin, or output, warn on AI theater and distraction traps, and recommend one narrow one-week test. Use for automation…
Skill Claude CodeCodexCursor
Run a pre-build blind spot pass before the agent builds anything. Treat the user's prompt as the map and the real project as the territory: classify gaps across known knowns, known unknowns, unknown knowns, and unknown unknowns (with deps, edge cases, and blast radius under unknown unknowns); ask 5 to 10 high-leverage…
Skill Claude CodeCodexCursor
Thorough PR code review before approval.
Skill Claude CodeCodexCursor
Commit directly on main/master when explicitly allowed.
Skill Claude CodeCodexCursor
Commit on the current branch with conventional message.
Skill Claude CodeCodexCursor
Commit on a new branch with conventional message.
Skill Claude CodeCodexCursor
Create a pull request targeting main.
Skill Claude CodeCodexCursor
Systematically debug a reported issue.
Skill Claude CodeCodexCursor
Post-build decision ledger and pride gate: list meaningful agent choices and assumptions after work has landed, with why, alternatives, and confidence; flag debt and edge cases; do not change code until the user says revise now. Use when the user invokes /decision-audit or asks for a post-execution decision audit or…
Skill Claude CodeCodexCursor
Turn a rough task into an agent Goal (outcome, verification with 3 to 5 success criteria, constraints, boundaries, iteration policy, stopping condition, and helper goals when parallel work is implied) so an agent can run with minimal babysitting. Plan-only, no execution in the same turn. Use for Goal, delegate, run…
Skill Claude CodeCodexCursor
Design a reusable agent loop as a graph before running it. Take a TASK and COMPLETION CRITERIA, draw the node graph (input, plan, act, verify, retry or escalate, done), specify context, tools, expected output, and evidence per node, label every transition trigger, set max retries, budget ceilings, and human approval…