Claude skills and agent skills

jaydubya818Skill

how

jaydubya818/MissionControl/skills/how/SKILL.md

Use for runtime, ownership, layering, code-walkthrough, and placement questions.

Often used withpoteto-help·principle-explain-the-number·make-bot-ui

jaydubya818Skill

interrogate

jaydubya818/MissionControl/skills/interrogate/SKILL.md

Use when a change's assumptions, evidence, or design need adversarial review.

Often used withprinciple-explain-the-number·poteto-help·make-bot-ui

jaydubya818Skill

maintain-verification-skill

jaydubya818/MissionControl/skills/maintain-verification-skill/SKILL.md

Use when a project's verification driver or feature map may be stale.

Often used within-your-own-words·principle-explain-the-number·poteto-help

jaydubya818Skill

make-pr-easy-to-review

jaydubya818/MissionControl/skills/make-pr-easy-to-review/SKILL.md

Use when a correct pull request needs clearer history, description, or reviewer guidance.

jaydubya818Skill

mission-control-budget-control

jaydubya818/MissionControl/skills/mission-control-budget-control/SKILL.md

Tracks and enforces agent spend in Mission Control. Use this skill when recording costs via api.agents.recordSpend, declaring budgetDaily and budgetPerRun limits at registration, or reacting to budgetRemaining and budgetExceeded values returned by the heartbeat before spending more money.

jaydubya818Skill

mission-control-delivery

jaydubya818/MissionControl/skills/mission-control-delivery/SKILL.md

Preserve Mission-to-release lineage, evidence, and authority boundaries. Use when Mission Control or a similar software factory governs the work.

jaydubya818Skill

mission-control-heartbeat

jaydubya818/MissionControl/skills/mission-control-heartbeat/SKILL.md

Keeps an agent alive in Mission Control by calling the api.agents.heartbeat mutation every 30-60 seconds. Use this skill when running any agent session: agents that miss heartbeats for 2 minutes get quarantined, and the heartbeat response is how you discover pending tasks, approvals, and budget state.

jaydubya818Skill

mission-control-record-memory

jaydubya818/MissionControl/skills/mission-control-record-memory/SKILL.md

Persists agent knowledge across sessions using the Mission Control agent documents system. Use this skill when depositing session memory before shutting down, keeping a WORKING_MD scratchpad up to date, writing daily notes, or reading back previously stored memories at session start.

jaydubya818Skill

mission-control-register-agent

jaydubya818/MissionControl/skills/mission-control-register-agent/SKILL.md

Registers an agent with Mission Control via the Convex api.agents.register mutation. Use this skill when an agent session starts and the agent must announce itself (name, emoji, role, workspace, task types, budgets) before doing any other work. Re-registering an existing agent updates its heartbeat.

jaydubya818Skill

mission-control-request-approval

jaydubya818/MissionControl/skills/mission-control-request-approval/SKILL.md

Requests human or dual-control approval for risky actions through the Convex api.approvals.request mutation. Use this skill when an action is YELLOW or RED risk tier — YELLOW needs a single approval, RED needs dual control (two decisions), and GREEN/LOW actions auto-approve. Poll status before acting.

jaydubya818Skill

mission-control-run-logging

jaydubya818/MissionControl/skills/mission-control-run-logging/SKILL.md

Records every agent execution turn as a run in Mission Control. Use this skill when starting a run (status RUNNING), completing or failing one (COMPLETED / FAILED), and reporting model, token counts, and cost so the observability and audit trail stays honest across all agent activity.

jaydubya818Skill

mission-control-submit-deliverable

jaydubya818/MissionControl/skills/mission-control-submit-deliverable/SKILL.md

Submits finished work to Mission Control as content drops and posts progress to task threads. Use this skill when a piece of work is complete and needs human review, or when you should communicate progress, questions, or artifacts on a task — don't just complete tasks; submit the actual work.

jaydubya818Skill

mission-control-task-lifecycle

jaydubya818/MissionControl/skills/mission-control-task-lifecycle/SKILL.md

Drives tasks through the Mission Control state machine: find INBOX tasks, assign yourself, and transition through ASSIGNED, IN_PROGRESS, REVIEW, and DONE. Use this skill when claiming, creating, or progressing a task — every status change must go through api.tasks.transition with an idempotency key.

jaydubya818Skill

new-feature

jaydubya818/MissionControl/skills/new-feature/SKILL.md

Create or use a task-owned Git worktree for repository edits. Use for features, fixes, or documentation changes; skip read-only work.

jaydubya818Skill

no-comments

jaydubya818/MissionControl/skills/no-comments/SKILL.md

Use when code comments need structural review, root-cause fixes, and constraint encoding.

Often used withpoteto-help·principle-explain-the-number·make-bot-ui

jaydubya818Skill

plan-arbiter

jaydubya818/MissionControl/skills/plan-arbiter/SKILL.md

Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

jaydubya818Skill

poteto-mode

jaydubya818/MissionControl/skills/poteto-mode/SKILL.md

Use when non-trivial work should follow the smallest rigorous Jstack workflow.

Often used withpoteto-help·setup-pstack·make-bot-ui

jaydubya818Skill

principle-attack-the-premise

jaydubya818/MissionControl/skills/principle-attack-the-premise/SKILL.md

Apply when repeated fixes fail and a shared assumption may be wrong.

Often used withprinciple-explain-the-number·poteto-mode·poteto-help

jaydubya818Skill

principle-boundary-discipline

jaydubya818/MissionControl/skills/principle-boundary-discipline/SKILL.md

Apply when validation or adapters leak from external boundaries into core logic.

Often used withprinciple-explain-the-number·poteto-mode·setup-pstack

jaydubya818Skill

principle-build-the-lever

jaydubya818/MissionControl/skills/principle-build-the-lever/SKILL.md

Apply when a rerunnable script, codemod, generator, or check makes work auditable.

Often used withprinciple-explain-the-number·poteto-mode·setup-pstack