Menu
Use when an approved FSD goal or lightweight issue pointer is ready for implementation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when following the Super Compound BRD -> PRD -> FSD -> GOAL -> IMPLEMENTATION -> VERIFICATION delivery path, artifact traceability, FSD authority, optional ADR handling, zero context bloat issue slicing, or OPEN-* stop conditions.
Use when multi-component work needs cross-component verification of API contracts, data flow, events, auth, config, UI, background jobs, or tests.
Use when /sc-plan needs FSD GOAL-* packets turned into lightweight issue pointers, local Markdown Kanban boards, blocker DAGs, or multi-agent task contracts.
Use when a plan or issue board has 2+ independent execution streams whose time saving exceeds coordination overhead. Dispatches agents in isolated git worktrees only after required delivery gates pass.
Use when an FSD and goal issue board need requirement coverage, goal quality, dependency DAG, sizing, and verification validated before execution.
Use when an approved BRD must be translated into observable product requirements before FSD planning.
| name | executing-plans |
| description | Use when an approved FSD goal or lightweight issue pointer is ready for implementation. |
Announce: "I'm using the executing-plans skill to implement this FSD goal."
Execute approved scope through focused edits, durable progress, and evidence. Sequential execution is the default.
Use only after an approved FSD goal or .scratch/<feature>/issues/ pointer defines authority, acceptance, and dependencies.
Search symbols, paths, tests, and nearby implementations before creating or declaring anything missing. A narrow search miss is not proof of absence.
Stop with OPEN-* when acceptance criteria, FSD authority, TDEC-*, accepted ADR status, or required behavior is missing or contradictory. Stop on unfinished blockers unless the user explicitly reorders work. Never invent schema, APIs, authorization, roles, workflows, state transitions, business rules, or UI behavior outside approved authority.
For UI-integrated work, validate the issue's pinned contract version and
required gate. Before editing an issue-backed goal, require ready-for-agent
and every Blocked by dependency at verified; missing, stale, or unsatisfied
evidence returns to needs-info/blocked with OPEN-*. HARDENING requires
every applicable UI delivery slice verified. A first slice must prove the real
provider with auth/permission, success, and representative failure through
integration-checking. Parallel scale-out is forbidden until that issue is
verified; mock-only evidence never opens the gate.
Before product code, verify placement and dependency direction with architecture-enforcement; implement behavior through test-driven-development.
For one goal at a time:
verification-before-completion before any done claim.Do not opportunistically refactor or overwrite user changes. Route branch, worktree, commit, push, and PR operations through /sc-go and git-workflow-operation; never perform them merely because implementation finished.
| Thought | Required response |
|---|---|
| "The FSD probably means..." | Stop with OPEN-* unless delegation is explicit. |
| "I'll create what search did not find" | Broaden search and verify absence. |
| "Parallel will be faster" | Prove independence and file ownership first. |
| "I'll clean this nearby code" | Record follow-up; stay in goal scope. |
| "The agent/check said done" | Verify independently before transition. |
Inputs come from agentic-delivery, writing-plans, and issue-workflow. Execution uses architecture-enforcement, test-driven-development, systematic-debugging, and state-management; integration-checking, code-review, and verification-before-completion close the loop. All Git delivery uses /sc-go and git-workflow-operation.