Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
原文语言:英语
菜单
这个仓库中的 skills
SkillsMP 已收集 zaxbysauce/opencode-swarm 中的 120 个 Skill。打开任一 Skill 可查看来源和详情。
zaxbysauce/opencode-swarm已展示 40 / 120 个已收集 Skill。
Apply before starting work on an existing branch. Checks for parallel work by other agents or developers that may supersede or conflict with your planned changes. Prevents wasted effort on stale branches.
原文语言:英语
End-to-end CI monitor that takes an already-human-reviewed PR, exhaustively researches every CI failure, fixes it end-to-end, iterates until all required checks are green (max 5 fix cycles), then merges. Use only after human review is complete and the PR is…
原文语言:英语
Full execution protocol for MODE: SPECIFY -- spec creation, codebase reality checks, SME input, QA gate persistence, and optional council spec review.
原文语言:英语
Protocol for splitting test files that approach or exceed the FR-006 500-line limit (enforced in CI by scripts/check-test-file-cap.ts as a diff-scoped ratchet). Covers describe-block extraction, shared helper management, pure-function extraction, mock…
原文语言:英语
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a…
原文语言:英语
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback.…
原文语言:英语
Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.
原文语言:英语
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
原文语言:英语
Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
原文语言:英语
Codex adapter for closing known PR feedback in any repository. Use when asked to address pasted review feedback, GitHub review comments or threads, requested changes, CI/check failures, merge conflicts, stale PR branches, or follow-up work that must verify…
原文语言:英语
Claude Code adapter for closing known PR feedback. Use when addressing pasted review feedback, GitHub review comments or threads, requested changes, CI/check failures, merge conflicts, stale PR branches, or PR follow-up work that must verify every claim…
原文语言:英语
Add path-type assertions or realpath/resolve calls in path-joining utility functions
原文语言:英语
check skill provenance stamps before archiving knowledge entries
原文语言:英语
ci-failure-batching
原文语言:英语
confirm failures are causally linked to the task before reporting rejection
原文语言:英语
ensure all tests pass after code changes
原文语言:英语
grep for 'mock.module' across the entire test file and confirm every occurrence uses spread-real-exports before marking the file as converted
原文语言:英语
include test files that assert on behavior being changed in declared scope
原文语言:英语
mock.module
原文语言:英语
mock-to-internals-migration
原文语言:英语
opt-in-tool-registration
原文语言:英语
phase_complete
原文语言:英语
Legacy compatibility shim — use swarm-pr-feedback instead
原文语言:无法判定
propagation test
原文语言:英语
restore _internals seams in finally blocks after each test
原文语言:英语
run failing tests immediately after test_gate failure
原文语言:英语
run relevant tests after adding error-handling wrappers
原文语言:英语
run relevant tests after logic changes
原文语言:英语
run test suite after registration changes
原文语言:英语
run tests on the unmodified codebase before starting to establish a failure baseline
原文语言:英语
spread real module exports as base of every mock.module return object
原文语言:英语
update or delete tests that assert intentionally removed behavior
原文语言:英语
verify skill mirror pairs exist in both .opencode/skills/ and .claude/skills/
原文语言:英语
widen return type
原文语言:英语
Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write scoped subagent prompts with bounded structured returns, and…
原文语言:英语
Cross-agent swarm-mode behavior model — a higher-rigor workflow using parallel investigation, independent reviewer validation, and critic challenge, plus the mandatory implementation closeout gate. Runtime adapters (.claude, .agents) add execution-specific…
原文语言:英语
Codex adapter for opencode-swarm engineering invariants. Use before modifying plugin initialization, subprocesses, runtime portability, .swarm containment, plan durability, test_runner behavior, test-writing patterns, session/global state, guardrails/retry…
原文语言:英语
Mandatory Codex/Copilot publication adapter for opencode-swarm. Use for every GitHub issue assignment that results in code changes, commits, pushes, draft PRs, PR body edits, PR readying, release notes, or CI closeout. Must be loaded before `git push`, `gh pr…
原文语言:英语
Codex adapter for end-to-end CI monitoring of an already-reviewed PR in opencode-swarm. Use when the user wants the swarm to monitor a reviewed-and-approved PR's CI, research every failure exhaustively, fix end-to-end, iterate until green (max 5 cycles), then…
原文语言:英语
Codex adapter for complex implementation work using the canonical opencode-swarm implementation workflow. Use for multi-file features, bug fixes, refactors, risky code changes, or tasks that benefit from exploration, scoped planning, implementation, review,…
原文语言:英语