菜单
Full autonomous engineering workflow
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Generate and critically evaluate grounded improvement ideas for the current project. Use when asking what to improve, requesting idea generation, exploring surprising improvements, or wanting the AI to proactively suggest strong project directions before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on this project', 'surprise me with improvements', 'what would you change', or any request for AI-generated project improvement suggestions rather than refining the user's own idea.
Create structured plans for any multi-step task -- software features, research workflows, events, study plans, or any goal that benefits from structured breakdown. Also deepen existing plans with interactive review of sub-agent findings. Use for plan creation when the user says 'plan this', 'create a plan', 'write a tech plan', 'plan the implementation', 'how should we build', 'what's the approach for', 'break this down', 'plan a trip', 'create a study plan', or when a brainstorm/requirements document is ready for planning. Use for plan deepening when the user says 'deepen the plan', 'deepen my plan', 'deepening pass', or uses 'deepen' in reference to a plan.
[BETA] Execute work with external delegate support. Same as gh:work but includes experimental Codex delegation mode for token-conserving code implementation.
Execute work efficiently while maintaining quality and finishing features
Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating, replacing, or deleting them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, when pattern docs no longer reflect current code, or when multiple docs seem to cover the same topic and might benefit from consolidation.
Document a recently solved problem to compound your team's knowledge or update CONCEPTS.md, the project's shared domain vocabulary.
基于 SOC 职业分类
| name | lfg |
| description | Full autonomous engineering workflow |
| argument-hint | [feature description] |
| disable-model-invocation | true |
CRITICAL: You MUST execute every step below IN ORDER. Do NOT skip any required step. Do NOT jump ahead to coding or implementation. The plan phase (step 1) MUST be completed and verified BEFORE any work begins. Violating this order produces bad output.
When invoking any skill referenced below, resolve its name against the available-skills list the host platform provides and use that exact entry. Some platforms list skills under a plugin namespace (e.g., galeharness-cli:gh-plan); others list the bare name. Invoking a short-form guess that isn't in the list will fail — always match a listed entry verbatim before calling the Skill/Task tool.
Invoke the gh-plan skill with $ARGUMENTS.
GATE: STOP. If gh:plan reported the task is non-software and cannot be processed in pipeline mode, stop the pipeline and inform the user that LFG requires software tasks. Otherwise, verify that the gh:plan workflow produced a plan file in docs/plans/. If no plan file was created, invoke gh-plan again with $ARGUMENTS. Do NOT proceed to step 2 until a written plan exists. Record the plan file path — it will be passed to gh:review in step 3.
Invoke the gh-work skill.
GATE: STOP. Verify that implementation work was performed - files were created or modified beyond the plan. Do NOT proceed to step 3 if no code changes were made.
Invoke the gh-review skill with mode:autofix plan:<plan-path-from-step-1>.
Pass the plan file path from step 1 so gh:review can verify requirements completeness.
Invoke the test-browser skill with mode:pipeline.
Invoke the git-commit-push-pr skill.
This commits any remaining changes, pushes the branch, and opens a pull request. If a PR already exists (check with gh pr view --json number,url,state 2>/dev/null), skip PR creation but still commit and push any uncommitted changes.
Output <promise>DONE</promise> when complete
Start with step 1 now. Remember: plan FIRST, then work. Never skip the plan.
