finalize-agent-prompt
Finalize prompt file using the role of an AI agent to polish the prompt for the end user.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 4.1w
- Forks
- 5.3k
01 前言 Front Matter
- name
- finalize-agent-prompt
- description
- Finalize prompt file using the role of an AI agent to polish the prompt for the end user.
02 资源文件 84
- 参考文档agents/interface.yaml865 B
- 参考文档COMMERCIAL-LICENSING.md788 B
- 许可证LICENSE33.7 KB
- 许可证LICENSE-SCOPE.md1.2 KB
- 参考文档LOCAL-INSTALL.md804 B
- 参考文档manifests/geo-content.json1.3 KB
- 参考文档manifests/geo-diagnose.json1.3 KB
- 参考文档manifests/geo-discover.json1.1 KB
- 参考文档manifests/geo-measure.json1.2 KB
- 参考文档manifests/geo.json1015 B
- 参考文档manifests/seo.json1.2 KB
- 参考文档PACKAGE-METADATA.json127 B
- 其他pyproject.toml3.5 KB
- 参考文档references/providers/geo-content.md1.5 KB
- 参考文档references/providers/geo-content/content-method.md1.2 KB
- 参考文档references/providers/geo-content/evidence-policy.md1.2 KB
- 参考文档references/providers/geo-content/input-example.json837 B
- 参考文档references/providers/geo-content/modes.md1.4 KB
- 参考文档references/providers/geo-content/output-contract.md629 B
- 参考文档references/providers/geo-diagnose.md1.6 KB
- 参考文档references/providers/geo-diagnose/diagnosis-method.md4.7 KB
- 参考文档references/providers/geo-diagnose/input-example.json577 B
- 参考文档references/providers/geo-discover.md1.5 KB
- 参考文档references/providers/geo-discover/discovery-method.md1.8 KB
- 参考文档references/providers/geo-discover/input-example.json277 B
- 参考文档references/providers/geo-measure.md1.6 KB
- 参考文档references/providers/geo-measure/input-example.json917 B
- 参考文档references/providers/geo-measure/measurement-method.md1.4 KB
- 参考文档references/providers/geo.md1.1 KB
- 参考文档references/providers/geo/RESOLVER.md6.0 KB
- 参考文档references/providers/geo/routing-contract.md1.6 KB
- 参考文档references/providers/seo.md1.7 KB
- 参考文档references/providers/seo/input-example.json272 B
- 参考文档references/providers/seo/seo-method.md1.9 KB
- 参考文档references/RESOLVER.md6.0 KB
- 参考文档references/routing-contract.md1.6 KB
- 参考文档registry/research-evidence.json10.7 KB
- 参考文档registry/skills.schema.json2.7 KB
- 参考文档registry/skills.yaml4.8 KB
- 参考文档schemas/brand-fact-card.schema.json950 B
- 参考文档schemas/content-evidence-units.schema.json2.3 KB
- 参考文档schemas/content-spec.schema.json1.0 KB
- 参考文档schemas/diagnosis-funnel.schema.json2.8 KB
- 参考文档schemas/evidence-ledger.schema.json1.1 KB
- 参考文档schemas/geo-brief.schema.json1.6 KB
- 参考文档schemas/measurement-brief.schema.json4.9 KB
- 参考文档schemas/measurement-report.schema.json6.7 KB
- 参考文档schemas/opportunity-map.schema.json1.2 KB
- 参考文档schemas/quality-report.schema.json842 B
- 参考文档schemas/query-map.schema.json1.6 KB
- 参考文档schemas/research-context.schema.json1.3 KB
- 参考文档schemas/research-evidence-registry.schema.json3.0 KB
- 参考文档schemas/run-manifest.schema.json1.3 KB
- 参考文档schemas/seo-brief.schema.json1.8 KB
- 参考文档schemas/seo-plan.schema.json2.5 KB
- 脚本scripts/run_content.py436 B
- 脚本scripts/run_diagnose.py424 B
- 脚本scripts/run_discover.py438 B
- 脚本scripts/run_measure.py422 B
- 脚本scripts/run_route.py405 B
- 脚本scripts/run_seo.py431 B
- 参考文档src/geo_seo_hub.egg-info/dependency_links.txt1 B
- 参考文档src/geo_seo_hub.egg-info/entry_points.txt53 B
- 其他src/geo_seo_hub.egg-info/PKG-INFO1.9 KB
- 参考文档src/geo_seo_hub.egg-info/requires.txt135 B
- 参考文档src/geo_seo_hub.egg-info/SOURCES.txt2.6 KB
- 参考文档src/geo_seo_hub.egg-info/top_level.txt12 B
- 脚本src/geo_seo_hub/__init__.py246 B
- 脚本src/geo_seo_hub/__main__.py80 B
- 脚本src/geo_seo_hub/artifact_bus.py5.4 KB
- 脚本src/geo_seo_hub/cli.py3.7 KB
- 脚本src/geo_seo_hub/content.py55.6 KB
- 脚本src/geo_seo_hub/diagnose.py61.0 KB
- 脚本src/geo_seo_hub/discover.py10.9 KB
- 脚本src/geo_seo_hub/measure.py14.6 KB
- 脚本src/geo_seo_hub/paths.py599 B
- 脚本src/geo_seo_hub/registry.py4.5 KB
- 脚本src/geo_seo_hub/research.py3.8 KB
- 脚本src/geo_seo_hub/router.py32.3 KB
- 脚本src/geo_seo_hub/seo.py11.4 KB
- 脚本src/geo_seo_hub/validation.py7.1 KB
- 脚本src/geo_seo_hub/version.py676 B
- 参考文档THIRD_PARTY_NOTICES.md3.9 KB
- 其他VERSION6 B
03 SKILL.md 正文
Finalize Agent Prompt
Current Role
You are an AI agent who knows what works best for the prompt files you have seen and the feedback you have received. Apply that experience to refine the current prompt so it aligns with proven best practices.
Requirements
- A prompt file must be provided. If none accompanies the request, ask for the file before proceeding.
- Maintain the prompt’s front matter, encoding, and markdown structure while making improvements.
Goal
- Read the prompt file carefully and refine its structure, wording, and organization to match the successful patterns you have observed.
- Check for spelling, grammar, or clarity issues and correct them without changing the original intent of the instructions.
04 同仓库更多 Skills
supabase-rls-policies
Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.
skill-distribution-audit
Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.
logicapps-custom-code-net10-migration
Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project/package configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.
winmd-api-search
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI
quality-playbook
Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.