Run any Skill in Manus with one click

$pwd:

estatewise-codex-support

Name: Estatewise Codex Support
Author: hoangsonww

// Extend or audit Codex support in the EstateWise repository. Use when changing .codex config, .codex/rules, .agents/skills, AGENTS.md layering, multi-agent roles, project guidance discovery, or Codex-specific documentation and workflows.

Run Skill in Manus

$ git log --oneline --stat

stars:31

forks:20

updated:February 28, 2026 at 02:15

File Explorer

3 files

SKILL.md

readonly

name	estatewise-codex-support
description	Extend or audit Codex support in the EstateWise repository. Use when changing .codex config, .codex/rules, .agents/skills, AGENTS.md layering, multi-agent roles, project guidance discovery, or Codex-specific documentation and workflows.

EstateWise Codex Support

Use this skill when the task is about Codex itself in this repository rather than product code.

Codex Extension Surfaces In This Repo

Root guidance: AGENTS.md
Nested guidance: package-level AGENTS.md files under repo subdirectories
Codex skills: .agents/skills/
Codex config: .codex/config.toml
Codex multi-agent role configs: .codex/agents/*.toml
Codex rules: .codex/rules/*.rules

Read references/codex-extension-checklist.md when the change spans more than one of these surfaces.

Design Rules

Keep root AGENTS.md repository-wide and stable.
Put subsystem-specific guidance into nested AGENTS.md files close to the owning package.
Keep each skill focused on one job with a sharp description that clearly states when it should and should not trigger.
Use agents/openai.yaml for UI metadata and invocation policy rather than bloating SKILL.md.
Prefer concise metadata and concise skill bodies; move heavier material into references/.
Only add rules for command families that are genuinely risky or repeatedly worth controlling.
Use the OpenAI Developers docs MCP server when verifying current Codex behavior instead of relying on memory.

Skill Creation Checklist

For each new or updated skill:

Keep frontmatter to name and description only.
Make the description explicit about trigger scope and non-goals.
Keep the body imperative and procedural.
Add agents/openai.yaml with:
- interface.display_name
- interface.short_description
- interface.default_prompt
- policy.allow_implicit_invocation
Add references/ only when the extra material is genuinely needed later.
Do not add README or changelog files inside the skill directory.

AGENTS Layering Checklist

When adding nested AGENTS.md files:

Keep them narrower than the root file.
Focus on package ownership, high-risk files, contract edges, and validation commands.
Avoid restating large portions of the root instructions.
Place overrides as close to specialized work as possible.

Rules Checklist

When adding .codex/rules/*.rules:

Use prompt for risky command families with legitimate uses.
Use forbidden only when the alternative is clear and the project truly never wants the command.
Add match and not_match examples to catch mistakes.
Prefer exact prefixes over broad wrappers like bash -lc.

Validation

After editing Codex support files:

Re-read affected AGENTS.md, skill, config, and rules files for conflicts.
Validate TOML/JSON syntax where relevant.
Run git diff --check.
If you added or changed rules, sanity-check the rule shapes and examples carefully.

Documentation

Update these when Codex support changes:

.agents/README.md
.codex/README.md
root README.md only if repository-wide contributor workflow materially changed

related-skills.json

same repository

estatewise-ai-runtime.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Work on EstateWise MCP, agentic-ai, web-grounding, token flows, and A2A integrations. Use when changing tool behavior, orchestration, runtime flags, MCP wrappers, HTTP/A2A endpoints, or AI integration paths.

2026-02-2831

estatewise-contracts.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Audit producer-consumer alignment in EstateWise when REST, tRPC, MCP, gRPC, A2A, or shared payloads may have changed. Use when one package's change could silently break another package, tool, or doc set.

2026-02-2831

estatewise-engineering.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Execute production-safe code changes in the EstateWise monorepo. Use when implementing or fixing behavior in backend, frontend, MCP, agentic-ai, gRPC, deployment-control, tests, or repo docs. Do not use for pure brainstorming, skill installation, or work outside this repository.

2026-02-2831

estatewise-local-stack.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Run or debug the EstateWise local environment. Use when setting up services, choosing the smallest service combination, checking local endpoints, or troubleshooting environment/config issues. Do not use for routine code implementation unless local run/debugging is the main task.

2026-02-2831

estatewise-ops.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Work on EstateWise deployment-control, Docker, Kubernetes, Helm, Terraform, Jenkins, and cloud deployment assets. Use for infrastructure and operational workflow changes, not ordinary application feature work.

2026-02-2831

estatewise-review.md

from "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

Review EstateWise changes for correctness, regressions, security issues, contract mismatches, operational risk, and missing tests. Use for PR review, diff review, bug hunts, and branch-vs-main analysis. Do not use for implementation tasks unless the user asks for fixes after findings are reported.

2026-02-2831

package.json

"author": "hoangsonww"

"repository": "hoangsonww/EstateWise-Chapel-Hill-Chatbot"

View GitHub Repository View Creator Repositories

$ install --global

$ download --local

Run Skill in Manus

$ useful --forSOC

Software DevelopersComputer and Mathematical Occupations15-1252L4

name	estatewise-codex-support
description	Extend or audit Codex support in the EstateWise repository. Use when changing .codex config, .codex/rules, .agents/skills, AGENTS.md layering, multi-agent roles, project guidance discovery, or Codex-specific documentation and workflows.

EstateWise Codex Support

Use this skill when the task is about Codex itself in this repository rather than product code.

Codex Extension Surfaces In This Repo

Root guidance: AGENTS.md
Nested guidance: package-level AGENTS.md files under repo subdirectories
Codex skills: .agents/skills/
Codex config: .codex/config.toml
Codex multi-agent role configs: .codex/agents/*.toml
Codex rules: .codex/rules/*.rules

Read references/codex-extension-checklist.md when the change spans more than one of these surfaces.

Design Rules

Keep root AGENTS.md repository-wide and stable.
Put subsystem-specific guidance into nested AGENTS.md files close to the owning package.
Keep each skill focused on one job with a sharp description that clearly states when it should and should not trigger.
Use agents/openai.yaml for UI metadata and invocation policy rather than bloating SKILL.md.
Prefer concise metadata and concise skill bodies; move heavier material into references/.
Only add rules for command families that are genuinely risky or repeatedly worth controlling.
Use the OpenAI Developers docs MCP server when verifying current Codex behavior instead of relying on memory.

Skill Creation Checklist

For each new or updated skill:

Keep frontmatter to name and description only.
Make the description explicit about trigger scope and non-goals.
Keep the body imperative and procedural.
Add agents/openai.yaml with:
- interface.display_name
- interface.short_description
- interface.default_prompt
- policy.allow_implicit_invocation
Add references/ only when the extra material is genuinely needed later.
Do not add README or changelog files inside the skill directory.

AGENTS Layering Checklist

When adding nested AGENTS.md files:

Keep them narrower than the root file.
Focus on package ownership, high-risk files, contract edges, and validation commands.
Avoid restating large portions of the root instructions.
Place overrides as close to specialized work as possible.

Rules Checklist

When adding .codex/rules/*.rules:

Use prompt for risky command families with legitimate uses.
Use forbidden only when the alternative is clear and the project truly never wants the command.
Add match and not_match examples to catch mistakes.
Prefer exact prefixes over broad wrappers like bash -lc.

Validation

After editing Codex support files:

Re-read affected AGENTS.md, skill, config, and rules files for conflicts.
Validate TOML/JSON syntax where relevant.
Run git diff --check.
If you added or changed rules, sanity-check the rule shapes and examples carefully.

Documentation

Update these when Codex support changes:

.agents/README.md
.codex/README.md
root README.md only if repository-wide contributor workflow materially changed

estatewise-codex-support

EstateWise Codex Support

Codex Extension Surfaces In This Repo

Design Rules

Skill Creation Checklist

AGENTS Layering Checklist

Rules Checklist

Validation

Documentation

More from this repository

More from this repository

EstateWise Codex Support

Codex Extension Surfaces In This Repo

Design Rules

Skill Creation Checklist

AGENTS Layering Checklist

Rules Checklist

Validation

Documentation