Communitygithub.com

grahama1970/plugin-creator

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

plugin-creator 是什麼?

plugin-creator is a Claude Code agent skill that create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugin during development with the CLI-driven cachebuster and reinstall flow.

相容平台Claude CodeCodex CLI~Cursor
npx skills add https://github.com/grahama1970/agent-skills/tree/main/skills/.system/plugin-creator

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Plugin Creator

Quick Start

  1. Run the scaffold script:
# Plugin names are normalized to lower-case hyphen-case and must be <= 64 chars.
# The generated folder and plugin.json name are always the same.
# Run from the skill root (the directory containing this `SKILL.md`).
# By default creates in `~/plugins/<plugin-name>`.
python3 scripts/create_basic_plugin.py <plugin-name>
  1. Edit <plugin-path>/.codex-plugin/plugin.json when the request gives specific metadata. The scaffold starts with valid defaults and must not contain [TODO: ...] placeholders.

  2. Generate or update the personal marketplace entry when the plugin should appear in Codex UI ordering:

# Personal marketplace entries default to `~/.agents/plugins/marketplace.json`.
python3 scripts/create_basic_plugin.py my-plugin --with-marketplace

Only specify --marketplace-name <name> when the default personal marketplace name is already taken or installed and you need to seed a different new marketplace file:

python3 scripts/create_basic_plugin.py my-plugin \
  --with-marketplace \
  --marketplace-name team-local

Only use a repo/team marketplace when the user specifically asks for that destination:

python3 scripts/create_basic_plugin.py my-plugin \
  --path <repo-root>/plugins \
  --marketplace-path <repo-root>/.agents/plugins/marketplace.json \
  --with-marketplace

When the user specifies a marketplace path, make sure that marketplace is actually installed before telling the user to reinstall from it. The default personal marketplace file at ~/.agents/plugins/marketplace.json is discovered implicitly, but other marketplace paths are not. On Windows, use the equivalent path under the user profile.

  1. Generate/adjust optional companion folders as needed:
python3 scripts/create_basic_plugin.py my-plugin \
  --path <parent-plugin-directory> \
  --marketplace-path <marketplace-json-path> \
  --with-skills --with-hooks --with-scripts --with-assets --with-mcp --with-apps --with-marketplace

<parent-plugin-directory> is the directory where the plugin folder <plugin-name> will be created (for example ~/plugins).

  1. Before handing back a generated plugin, run:
python3 scripts/validate_plugin.py <plugin-path>

For updates to an existing local plugin during development, keep the scaffold flow as-is and use the reference instead of hand-editing marketplace files:

python3 scripts/update_plugin_cachebuster.py <plugin-path>

Prefer the helper default cachebuster unless the user explicitly asks for a specific override. See references/installing-and-updating.md for the expected cachebuster and reinstall flow while iterating on an existing local plugin.

What this skill creates

  • Default marketplace-backed scaffolds use the personal marketplace file at ~/.agents/plugins/marketplace.json, with plugins generally being stored in ~/plugins/<plugin-name>/.
  • Creates plugin root at /<parent-plugin-directory>/<plugin-name>/.
  • Always creates /<parent-plugin-directory>/<plugin-name>/.codex-plugin/plugin.json.
  • Fills the manifest with the validated schema shape that the ingestion path accepts.
  • Creates or updates ~/.agents/plugins/marketplace.json when --with-marketplace is set.
    • If the marketplace file does not exist yet, seed a personal marketplace root before adding the first plugin entry.
  • <plugin-name> is normalized using skill-creator naming rules:
    • My Pluginmy-plugin
    • My--Pluginmy-plugin
    • underscores, spaces, and punctuation are converted to -
    • result is lower-case hyphen-delimited with consecutive hyphens collapsed
  • Supports optional creation of:
    • skills/
    • hooks/
    • scripts/
    • assets/
    • .mcp.json
    • .app.json

Marketplace workflow

  • Personal-marketplace creation defaults to ~/.agents/plugins/marketplace.json. Here, "personal marketplace" means the marketplace whose file is at that path.
  • Repo/team marketplace creation is opt-in through both --path and --marketplace-path, only when the user specifically requests it.
  • --marketplace-name is an exception path. Use it only when the default personal marketplace name is already taken and you need to seed a different new marketplace file.
  • Do not use --marketplace-name to rename an existing marketplace file in place. If the file already exists, its top-level name must already match.
  • If the user specifies a different marketplace path, treat that marketplace as needing explicit installation via codex plugin marketplace add.
  • Prefer scripts/read_marketplace_name.py when you need the marketplace name from any marketplace.json file. With no argument it reads the default personal marketplace; with an explicit path it works for repo/team marketplaces too.
  • In either location, the generated source path remains ./plugins/<plugin-name>.
  • Marketplace root metadata supports top-level name plus optional interface.displayName.
  • Treat plugin order in plugins[] as render order in Codex. Append new entries unless a user explicitly asks to reorder the list.
  • displayName belongs inside the marketplace interface object, not individual plugins[] entries.
  • Each generated marketplace entry must include all of:
    • policy.installation
    • policy.authentication
    • category
  • Default new entries to:
    • policy.installation: "AVAILABLE"
    • policy.authentication: "ON_INSTALL"
  • Override defaults only when the user explicitly specifies another allowed value.
  • Allowed policy.installation values:
    • NOT_AVAILABLE
    • AVAILABLE
    • INSTALLED_BY_DEFAULT
  • Allowed policy.authentication values:
    • ON_INSTALL
    • ON_USE
  • Treat policy.products as an override. Omit it unless the user explicitly requests product gating.
  • The generated plugin entry shape is:
{
  "name": "plugin-name",
  "source": {
    "source": "local",
    "path": "./plugins/plugin-name"
  },
  "policy": {
    "installation": "AVAILABLE",
    "authentication": "ON_INSTALL"
  },
  "category": "Productivity"
}
  • Use --force only when intentionally replacing an existing marketplace entry for the same plugin name.

  • If the target marketplace file does not exist yet, create it with top-level "name", an "interface" object containing "displayName", and a plugins array, then add the new entry.

  • For a brand-new marketplace file, the root object should look like:

{
  "name": "personal",
  "interface": {
    "displayName": "Personal"
  },
  "plugins": [
    {
      "name": "plugin-name",
      "source": {
        "source": "local",
        "path": "./plugins/plugin-name"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Productivity"
    }
  ]
}

Required behavior

  • Outer folder name and plugin.json "name" are always the same normalized plugin name.
  • Do not remove required structure; keep .codex-plugin/plugin.json present.
  • Do not leave [TODO: ...] placeholders in plugin manifests.
  • Keep apps and mcpServers out of plugin.json unless their companion files are actually created.
  • Omit unsupported plugin manifest fields that validation rejects, including hooks.
  • If creating files inside an existing plugin path, use --force only when overwrite is intentional.
  • Preserve any existing marketplace interface.displayName.
  • When generating marketplace entries, always write policy.installation, policy.authentication, and category even if their values are defaults.
  • Add policy.products only when the user explicitly asks for that override.
  • Keep marketplace source.path relative to the selected marketplace root as ./plugins/<plugin-name>.
  • Only use --marketplace-name when creating a new marketplace file whose name should not be personal because that name is already taken or installed elsewhere.
  • If Codex would need approval to write the marketplace file, ask for that approval before proceeding. If the user prefers to run the write themselves, provide the exact scaffold command and then continue from validation or subsequent plugin edits instead of leaving the workflow vague.
  • For updates to an existing local plugin during development, do not hand-edit marketplace config or marketplace.json. Use the update flow documented in references/installing-and-updating.md and scripts/update_plugin_cachebuster.py.
  • Do not tell the user to run codex plugin marketplace add for the default personal-marketplace flow. That command is for explicit non-default marketplace configuration, not for the standard ~/.agents/plugins/marketplace.json path.
  • If the user provided a non-default --marketplace-path, make sure that marketplace is installed before giving reinstall instructions. Use codex plugin marketplace add <path-to-marketplace-root> when that explicit marketplace has not been configured yet.
  • When the workflow created or updated a marketplace-backed plugin, end the final user-facing response with a short Codex app handoff. Say To view this in the Codex app: and write View <normalized plugin name> and Share <normalized plugin name> as Markdown links, not raw URLs or code spans.
  • The View deeplink uses codex://plugins/<normalized plugin name>?marketplacePath=<absolute marketplace.json path>. The Share deeplink uses the same URL with &mode=share.
  • Replace the placeholders with the real normalized plugin name and absolute marketplace.json path from the scaffolded plugin. URL-encode the path segment and query value when needed.
  • Do not add pluginName or hostId query parameters to these deeplinks. Codex derives both after the user clicks the link.
  • Do not emit the View <normalized plugin name> or Share <normalized plugin name> links when no marketplace entry was created or updated.

Reference to exact spec sample

For the exact canonical sample JSON for both plugin manifests and marketplace entries, use:

  • references/plugin-json-spec.md
  • references/installing-and-updating.md for update/reinstall guidance while iterating on an existing local plugin, plus the new-thread pickup behavior after reinstall

Validation

After editing SKILL.md, run:

python3 ../skill-creator/scripts/quick_validate.py .

Before handing back a generated plugin, run:

python3 scripts/validate_plugin.py <plugin-path>

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

grahama1970/acceptance-contract

Turn a client brief, zip bundle, directory, or single requirements file into a typed acceptance-contract bundle with extracted requirements, acceptance checks, open questions, an immutable-goal draft, and a create-report-backed decision report. Use when users say acceptance contract, brief to requirements, freeze the goal, create immutable goal, amend immutable goal, build a Battle requirements bundle, or extract requirements from this bundle.

grahama1970/agent-ecosystem

Canonical map and shared contracts for the agent-governance ecosystem: the pi.receipt_envelope.v1 boundary envelope, the component graph, and the rules for which component owns which schema. Use when wiring a skill or extension into the shared receipt world, when asking how shame, triage-error, tau, ask, project-watchdog, ops-herdr, ponytail, and Memory fit together, or when validating an envelope.

grahama1970/agentic-evals

Agentic evaluation of skills using multi-trial fixtures, deterministic command assertions, trajectory checks, safety constraints, and evidence-backed readiness scoring. Use when users ask for agentic evals, multi-trial skill evaluation, skill trajectory validation, or readiness scoring for a skill workflow.

grahama1970/agent-inbox

File-based inter-agent messaging with headless dispatch. Check inbox, send bugs/requests to other projects, automatically spawn headless agents to fix bugs, and track progress via task-monitor.

grahama1970/agents-registry

Generate and query the centralized agent identity registry. Scans .pi/agents/*/AGENTS.md, parses frontmatter, outputs agents-registry.json and optionally syncs to /memory for semantic search.

grahama1970/agent-status

Artifact-driven status surfaces for long-running project-agent work. Maintains status.json, events.jsonl, proof manifests, and a stale-aware STATUS.html so humans can tell where the agent is, what passed, what is still unproven, and what decision or action is next — without dashboard theater.

grahama1970/align

Round-based context alignment before execution. Use when the human, project agent, WebGPT, scillm, ask, dogpile, memory, or project-knowledge may each hold different facts about a task; especially before ambiguous design, infographic, product workflow, high-stakes implementation, plan-iterate, project-infographic, or multi-review work.

grahama1970/analytics

Flexible data science analytics for any dataset. Auto-discovers schema, recommends charts, exports to create-figure. Works with JSONL, JSON, CSV from any source.

grahama1970/analyze-chatterbox-emotions

Evaluate generated Chatterbox voice files as voice-quality artifacts: affect match, arousal/valence proxies, pause placement, intelligibility inputs, clipping, loudness, and discontinuity flags. Use when reviewing Chatterbox emotional tags, pauses, Turbo/base affect delivery, Persona Dream utterance renders, or whether generated speech matches an intended product-facing affect.

grahama1970/analyze-elf

Reverse-engineer features from ELF binaries. Extracts CLI commands, state machines, protocols, Zod schemas, and data models. Automatically generates a /create-walkthrough prosecution brief with Mermaid diagrams. Uses /treesitter for AST analysis of bundled JS/TS source.

grahama1970/animation-vocabulary

Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.

grahama1970/anonymize-data

Anonymize supported CSV, JSON, UTF-8 text, and SQLite files using an explicit policy through the oai-trial project. Use for anonymize data, pseudonymize exports, redact policy literals, or discover and explicitly approve fuzzy name aliases. The skill is a thin CLI/Docker interface, not another engine.

grahama1970/anvil

Heavy-duty "No-Vibes" debugging and hardening orchestrator. Use this for complex, stubborn bugs where `review-code` has failed, or for "Red Teaming" (hardening) a codebase. Runs multiple agents in parallel (Thunderdome) using git worktree isolation.

grahama1970/apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

grahama1970/argue

Multi-persona structured debate orchestrator. Personas research via /dogpile, consult colleagues via /ask, and argue toward nuanced synthesis on complex questions.

grahama1970/arxiv

Search arXiv for papers and extract knowledge into memory. Use `search` to find papers, `learn` to extract knowledge.

grahama1970/ask

Use when the user asks to query project memory, ask an oracle, use supported browser-backed reviewers, run Tau roundtable/single-handler workflows, ask Pi-native subagents from within Pi, run persona/deep-review workflows, generate image prompts, check OS/project health through composed skills, or run an ask DAG. This skill is the executable /ask runtime; do not replace it with an informal subagent, plain web search, or hand-written review; inside Pi, explicit Pi-native subagent targets are routed through the pi-subagents tool as an Ask target type.

grahama1970/assess

Step back and critically reassess project state. Use when asked to "assess", "step back", "fresh eyes", "check alignment", "sanity check", "health check", "prune documentation", or "evaluate what's working". Offers documentation pruning and doc-code alignment analysis. Offer to run after major changes (don't auto-run).

grahama1970/assistant

Shared GPT + classifier inference gateway for persona monitor tasks. Routes validation and classification through a 4-tier cascade: heuristic → classifier → local GPT → scillm.

grahama1970/assistant-lab

Self-improvement workbench for /assistant. All the tools needed to diagnose, train, evaluate, and promote models in a continuous loop. The "warm pond" where /assistant evolves its own inference stack.

相關技能