Scaffold Codex plugin packages with deterministic manifests, marketplace metadata, and traceability or evidence contracts for non-trivial adoption. Use when creating plugin roots or adopting existing skills into plugin ownership.
60
71%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./Plugins/plugin-factory/skills/scaffolding_templates/plugin-creator/SKILL.mdUse for initial plugin scaffolding.
Return: schema_version, plugin_name, plugin_path, validation, optional blocked_by.
For non-trivial plugins, also return factory_governance with plugin posture, visibility policy, traceability mode, budget posture, and risks.
Use the detailed scaffold procedure in references/workflow.md.
Apply the context-disposition policy: move important still-valid context to references, and intentionally discard stale, duplicated, unsafe, superseded, or low-signal text.
Classify reusable, delivery-oriented, visible-family, or coding-harness plugins with references/factory-governance-spine.md. Keep one-skill plugins minimal.
Apply the OpenAI-style plugin design contract during scaffold shape decisions: keep the root-visible surface small, split child skills by distinct user intent, declare side-effect classes early, and leave confirmation behavior for install, external write, destructive, or completion-gating actions. Add bundled hooks only when lifecycle behavior is explicitly requested, and prefer hooks/hooks.json.
Read when:
nameCreate or adopt plugin-owned canonical source only. Do not edit generated runtime mirrors, user-level plugin copies, or marketplace projections as the source of truth.
Keep plugin scaffolding separate from skill hardening. Route detailed skill quality work to [[skill-builder]] after the plugin package has deterministic ownership, manifest policy, and validation evidence.
If the destination plugin root, marketplace ownership, or skill-adoption move semantics are ambiguous, stop and ask before writing.
For non-trivial factory work, include first_principles_gate or an explicit first_principles_gate_status: not_applicable with the reason in the output or handoff before claiming readiness.
python3 Skills/skill-builder/Infrastructure/scripts/quick_validate.py Plugins/plugin-factory/skills/scaffolding_templates/plugin-creator
bash Infrastructure/scripts/validation-and-linting/validate_skill_authoring_family.shFail fast: stop at first failed gate and report blocker text.
.codex-plugin/plugin.jsonlinear-helpers with the required .codex-plugin/plugin.json, but do not add marketplace metadata yet."review-tools as a plugin and add it to the local marketplace with explicit installation and authentication policy fields."agent-ops/branch-cleanup skill into a new plugin without leaving a duplicate canonical copy."references/workflow.mdreferences/factory-governance-spine.mdreferences/contract.yamlreferences/evals.yamlreferences/task-profile.jsonreferences/plugin-json-spec.md../../../../../Infrastructure/references/openai-style-plugin-design-contract.md../../../../../Infrastructure/references/software-literature-expert-lens-pack.md../../../../../Infrastructure/references/software-literature-skill-expertise-map.mdassets/46e4be2
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.