j-mauro-r/SAT-Dengue-V2 / .agents/skills/deepworkplan
deepworkplan
VerifiedDeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.
spec/schema/dwp-config-v1.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://deepworkplan.com/schema/dwp-config/v1.json",
"description": "DeepWorkPlan configuration file, v1 (spec/CONFIG.md): <repo>/.dwp/config.json and ~/.dwp/config.json share this shape. Two keys today - benchmark (spec/BENCHMARK.md section 1) and addons (the addon registry, spec/CONFIG.md section 3). Read by one stdlib parser, shared/config.py. Fail-closed at runtime: a malformed or wrong-typed value disables what it affects with one warning; it never aborts a flow. Unknown top-level keys and unknown addon keys are tolerated for forward compatibility (the reader ignores an unknown addon key with one warning). The registry is informative: no addon entry gates conformance or any plan.",
"type": "object",
"additionalProperties": true,
"properties": {
"schema": {
"const": "https://deepworkplan.com/schema/dwp-config/v1.json",
"description": "Optional self-identification; the reader does not require it."
},
"benchmark": {
"type": "object",
"description": "Opt-in field metrics (spec/BENCHMARK.md). Resolved wholesale: a repository file that carries this object overrides the user file.",
"additionalProperties": true,
"properties": {
"enabled": { "type": "boolean" },
"learnings": { "type": "boolean" }
}
},
"host": {
"type": "object",
"description": "Machine-readable host capability record (F-17, spec/CONFIG.md section 3a): which abilities the host that runs plans here provides. Per capability the user file wins over the repository file (the record describes a machine); an explicit resources.py --caps declaration wins over both. Unstated capabilities stay at the all-False floor; the reader ignores an unknown or non-boolean capability with one warning.",
"additionalProperties": false,
"properties": {
"stop_agent": { "type": "boolean" },
"meter_spend": { "type": "boolean" },
"meter_tokens": { "type": "boolean" },
"meter_wall_clock": { "type": "boolean" },
"cancel_children": { "type": "boolean" },
"model_routing": { "type": "boolean" },
"subagents": { "type": "boolean" },
"telemetry": { "type": "boolean" }
}
},
"addons": {
"type": "object",
"description": "The addon registry. Keys are in-pack addon directory names (contract amendment A1); resolved per key, repository entry over user entry. Absent means not enabled.",
"propertyNames": { "pattern": "^[a-z][a-z0-9-]{0,63}$" },
"additionalProperties": { "$ref": "#/$defs/addonEntry" }
}
},
"$defs": {
"addonEntry": {
"type": "object",
"additionalProperties": false,
"required": ["enabled"],
"properties": {
"enabled": {
"type": "boolean",
"description": "Required to enable; only true enables."
},
"version": {
"type": "string",
"pattern": "^v\\d+\\.\\d+\\.\\d+(-[0-9A-Za-z.]+)?$",
"description": "Informative product tag the repository expects (verify warns on a mismatch, never fails)."
},
"note": {
"type": "string",
"minLength": 1,
"maxLength": 200,
"pattern": "^[^\\n\\r]*$",
"description": "Optional one-line note on the decision, e.g. 'accepted; machine-level install deferred'. An enabled addon that is not detected and carries a note is reported as deferred, without a warning."
}
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |