.claude/skills/subagent-driven-developmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Use when executing implementation plans with independent tasks in the current session
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/subagent-driven-developmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/subagent-driven-developmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/subagent-driven-developmentRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @eohmig/subagent-driven-developmentclawhub inspect @eohmig/subagent-driven-development --version 1.0.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:d121c621ec782c2fbaf794e81377b19109c8ab4628f72afae35d129baeebf8fbimplementer-prompt.mdre-review-prompt.mdscripts/review-packagescripts/sdd-workspacescripts/task-briefskill-card.mdSKILL.mdtask-reviewer-prompt.mdInitial version of subagent-driven-development skill. - Introduces a framework for executing implementation plans by dispatching a dedicated subagent per independent task. - Ensures isolated context for each task to prevent context pollution and maximize focus. - Enforces a structured review process: per-task code and spec review, plus a final whole-branch review before completion. - Automates execution without human check-ins between tasks, stopping only for blocking issues or ambiguity. - Specifies workspace and ledger management for robust progress tracking and artifact isolation.