Load methodology context for creating or fixing Claude Code instruction artifacts (discovery: implementation-clarity). Evaluate at implementation-clarity when artifact type is known (command, skill, hook, protocol, external tool config) and implementation approach needs methodology guidance.
View on GitHubMariusWilsch/clarity-workflow-plugin
clarity-workflow
skills/manage-artifact/SKILL.md
February 1, 2026
Select agents to install to:
npx add-skill https://github.com/MariusWilsch/clarity-workflow-plugin/blob/main/skills/manage-artifact/SKILL.md -a claude-code --skill manage-artifactInstallation paths:
.claude/skills/manage-artifact/# Manage Artifact Provides methodology context for creating or fixing instruction artifacts. ## Artifact Type Routing After rubber-duck diagnoses the artifact type, load the appropriate methodology: | Artifact Type | Reference Files | Fix Tool | |--------------|-----------------|----------| | **Command/Prompt** | [command.md](references/command.md) + [persuasion-principles.md](references/persuasion-principles.md) | /stage | | **Skill** | [skill.md](references/skill.md) + [persuasion-principles.md](references/persuasion-principles.md) | skill-creator | | **Hook** | (not yet implemented) | settings.json | | **Protocol** | [protocol.md](references/protocol.md) + [persuasion-principles.md](references/persuasion-principles.md) | CLAUDE.md edit | | **External Tool Config** | [external-tool-config.md](references/external-tool-config.md) | hippocampus | > **Note:** Command/Prompt covers ALL prompt types: slash commands, agent prompts, prompt templates. Any engineered prompt follows the same methodology. **Note:** Hooks use settings.json (declarative config) - no persuasion principles needed. External tools use hippocampus for documentation - no persuasion principles needed. Commands, skills, and protocols require persuasion techniques to ensure AI compliance. ## Workflow 1. Confirm artifact type from rubber-duck diagnosis 2. Read the appropriate reference file(s) for methodology context 3. **For Command/Skill/Protocol:** Also read [persuasion-principles.md](references/persuasion-principles.md) 4. Apply the methodology during implementation using persuasive language (Authority + Commitment + Social Proof) 5. **PRE-COMMIT PAUSE** before finalizing (see verification workflow below) ## Verification Workflow After implementing the fix, do NOT commit immediately. Follow this flow: ### PRE-COMMIT PAUSE Announce: "Fix implemented. Verify in a new project session before committing." ### Accept Verification Session Path After user provides Session C conversation path, *