بنقرة واحدة
status
Show Clarity Protocol status — stale documents, recommended next step, decisions
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Show Clarity Protocol status — stale documents, recommended next step, decisions
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Build the project narrative and audience-specific messaging
An AI thinking partner that pushes back. Use when the user wants to think through what they're building and why — explore or clarify a problem, requirements, or stakeholders; weigh a solution or architecture; brainstorm risks and failure modes; or work through a consequential decision. Also use proactively at inflection points: before choices that would be expensive to reverse (new services, auth/trust models, data schemas, external integrations, significant API contracts) — if getting it wrong means a multi-day rework rather than a 5-minute fix, engage. Works for software and non-software projects alike.
Work through an important decision with structured guidance
Embed the Clarity Protocol into this project (scaffold protocol dir + CLAUDE.md snippet)
Brainstorm failure modes and risks with specialist thinker subagents
| name | status |
| description | Show Clarity Protocol status — stale documents, recommended next step, decisions |
| disable-model-invocation | true |
Call the get_packet_status MCP tool (from the clarity-agent server). If the MCP server is unavailable, the fallback is the status script:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/protocol_status.py" . --agent
If there is no protocol directory, say so and offer /claudity:embed.
Summarize the output for the user in plain language (don't dump the raw report): one or two sentences on where the project stands, the recommended next step and why, and any decisions needing reconsideration. Offer to start the recommended process via Claudity's start skill.