web-otel-spec-audit-orchestrator
Skill44 starsChanged 5 months agoApache-2.0View on GitHub
Index skill for the SPEC audit orchestrator — load the agent definition for full persona, Task invocation, and iteration loop. Use when the user @mentions the orchestrator skill or asks for multi-pass SPEC vs implementation sweeps for pulse-web-otel.
In this repository20 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- product/CLAUDE.mdCLAUDE.md
- pulse-web-otel/CLAUDE.mdCLAUDE.md
- add-ai-sub-agentSkill
- add-alert-metricSkill
- add-api-endpointSkill
- add-ui-componentSkill
- add-ui-screenSkill
- clickhouse-migrationSkill
- deploy-serviceSkill
- fatal-fiveSkill
- integrate-pulse-web-sdkSkill
- pr-reviewSkill
- pulse-prd-authorSkill
- pulse-prd-reviewSkill
- web-otel-spec-implementation-auditSkill
- web-sdk-e2e-matrixSkill
- web-sdk-instrumentSkill
- web-sdk-shipSkill
The file
Files
Web SDK — SPEC audit orchestrator (skill index)
Canonical orchestrator persona (read this first): .agents/agents/web-otel-spec-audit-orchestrator.md
Act as that agent: mission, audit priority (correctness before structure; smoke escape), preconditions, Invocation (@web-otel-spec-audit-orchestrator or Task(subagent_type="web-otel-spec-audit-orchestrator", …)), confirmation gate, outer iteration loop, queue drain, nested Task(subagent_type="pulse-web-sdk", readonly=true) for per-unit audits, fallback in-thread audit, and § F close-out.
Shared index: web-otel-spec-implementation-audit/audit-index.json
Per-unit checklist: web-otel-spec-implementation-audit/SKILL.md
Hooks: .cursor/hooks/queue-web-otel-spec-audit.sh (queue + stderr nudge) + resolve-spec-audit-instrumentation.mjs → .cursor/pulse-web-otel-spec-audit-queue.jsonl
Verify setup: .cursor/hooks/verify-spec-audit-setup.sh
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

