بنقرة واحدة
sw-analytics
Analytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Analytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts.
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
Write a portable, secret-scrubbed work handoff doc so you can continue this work in any AI tool. Use when saying "handoff", "running out of tokens", "switch to Codex/OpenCode/Gemini/Cursor", "continue elsewhere", or "continue on another machine".
Batch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close".
[DEPRECATED] Use `sw:multi-project --tool github` instead. Organizes specs and splits tasks across multiple GitHub repositories. This skill will be removed in SpecWeave v1.3.0.
Unified multi-project management skill for GitHub, Azure DevOps, and Jira. Organizes specs and splits tasks across multiple repositories or projects for monorepo, polyrepo, project-per-team, and area-path architectures. Use `--tool github|ado|jira` to select the target integration.
[DEPRECATED] Use sw:team-lead --preset <name> instead.
[DEPRECATED] GitHub issue formatting standard. See docs/internal/specs/github-issue-standard.md
| name | sw/analytics |
| description | Analytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts. |
| version | 1.0.0 |
| allowed-tools | Read, Bash |
specweave metrics CLI commands to gather live telemetry data.sw:analytics [--cache-stats] [--spawn-count] [--token-usage]
Displays prompt cache hit rates per skill for the current session.
Output format:
Cache Statistics (current session)
───────────────────────────────────
sw/grill hit rate: 78% (1,240 tokens from cache)
sw/judge-llm hit rate: 65% (980 tokens from cache)
sw/code-reviewer hit rate: 82% (1,560 tokens from cache)
───────────────────────────────────
Overall: hit rate: 75%
Requirements:
cache.staticContextFiles non-empty in config)Enable persistent metrics: Set analytics.cacheMetrics.enabled: true in .specweave/config.json.
Reports agent spawn counts per team session. Use to verify that Opus 4.7 fan-out reduction is working (target: ≤ 50% of pre-1.1.0 baseline).
Reports total token consumption per skill across the session.