ai-team-library/claude/skills/telemetry-report/SKILL.md
# Skill: Telemetry Report ## Description Parses telemetry data from all bean.md files and produces an aggregate summary of project metrics: total time invested, average bean duration, breakdowns by category and owner, and identification of outliers. ## Trigger - Invoked by the `/telemetry-report` slash command. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | category | String | No | Filter to a single category: `App`, `Process`, or `Infra`. C
npx skillsauth add beekeeper-lab/foundry ai-team-library/claude/skills/telemetry-reportInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Parses telemetry data from all bean.md files and produces an aggregate summary of project metrics: total time invested, average bean duration, breakdowns by category and owner, and identification of outliers.
/telemetry-report slash command.| Input | Type | Required | Description |
|-------|------|----------|-------------|
| category | String | No | Filter to a single category: App, Process, or Infra. Case-insensitive. |
| status | String | No | Filter by bean status. Default: Done (only completed beans). Use all for everything. |
| since | String | No | Only include beans created on or after this date (YYYY-MM-DD). |
Read the backlog index — Parse ai/beans/_index.md to get the list of all beans with their metadata (ID, title, category, status, owner).
Apply filters — If category, status, or since is provided, filter the bean list accordingly.
Read telemetry from each bean — For each bean in the filtered list, read its bean.md and extract:
Duration field from the metadata table (e.g., 3m, 1h 15m, < 1m)Started and Completed fieldsCategory and Owner fields< 1m → 30s, Xm → X×60s, Xh Ym → (X×3600 + Y×60)s, Xh → X×3600s.Compute aggregate statistics:
Compute category breakdown:
| Category | Beans | Total Time | Avg Time |
|----------|-------|------------|----------|
| App | 80 | 18h 30m | 13m |
| Process | 20 | 3h 10m | 9m |
| Infra | 10 | 1h 28m | 8m |
Compute owner breakdown:
| Owner | Beans | Total Time | Avg Time |
|-----------|-------|------------|----------|
| team-lead | 95 | 20h 5m | 12m |
| developer | 15 | 3h 3m | 12m |
Identify outliers:
Display the report:
===================================================
TELEMETRY REPORT
===================================================
Beans: N total (N with data, N without)
Time: Xh Ym total
Average: Xm per bean
Median: Xm per bean
===================================================
BY CATEGORY
| Category | Beans | Total Time | Avg Time |
...
BY OWNER
| Owner | Beans | Total Time | Avg Time |
...
LONGEST BEANS
| Bean | Title | Duration |
...
SHORTEST BEANS
| Bean | Title | Duration |
...
===================================================
| Output | Type | Description | |--------|------|-------------| | report | Console text | Formatted telemetry summary displayed in the terminal |
| Error | Cause | Resolution | |-------|-------|------------| | No beans found | Backlog is empty or filters match nothing | Report "No beans match the given filters" | | No telemetry data | Beans exist but none have duration values | Report count and suggest running BEAN-114 backfill |
development
# Skill: VDD (Verification-Driven Development) Gate ## Description Runs the programmatic VDD gate for a bean: parses the bean's `## Acceptance Criteria` section, dispatches each criterion's evidence type to the matching runner (test, lint, file, file-contains, or manual), aggregates the results into a pass/fail verdict, and writes a structured markdown report at `ai/outputs/tech-qa/vdd-<NNN>.md` (zero-padded NNN). This is the machine-checkable counterpart to the prose VDD policy in `ai/contex
tools
# Skill: Spawn Task ## Description Dispatches a single specialist persona to execute a single task with only that task's context. Auto-detects the runtime environment and chooses one of two execution paths: - **In tmux** (`$TMUX` set): spawn a worker in a git worktree using a child tmux window. Process-isolated, parallelizable, durable across the calling session's lifetime. Same pattern as `/spawn-bean` but at task granularity. - **Not in tmux**: invoke the `Agent` tool with `subagent_typ
development
# Skill: Orchestration Report ## Description Aggregates the per-bean **Orchestration Telemetry** blocks (BEAN-278) across recent Done beans and produces a markdown report that answers the architecture-aware-evaluation question: **is the orchestration paying for itself?** Distinct from `/telemetry-report` (which aggregates raw cost, duration, and tokens); this skill aggregates the orchestration-quality metrics layered on top — bounces, persona activations, contract violations, escape-hatch usag
development
# Skill: Health Check ## Description Runs all health checks defined in `ai/context/health-checks.md` and produces a table-format report. Can be called standalone or by other skills (e.g., `/long-run`). ## Trigger - Invoked by the `/health-check` slash command. - Called programmatically by `/long-run` at the start of each cycle. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | health_checks | Markdown file | Yes | `ai/context/health-checks.md`