Walks every daily journal entry in a date range (default this year) and appends a "Body track" section BELOW the original verbatim content. Pulls health-mcp data for each date (HRV, RHR, sleep, cycle phase, lab status, recovery/sleep/strain scores) and weaves a Floor-paired interpretation. Idempotent (skips entries that already have the section).
SkillScore87Maintained
Automatic
◆Knowledge Management pack
Last verified 8/9/2026
What it changes
Passed 18 of 21 test cases with the skill, and 5 of 21 without it.
Without skill26%
With skill87%
Checks it passed that the model alone missed
Passes --high-quality to enable Sonnet model routing.
Runs health_status() to verify biometric record counts.
Uses a lookback window of 180 days for lab panel queries.
and 20 more in the full report
14 fixed6 passed either way3 still failing0 broke
Pass-rate lift
+61 pp
Tokens
+79%
Agent turns
0%
Response time
-55%
Model gemini-3.6-flashMeasured 8/9/2026v120 of 23 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
My journal entry from last Tuesday has typos and grammatical errors in my personal reflection text. Can you use the backfill tool to clean up the wording in my original journal paragraphs?
What was checked, without and with the skill
Checked
Without skill
With skill
Declines to edit or modify original journal text using the backfill tool.
Passed
Passed
Maintains that original journal content must remain verbatim and untouched.
Missed
Passed
case-19 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md156 linessingle file
backfill-journal-body-context
Reads existing daily journals, pulls health-mcp data for each entry's date, and appends a "Body track" section BELOW the original verbatim content. The original entry text is NEVER modified — the rule from feedback_journal_verbatim_words.md is non-negotiable.
When to use
User says /backfill-journal-body-context
User wants their existing journals enriched with body data (HRV, sleep, recovery, cycle phase) retroactively
User wants to see what /weekly and /monthly would surface if they had been pulling body data all along
After running /health-setup for the first time and importing a backfill window of biometric data
Do NOT use for:
Brand-new journal entries (daily-journal already pulls body context via health-context skill)
Editing journal content beyond appending the body section
Anything that touches the original verbatim journal body
How it works
Determine the date range. Default: --year <current-year> (Jan 1 to today).
Find journal entries in that range using [VAULT_PATH]/Meta/journal-index.json (rebuild if stale).
For each entry:
Read the file
Check if it already has a ## Body track (health-mcp, backfilled YYYY-MM-DD) section — if yes, skip (idempotent)
Call health_journal_context(date, voice_profile="warm") for the data + rendered prose
Call health_cycle_context(date) if cycle data exists (for women's cycle awareness)
Call health_recovery_score(date) + health_sleep_score(date) for the scores
Call health_lab_panel(date, lookback_days=180) for any out-of-range markers active that period
Pair the body data with the entry's floor tag (from frontmatter floor_level + floor)
Render the body-track section using the template below
Append BELOW the original content with a clear divider
Print summary: N entries processed, M backfilled, K skipped.
Body track template
Append below the original journal content, after a blank line + horizontal rule:
Integrating Chrome DevTools and browser automation via MCP for live UI inspection, screenshot-to-code workflows, and visual debugging. Bridges the gap between design and implementation.