fru-dev3/ai-ready-life/health-task-attach-trend-context
Claude Code and agent skill by fru-dev3/ai-ready-life
- community
Checking that the SKILL.md file is still in the repository.
Given a biomarker name and a current value, returns the prior value, delta, percent change, and a 3-panel direction (improving / stable / worsening) using the biomarker's reference range to determine which direction is favorable. Single primitive enforced across labs, vitals, weight, and any other tracked health metric. Ensures no value is ever shown without context.
Install
npx vskill@latest install fru-dev3/ai-ready-life/health-task-attach-trend-contextSKILL.md
The same SKILL.md was published earlier as fru-dev3/ai-ready-life/health-task-attach-trend-context.
health-attach-trend-context
Trigger: Called by flow-build-lab-summary, task-flag-out-of-range-value, flow-prep-appointment-brief, flow-build-wellness-summary, flow-fitness-goal-review. Produces: Trend record returned to caller; no vault writes.
What It Does
The paragon rule "lab results never presented without trend + prior period" applies to every metric, not just labs. This is the single primitive that enforces it.
Inputs: biomarker name, current value, current date.
Outputs (returned struct):
prior_value— most recent value before current, ornullif noneprior_date— date of prior measurementdelta_absolute— current minus priordelta_percent—(current - prior) / prior × 100direction— one ofimproving,stable,worseningbased on whether the delta moves toward or away from the in-range targetband_change—entered_range,left_range,improved_within_range,worsened_within_range,still_out_of_range,still_in_rangepanel_summary— three-line text: prior → current → direction (e.g., "Last: 7.2 (3 mo ago) → Now: 6.4 → Improving toward target")
Direction logic:
- For biomarkers where lower is better (e.g., LDL, A1c, BP): downward delta = improving
- For biomarkers where higher is better (e.g., HDL, vitamin D, eGFR): upward delta = improving
- For range-bounded biomarkers (e.g., TSH, sodium): "improving" = closer to range midpoint
- Direction polarity is read from
vault/health/00_current/lab-reference.md
Steps
- Look up biomarker reference range and direction polarity
- Search
vault/health/00_current/labs/and01_prior/labs/for the most recent prior value - If no prior value exists, return struct with
prior_value: nullandpanel_summary: "No prior value on file — establishing baseline." - Compute deltas, direction, band change
- Format
panel_summarytext - Return struct
Configuration
vault/health/config.md:
trend_lookback_months(default 24 — how far back to search for a prior value)
Vault Paths
- Reads:
vault/health/00_current/labs/,01_prior/labs/,lab-reference.md - Writes: none (returns struct)
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpaperclip-pkg/skills/health-task-attach-trend-context/SKILL.md
Popularity
- Repository stars
- 17
- Repository forks
- 5
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/fru-dev3/ai-ready-life/health-task-attach-trend-context)