agentleFS
davekilleendavekilleen/Dex/.agents/skills/project-health/SKILL.md

project-health

Skill509 starsChanged 3 months agoMITView on GitHub

Scan active projects for status, blockers and next actions. Use when the user says 'how are my projects', 'what's stuck', 'project status'. Also use proactively when projects have gone quiet. Not for writing a spec for a new product idea; use `product-brief`.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No tasks for 2+ weeks = yellow

    line 38
  2. Distinctive:

    Look for "blocked", "waiting on", "stuck" in project notes

    line 41
  3. Distinctive:

    Check if there's a clear next action

    line 45
  4. Distinctive:

    No next step = yellow

    line 46
  5. Distinctive:

    When feeling disconnected from the big picture

    line 71
  6. Distinctive:

    Before 1:1s to surface blocked projects

    line 72
  7. Distinctive:

    When deciding what to work on next

    line 73
  8. Very specific:

    Call refresh_project_related_tasks (no path) while scanning.

    line 79
  9. Very specific:

    If the result is on or off, say nothing about the preference.

    line 81
  10. Distinctive:

    Add a task to Week Priorities

    line 86
  11. Very specific:

    Call track_event with event_name project_health_checked and properties:

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from `.claude/skills/project-health/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->

Quick scan of all active projects to see what's stalled, blocked, or needs attention.

What This Does

Checks each project in 04-Projects/ for:

  1. Activity levels (when was project last touched?)
  2. Week Priorities presence (does project have active tasks?)
  3. Blockers (anything blocking progress?)
  4. Next steps clarity (is the next action clear?)

Process

Step 1: Scan Projects

List all projects in 04-Projects/:

ls -la 04-Projects/

Step 2: Check Each Project

For each project folder or file:

Activity Check:

  • Get last modification time
  • 7 days without activity = yellow

  • 14 days without activity = red

Week Priorities Presence:

  • Scan 00-Inbox/Weekly_Plans.md for project mentions
  • No tasks for 2+ weeks = yellow

Blocker Check:

  • Look for "blocked", "waiting on", "stuck" in project notes
  • Any logged blocker = red

Next Step Clarity:

  • Check if there's a clear next action
  • No next step = yellow

Step 3: Output Dashboard

### Project Health Dashboard

| Project | Status | Issue | Days Since Activity |
|---------|--------|-------|---------------------|
| [Project A] | 🟢 | On track | 2 |
| [Project B] | 🟡 | No active tasks | 8 |
| [Project C] | 🔴 | Blocked - waiting on [X] | 15 |

**Summary:** [N] projects ([X] 🟢 / [Y] 🟡 / [Z] 🔴)

Status Meanings

  • 🟢 Green: Active, clear next steps, no blockers
  • 🟡 Yellow: Stale 7-14 days, OR no active tasks, OR unclear next step
  • 🔴 Red: Blocked, OR stale 14+ days

When to Use

  • Weekly planning to check project health
  • When feeling disconnected from the big picture
  • Before 1:1s to surface blocked projects
  • When deciding what to work on next

Related tasks

Each project page can show a Related tasks list near the top — open work first, a few recently done underneath. The list links to the real task; ticking stays in 03-Tasks/Tasks.md. Only tasks with an explicit Project: link (path or project name) or a path/wikilink to that project file appear.

  1. Call refresh_project_related_tasks (no path) while scanning.
  2. If the result is needs_opt_in, ask once: "Project pages can show a Related tasks list near the top — open work first, a few recently done underneath. Only tasks you linked to that project appear, and you still tick them in the main task list. Turn it on?" Then call set_project_related_tasks with enabled true or false. Do not write the section before they answer, and do not ask again after they answer.
  3. If the result is on or off, say nothing about the preference.

Follow-up Actions

For yellow projects:

  • Add a task to Week Priorities
  • Clarify next step in project notes

For red projects:

  • Identify what's blocking progress
  • Escalate if needed
  • Or decide to pause/archive the project

Track Usage (Silent)

Call the mark_feature_used tool on the dex-analytics MCP server with project-health. This ticks the feature's box in System/usage_log.md, which is what /dex-level-up reads to recommend features that have not been tried. It writes locally and sends nothing, so it runs whether or not analytics is enabled.

Analytics (Silent):

Call track_event with event_name project_health_checked and properties:

  • projects_reviewed
  • blockers_found

This only fires if the user has opted into analytics. No action needed if it returns "analytics_disabled".

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.