Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Priority Dashboard

ASecurity

Use this to rebuild, inspect, or temporarily steer {{user_name}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.

26 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythonbash

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 9/27/2026

$npx -y skills add vincentmumme/personalos-boilerplate --skill priority-dashboard --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Priority Dashboard?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Priority Dashboard
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vincentmumme-priority-dashboard/badge)](https://www.skillsdirectory.com/skills/vincentmumme-priority-dashboard)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: priority-dashboard
description: "Use this to rebuild, inspect, or temporarily steer {{user_name}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes."
metadata:
  pos_schema_version: pos-v1
  pos_id: 01a0251c-9e64-7f0d-81a6-bf5efd9bc4d7
  pos_type: skill
  pos_title: "Skill: priority-dashboard"
  pos_created: "2026-08-21"
  pos_updated: "2026-08-22"
  pos_lifecycle: active
  pos_skill_version: 1.2.0
  pos_system_refs: ["[[system/contracts/core/personalos-mutation-contract]]", "[[system/frameworks/operations/action-und-attention-modell]]", "[[system/frameworks/operations/priority-dashboard]]", "[[system/rules/core/timezone-and-local-day-boundary]]"]
  pos_reads_profile_keys: ["action", "attention-trigger", "project", "priority-control", "view-record"]
  pos_writes_profile_keys: ["priority-control", "view-record"]
  pos_template_refs: ["[[system/templates/operations/priority-control]]", "[[system/templates/topology/view-record]]"]
  pos_invokes_skill_refs: ["[[skills/task-manager/SKILL]]", "[[skills/pos-verify/SKILL]]"]
  pos_check_refs: ["[[system/checks/pos-v1-contract]]", "[[system/checks/core/personalos-mutation-postflight]]"]
---

# Skill: priority-dashboard

## Contract

This skill produces exactly one current read model at priority dashboard. It reads canonical Actions, due Attention Triggers, relevant linked owner state, and the optional temporary priority control. It never owns task text, deadlines, evidence, completion, lifecycle, project truth, or recurring commitments.

The dashboard contains no checkboxes and no independent completion controls. Every surfaced item links to its canonical Action or Trigger and states why it is prioritized. The bounded view contains exactly one current focus, at most three next-seven-day outcomes, and enough 30-day life gates to keep the combined main-focus set at no more than five Actions. Waiting/cashflow risk and stale review remain separate lanes. Routine receipt/Admin work is invisible outside the final five calendar days and then appears only as a month-end batch; payment and material risk exceptions stay in the risk lanes.

Ranking follows [[system/frameworks/operations/priority-dashboard]]: effective {{user_name}} control first, then real `due` deadlines inside a rolling seven-day horizon, explicit `critical`/`high` priority and actual `in-progress` work, linked owner impact, soft `target` tie-breaking, and finally opportunities. A `target` never creates focus by itself. Free-text cadence words never affect rank. An expired control is ignored automatically and remains visibly identified as expired.

## Rebuild

Run from the PersonalOS root:

```bash
python3 skills/priority-dashboard/scripts/rebuild.py --reason manual
```

Use the explicit reason matching the event:

```bash
python3 skills/priority-dashboard/scripts/rebuild.py --reason manual-priority-change
python3 skills/priority-dashboard/scripts/rebuild.py --reason operational-state-change
```

The scheduled VPS run uses `--reason scheduled --timezone Europe/Berlin`. The timezone argument is explicit scheduler context, not a duplicate hidden default.

## Steering

When {{user_name}} changes focus, ordering, or exclusions:

1. Update only priority control using its registered profile and template.
2. Use canonical Action links; do not copy titles, Next Actions, Done Boundaries, or lifecycle state into the control record.
3. Set `priority_control_review_on`; an active control also requires `priority_control_expires_on`.
4. Rebuild immediately with `--reason manual-priority-change`.
5. Run `pos-verify` on the control and generated dashboard.

Manual focus and ordering affect only the read model. Exclusion hides an item from this dashboard temporarily; it does not cancel, defer, complete, or edit the Action.

## Operational Refresh

After a material Action, Trigger, or linked Project change, the supported explicit path is a rebuild with `--reason operational-state-change`. There is no realtime watcher. The daily scheduled rebuild makes the dashboard morning-ready, while explicit rebuilds cover same-day operational changes.

Before consuming the saved view, run:

```bash
python3 skills/priority-dashboard/scripts/rebuild.py --check
```

`--check` validates the saved `view-record` and compares its stored Source-Digest with the current Action, Trigger, Control, and Project sources. A mismatch is `drift`; rebuild rather than presenting stale priorities.

## Verification

Run:

```bash
python3 skills/priority-dashboard/scripts/test_rebuild.py
python3 system/data-model/scripts/pos_v1.py validate --files operations/priority-control.md operations/priority-dashboard.md
python3 skills/pos-verify/scripts/run.py --files operations/priority-control.md operations/priority-dashboard.md
```

The script validates the rendered `view-record` before writing and rejects checkbox output, an invalid active control, conflicting manual include/exclude refs, or more than five main-focus Action links.

## Failure Behavior

- Invalid or unreadable canonical Actions fail the rebuild rather than being silently reinterpreted.
- An active control without a valid expiry fails Registry validation.
- Expired control directions are ignored, not auto-renewed.
- Unknown control Action refs are surfaced as warnings and never promoted to invented tasks.
- The previous dashboard remains in place if rendering or validation fails.

## Resources

- `scripts/rebuild.py` — deterministic ranking and Markdown rebuild.
- `scripts/test_rebuild.py` — focused behavioral tests.

## Change History

- **{{install_date}}** | Foundation adopted from PersonalOS Boilerplate.

Attribution

vincentmummevincentmumme
View sourceSee grades on GitHubMore from vincentmumme →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →