Menu
Check system health — metadata gaps, graph integrity, alias sync, and referential integrity.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Prepare for a 1:1 — pull context from goals, meeting notes, Slack, and tasks to generate talking points
Auto-generate or update description, type, topics, aliases, and graph-backed relationship fields for a file.
Build a focused plan for today based on goals, tasks, and recent activity. Reads from the weekly plan if it exists and updates it.
Weekly review + compound learnings — review progress, surface blockers, distill insights into Memory
Cross-initiative alignment checker — surfaces misalignment, gaps, duplication, dependency risks, and synergy opportunities across active initiatives in the company and your groups roadmap. Complementary to /pulse (broad discovery); /align focuses on whether your initiatives are pulling in the same direction and have synergies with other company groups. Run ad-hoc or before key decisions.
Autonomously optimize any Agent skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoeval on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.
| name | verify |
| description | Check system health — metadata gaps, graph integrity, alias sync, and referential integrity. |
Run a health check on the personal-agent workspace and surface the issues most likely to make future sessions less reliable.
When the user invokes /verify, run all checks and present a consolidated
report.
Scan Tasks/, Context/Meeting Notes/, and Context/Document Hub/ for .md
files without a description: field in frontmatter.
If .claude/skills/link-audit/SKILL.md exists, use the same link-health logic
to identify broken links or disconnected active files. Summarise only the
highest-signal issues in the /verify output.
If Context/Memory/graph.yaml exists, validate:
nodes and edgessource / target resolves to a nodetype is in the allowed list documented in graph.yamlfile: pointer resolves to a real fileIf Context/Memory/graph.yaml exists, check:
Context/121s/*.md other than TEMPLATE.md has a matching
person node with a file: pointeraliases: has a matching project
or initiative nodefile:file:For graph nodes with file: pointers whose canonical page has an aliases:
frontmatter field, compare the page aliases to the graph aliases. Flag
mismatches.
Scan files with people:, projects:, or channels: arrays and ensure every
id resolves to an existing graph node of the right type:
people -> personprojects -> project or initiativechannels -> channel## System Health Report — [date]
### Descriptions
- [X] files missing descriptions
### Links
- [X] broken links or disconnected active files
### Graph
- Summary: [X] nodes, [X] edges — YAML [OK/FAIL]
- Integrity: [X] missing endpoints, unknown edge types, broken file pointers
- Coverage: [X] canonical pages missing nodes; [X] isolated nodes
- Alias Sync: [X] page aliases drifting from graph aliases
- Referential Integrity: [X] invalid people/projects/channels ids
### Recommended Actions
1. Run `/enrich` on the top files missing descriptions or relationship metadata
2. Fix graph file pointers or alias mismatches before trusting structured lookups
3. Run `/link-audit` if the workspace still has disconnected docs or tasks
Ask: "Want me to fix any of these?"