Install
$ agentstack add skill-djangonavarro220-agentic-life-os-work-portfolio ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
work-portfolio
Maintain professional evidence and opportunity material: achievements, projects, portfolio entries, interview stories, role targets, references, and follow-up actions.
Trigger
Use when the user asks to:
- capture professional achievements, project outcomes, or metrics
- prepare CV, portfolio, interview, or promotion material
- track opportunities, applications, recruiter conversations, or networking follow-ups
- review career direction and evidence gaps
- turn work history into concise reusable stories
Operating model
- Resolve the active runtime and private data directory.
- Read
$LIFEOS_DATA_DIR/config.jsonwhen available. - If source ownership for this domain is unknown, inspect runtime-owned systems read-only and propose a source decision before writing anything.
- Load only
runtimes/.mdif runtime-specific commands, storage pointers, delivery, scheduling, or integration behavior are needed. - Do not load other runtime adapters for the same task.
- Prefer pointers, access notes, review dates, and short operational state over duplicated raw data.
- Ask before changing external systems, creating reminders, contacting people, importing data, broad migrations, or destructive cleanup.
- Record useful Life OS coordination state under
$LIFEOS_DATA_DIR/work-portfolio/data.jsonwhen the user/runtime policy allows it.
Source decision
Store the source choice in $LIFEOS_DATA_DIR/work-portfolio/data.json when useful:
{
"source_decisions": {
"work_portfolio_records": {
"owner": "runtime|external|life-os",
"runtime": "",
"source": "",
"access": ""
}
}
}
This JSON shape belongs in $LIFEOS_DATA_DIR//data.json, not global config.json. Use Life OS as the source of truth only for Life-OS-specific preferences, technical state, or notes explicitly created inside Life OS. Do not silently create a second private database when the runtime or an external system already owns the real data.
Output contract
Keep output compact and action-oriented:
Summary:
- Signal: ...
- Risk: ...
- Next action: ...
- Review date: ...
If nothing changed, say so briefly or stay silent when running as a scheduled routine and the saved policy allows silence.
Data
Private state belongs in:
$LIFEOS_DATA_DIR/work-portfolio/data.json
Acceptable state:
- source decisions and access pointers
- last review/check timestamps
- suppression windows
- dated summaries or caches when useful
- non-secret user-approved notes for this domain
- follow-up pointers into runtime-owned tasks, reminders, calendar, mail, docs, or memory
Do not store credentials, raw account exports, full mail/chat logs, private delivery targets, raw medical records, bank credentials, identity document numbers, or secrets.
Runtime adapters
Runtime-specific commands and caveats live in separate Markdown files:
runtimes/hermes.md
runtimes/openclaw.md
Load only the adapter for the active runtime. Generic skill text must not inline both Hermes and OpenClaw command blocks.
Safety boundaries
Safe autonomously:
- read Life OS private state
- inspect available runtime state with read-only tools
- summarize already available information
- propose next actions, review dates, and source mappings
- write Life OS operational state when it does not alter external systems
Ask before:
- writing to external systems
- creating or changing runtime crons, reminders, calendar events, contacts, mail, tasks, or delivery routes
- importing, exporting, or migrating data
- deleting records or clearing caches broadly
- handling sensitive identity, medical, financial, or credential material
Common pitfalls
- Duplicating the runtime's real data into Life OS instead of storing a pointer.
- Loading multiple runtime adapters and polluting the prompt with irrelevant commands.
- Turning a light review into a heavyweight system of record.
- Alerting on every tiny change instead of respecting quiet policy.
Verification checklist
- [ ] Active runtime identified.
- [ ] Source owner recorded or explicitly deferred.
- [ ] Only the active runtime adapter was loaded when runtime details were needed.
- [ ] No secrets, raw exports, or private identifiers were written to repo files.
- [ ] Any external side effect had explicit user approval.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: djangonavarro220
- Source: djangonavarro220/agentic-life-os
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.