AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Okr Manager

skill-fractalmind-ai-okr-manager-skill-okr-manager-skill · by fractalmind-ai

OKR lifecycle management for AI agents. Use when creating, reviewing, updating, or reporting on OKRs. Ensures every OKR has measurable Success Criteria, result-oriented KRs with dependencies, and clear completion standards.

— No reviews yet
0 installs
36 views
0.0% view→install

Install

$ agentstack add skill-fractalmind-ai-okr-manager-skill-okr-manager-skill

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-fractalmind-ai-okr-manager-skill-okr-manager-skill)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
○ 6mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Okr Manager? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

OKR Manager

A skill for AI agents to manage OKR (Objectives and Key Results) lifecycle — from creation to completion.

When to Use

  • Your human assigns a new objective or goal
  • Creating or restructuring an OKR in your OKR file
  • Reviewing existing OKRs for completeness
  • Heartbeat/periodic audit: checking if any OKR lacks completion standards
  • Reporting OKR status to your human or team

Configuration

This skill works with any markdown-based OKR file. Set these in your workspace:

| Config | Default | Description | |--------|---------|-------------| | OKR file path | OKR.md | Where OKRs are stored | | Language | en | Primary language for OKR content (en, zh, etc.) | | Status markers | PENDING / IN PROGRESS / COMPLETE | KR status labels | | Priority markers | P0 / P1 / P2 | Priority levels |

OKR Creation Checklist

Every OKR MUST have ALL of these. Reject or flag any OKR missing items.

1. Objective (1 sentence)

  • Starts with a verb (Build / Implement / Complete / Deliver)
  • Describes the outcome, not the activity
  • Bad: "Do orderbook development" / Good: "Complete orderbook development, testing, and launch"

2. Success Criteria (1-3 bullets, quantifiable)

  • Must be binary verifiable: done or not done
  • Must include at least ONE measurable metric
  • Template: "Complete {N} {specific actions} in {environment}, verify {specific metric}"
  • Examples:
  • "Complete 1 gasless transaction on TestNet"
  • "Third-party PR 24h first-response rate >= 95%"
  • "E2E test pass rate 100%, matching latency Dependency order: KR1 → KR2 → ... → KRn

KR1: {title} — {status}

  • Deliverable: {what is produced}
  • Outcome: {observable change when KR is complete}
  • Verification: {how to prove done}

KR2: {title} — {status}

  • Deliverable: {what is produced}
  • Depends on: KR1
  • Outcome: {observable change when KR is complete}
  • Verification: {how to prove done}
Tasks / Milestones (recommended)
  • [ ] {execution step tied to KR1 / owner / dependency}
  • [ ] {execution step tied to KR2 / owner / dependency}

## OKR Lifecycle

Human assigns objective ↓ [Create OKR] → Use this skill to ensure checklist passes ↓ [Write to OKR file] → Confirm Success Criteria + KRs are complete ↓ [Human confirms] → If issues, iterate and fix ↓ [Execute & Track] → Each heartbeat/check-in: review progress, push forward ↓ [KR Complete] → Update status, notify human ↓ [Success Criteria met] → Mark OKR as ACHIEVED


## Operations

### Creating an OKR

1. Parse the human's objective into a clear, verb-first Objective statement
2. Draft measurable Success Criteria (what does "done" look like?)
3. Draft sequential, result-oriented KRs with dependencies
4. Add Tasks / Milestones if execution needs staging, owner mapping, or unblock steps
5. Validate against the checklist above
6. Write to OKR file
7. Confirm with human

### Updating KR Status

When a KR completes:
1. Update status: `PENDING` → `IN PROGRESS` → `✅ COMPLETE`
2. Add completion evidence (PR number, CI link, test results)
3. Check if downstream KRs are now unblocked
4. If all KRs complete → check Success Criteria → mark OKR ACHIEVED

### Heartbeat OKR Audit

During periodic check-ins:
1. Read the OKR file
2. For each ACTIVE OKR:
   - What KR is currently in progress?
   - Is anything blocked? For how long?
   - What's the next action?
3. Report summary to human (only if there are changes or blockers)
4. Push forward: assign tasks, trigger CI, follow up on blockers

### Reporting Status

Format for status reports:

[OKR Status] • {OKR Name}: KR{n}/{total} — {current KR title} ({status}) • {OKR Name}: KR{n}/{total} — {current KR title} ({status}) Blockers: {list or "none"}


## Priority Emojis

| Priority | Emoji | Meaning |
|----------|-------|---------|
| P0 | 🔴 | Must do — blocks everything else |
| P1 | 🟡 | Important — do this week |
| P2 | 🟢 | Nice to have — do when capacity allows |

## Common Anti-patterns (Avoid)

1. **Vague completion standards**: "launch" "improve" "optimize" — must quantify
2. **Missing verification**: KR says what to do but not how to prove it's done
3. **Task masquerading as KR**: "build agent manager" / "integrate Slack" — move this into Tasks / Milestones
4. **KR too large**: Single KR contains multiple independent pieces of work → split it
5. **No priority**: All OKRs appear equally important → must rank
6. **Passive voice**: "wait for deploy" "wait for confirmation" → change to active: "trigger deploy" "verify completion"
7. **No owner**: Nobody is accountable → every OKR needs an owner
8. **Stale OKRs**: OKR status not updated for >1 week → audit and update or archive

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [fractalmind-ai](https://github.com/fractalmind-ai)
- **Source:** [fractalmind-ai/okr-manager-skill](https://github.com/fractalmind-ai/okr-manager-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.