daddia Milestone Tracker
When to use
Critical-path milestone status with slippage against profile tolerance — knock-on effects, not flat date lists.
What this skill does not do
- Does not invent progress — ask for plan and actuals.
- Does not escalate non-critical float slips — distinguish timeline threats from noise.
Preconditions
| Input | If missing |
|---|---|
| Milestone plan | Ask — halt if absent |
| Current actuals/forecast | Ask — don't infer |
| Slippage tolerance (profile) | Default with [PROVISIONAL] |
Provisional mode
Partial actuals: assess available milestones; flag incomplete coverage.
Trust spine
- Confidence bands (
governance-tracking):- High: Critical path identified; slippage classified; knock-on effects stated.
- Medium: Some forecasts uncertain — tagged
[review]. - Low: Plan missing — halt.
- Failure modes:
- Incentive Gaming: N/A — schedule focus.
- Escalation triggers: Critical-path slip beyond tolerance — overall end date at risk.
Workflow
- Read profile for plan location and slippage tolerance.
- Get plan and actuals.
- Identify critical path vs float.
- Classify each critical milestone: on track / at risk / slipped.
- State knock-on effects for at-risk/slipped items.
- Note non-critical items briefly without escalation.
- Gaming-pattern check before output.
Output format
CONFIDENCE: [defensible recommendation | structured first pass]
CRITICAL PATH STATUS:
[Milestone] — Planned: [date] | Actual/Forecast: [date] | Status: [...]
Knock-on effect: [...]
NON-CRITICAL (float available): [...]
OVERALL END DATE: [on track | at risk | slipped] — [why]
Worked example
Input: Integration milestone 2 weeks late on critical path; QA milestone 1 week late with float.
Expected output: Integration slipped with end-date knock-on; QA noted non-critical only.
Quality checks before delivering
- Critical path distinguished from float
- Tolerance from profile applied
- Knock-on effects for critical slips
- No invented actuals
Propose profile update
When a stable convention surfaces during this run (thresholds, naming, tone, output format, or recurring corrections), propose a profile update: show the exact diff against ~/.claude/plugins/config/claude-for-strategy/pmo/CLAUDE.md (org-wide facts go to org-profile.md), ask for confirmation, and write only on yes. Only /pmo:practice-setup auto-applies a full profile write.
Outputs
Follows plugin CLAUDE.md § Outputs. Next: status-report, raid-log entry, or recovery plan.