plugins/pm-ops/skills/analyze-milestone/SKILL.md
Analyze project milestone health with actionable insights, target date assessment, risk analysis, and specific recommendations
npx skillsauth add coalesce-labs/catalyst analyze-milestoneInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generates a comprehensive health report for a project milestone.
Reports Include:
Philosophy: Provide insights and recommendations for milestone planning, not just data dumps.
# 1. Validate thoughts system (REQUIRED)
if [[ -f "scripts/validate-thoughts-setup.sh" ]]; then
./scripts/validate-thoughts-setup.sh || exit 1
else
# Inline validation if script not found
if [[ ! -d "thoughts/shared" ]]; then
echo "❌ ERROR: Thoughts system not configured"
echo "Run: ./scripts/humanlayer/init-project.sh . {project-name}"
exit 1
fi
fi
# 2. Determine script directory with fallback
if [[ -n "${CLAUDE_PLUGIN_ROOT}" ]]; then
SCRIPT_DIR="${CLAUDE_PLUGIN_ROOT}/scripts"
else
# Fallback: resolve relative to this command file
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/scripts"
fi
# 3. Check PM plugin prerequisites
if [[ -f "${SCRIPT_DIR}/check-prerequisites.sh" ]]; then
"${SCRIPT_DIR}/check-prerequisites.sh" || exit 1
else
echo "⚠️ Prerequisites check skipped (script not found at: ${SCRIPT_DIR})"
fi
Option A: User provides milestone name
MILESTONE_NAME="Q1 Launch"
PROJECT_NAME="Mobile App"
Option B: Interactive prompt
Which milestone would you like to analyze?
- Milestone name: [user input]
- Project name (optional, helps scope lookup): [user input]
Use Task tool with catalyst-dev:linear-research agent:
Prompt: "Get milestone '${MILESTONE_NAME}' details for project '${PROJECT_NAME}' with all issues (limit 100)"
Model: haiku (fast data gathering)
If milestone not found or ambiguous, report error and ask user to clarify.
Use Task tool with milestone-analyzer agent:
Input:
Agent returns: Structured markdown with:
Format the analyzer output into final report:
# Milestone Health Report: [Milestone Name]
**Project**: [Project Name]
**Target Date**: [YYYY-MM-DD] ([X] days remaining)
**Generated**: [YYYY-MM-DD HH:MM]
---
## 🟢/🟡/🔴 Health Assessment
**Takeaway**: [One-sentence summary with target date assessment]
**Current State**:
- Progress: X% complete (Y/Z issues done)
- Target: [YYYY-MM-DD] ([N] days remaining)
- Projected completion: [YYYY-MM-DD] (based on current velocity)
- Risk level: [On track / Behind by N days / Critical]
---
## 📊 Progress Tracking
[Progress bars, velocity, time remaining]
---
## ⚠️ Risks & Blockers
[Target date risks, blockers, at-risk issues]
---
## 💡 Recommendations
[Priority-ordered actions]
---
**Next Review**: [Suggested date based on target date proximity]
IMPORTANT: Document Storage Rules
thoughts/shared/pm/reports/thoughts/searchable/ — this is a read-only search indexREPORT_DIR="thoughts/shared/pm/reports"
mkdir -p "$REPORT_DIR"
# Sanitize milestone name for filename
MILESTONE_SLUG=$(echo "$MILESTONE_NAME" | tr '[:upper:]' '[:lower:]' | tr ' ' '-')
REPORT_FILE="$REPORT_DIR/$(date +%Y-%m-%d)-${MILESTONE_SLUG}.md"
# Write formatted report
# ...
echo "✅ Report saved: $REPORT_FILE"
# Update workflow context
if [[ -f "${SCRIPT_DIR}/workflow-context.sh" ]]; then
"${SCRIPT_DIR}/workflow-context.sh" add reports "$REPORT_FILE" "${TICKET_ID:-null}"
fi
🎯 Milestone Health: [Milestone Name] - [🟢/🟡/🔴]
Target Date: [YYYY-MM-DD] ([X] days remaining)
Progress: ████████░░ [X]% ([Y]/[Z] issues)
Status: [On track / Behind by N days]
Priority Actions:
1. [Action 1]
2. [Action 2]
3. [Action 3]
Full report: thoughts/shared/pm/reports/YYYY-MM-DD-milestone.md
testing
Phase-agent that fixes a failing verify verdict so the pipeline self-heals instead of stalling to needs-human (CTL-653). Reads `${ORCH_DIR}/workers/<ticket>/verify.json`, fixes the `findings[]` (every severity:"high" plus the regression_risk drivers) directly via Edit/Write, commits the remediation, and emits `phase.remediate.complete.<ticket>`. The scheduler's router then re-dispatches `verify` to re-check (the verify⇄remediate cycle, cap 3). Dispatched as a `claude --bg` job by `phase-agent-dispatch`, which invokes it via slash command — hence `user-invocable: true`.
development
Phase agent for the verify step of the 9-phase orchestrator pipeline (CTL-450). NEW skill — has no canonical wrapper. Runs read-only adversarial verification against the implement-phase diff: tsc, tests, lint, security scan, reward-hacking scan, code review, test coverage, silent-failure hunt. Writes ${ORCH_DIR}/workers/<TICKET>/verify.json then emits phase.verify.complete.<ticket>. Reads phase-implement.json as its prior-phase artifact. NEVER writes application code — only test files allowed. Spawned via phase-agent-dispatch via slash command — hence `user-invocable: true`.
tools
--- name: phase-triage description: Phase agent that triages a Linear ticket — expands acronyms, classifies (feature/bug/docs/refactor/chore), identifies dependencies, estimates scope, writes triage.json, and posts a triage analysis comment to Linear. Triage completion is signaled by that comment plus the local triage.json — there is no `triaged` label. Emits phase.triage.complete.<TICKET> on success and phase.triage.failed.<TICKET> on error. Dispatched by the phase-agent orchestrator (CTL-452)
testing
Phase agent for the review step of the 9-phase orchestrator pipeline (CTL-450). Wraps the /review skill (gstack) — explicitly skips /ultrareview per user decision. Reads verify.json from the prior phase, runs /review against the diff, writes ${ORCH_DIR}/workers/<TICKET>/review.json, and creates a remediation commit for any HIGH-severity finding that has a deterministic fix. Emits phase.review.complete.<ticket>. Spawned via phase-agent-dispatch via slash command — hence `user-invocable: true`.