Utility Pm Critic
product-on-purpose/pm-skills
Run adversarial review on a PM artifact via the pm-critic sub-agent.
Define success criteria and tracking setup for launch during PRD v0.9 Go-to-Market.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metrics --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .claude/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .claude/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metricsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metrics --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .agents/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .agents/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metrics --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .cursor/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .cursor/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mattgierhart/PRD-driven-context-engineering.git --path .claude/skills/prd-v09-launch-metrics--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metrics --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .gemini/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .gemini/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metricsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .github/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .github/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering prd-v09-launch-metrics --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/prd-v09-launch-metrics .opencode/skills/prd-v09-launch-metrics && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prd-v09-launch-metrics" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/prd-v09-launch-metrics into .opencode/skills/prd-v09-launch-metrics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prd-v09-launch-metrics", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prd-v09-launch-metricsDefine success criteria and tracking setup for launch during PRD v0.9 Go-to-Market.
Prd V09 Launch Metrics is an agent skill from mattgierhart/PRD-driven-context-engineering. Define success criteria and tracking setup for launch during PRD v0.9 Go-to-Market. Triggers on requests to define launch metrics, set up tracking, or when user asks "how do we measure launch success?", "launch KPIs", "tracking setup", "success criteria", "analytics", "launch goals". Outputs KPI- entries specialized for launch measurement.
Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files and assets (for example `assets/kpi-template.md`, `references/examples.md` and `references/launch-metrics.md`).
It sits in Product & Project Management, covering PRD writing, OKRs and executive reporting and Go-to-market strategy. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepWebSearchWebFetchFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prd V09 Launch Metrics loads about 4.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 885 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 885 words, ~4,651 tokens.
.claude/skills/prd-v09-launch-metrics/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.Position in workflow: v0.9 GTM Strategy → v0.9 Launch Metrics → v0.9 Feedback Loop Setup
Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.
| Mode | What this skill produces |
|---|---|
| quick | 3 KPIs (one each for Reach/Acquisition/Activation); Day 7 targets; basic dashboard |
| standard | Full funnel (Reach → Referral); Day 1/7/30 targets; dashboards + alerts |
| deep | Full funnel + tier targets + Day 1/7/30/90 + product-type calibration + cohort analysis |
This skill requires prior work from v0.3-v0.9:
This skill assumes GTM- entries are complete and tracking infrastructure is configured.
This skill creates/updates:
All KPI- entries for launch are measurement specifications, not confidence-based. They are:
Example KPI- entries:
KPI-101: Website Visitors (Launch Week)
Tier: Tier 3 (Leading)
Category: Reach
Stage: Launch (v0.9)
Owner: Growth Team
Definition: Unique visitors to marketing website from all GTM- channels
Unit: count
Source: Google Analytics 4 / Plausible
Targets:
Day 1: 5,000 (from GTM-002 PH expectations + GTM-007 paid channel)
Day 7: 25,000 (cumulative from all GTM channels)
Day 30: 50,000 (post-launch momentum)
Day 90: 100,000
Evidence: CFD-025 (competitor benchmarks show 5-10% market awareness for Fast Follow), CFD-008 (our GTM reach model projects this based on channel scale)
Product Type Calibration: Fast Follow — higher reach expected due to known category
Tracking:
Dashboard: Launch Dashboard > Reach panel
Alert: <1,000 on Day 1 (channel distribution problem)
Action Thresholds:
Red: <2,500 Day 7 (channel underperformance)
Yellow: <20,000 Day 7 (80% of target)
Green: >25,000 Day 7
GTM Connection: GTM-002 (Product Hunt), GTM-007 (Website), GTM-008 (Paid ads), GTM-010 (Email)
v0.3 KPI Link: N/A (launch-specific)
---
KPI-102: Trial Signups
Tier: Tier 2 (Conversion)
Category: Acquisition
Stage: Launch (v0.9)
Owner: Product Team
Definition: Completed signup flow (email verified, profile created)
Unit: count
Source: Application database + Mixpanel
Targets:
Day 1: 500 (5-10% conversion from reach)
Day 7: 2,000 (extrapolated from Day 1 + momentum)
Day 30: 5,000 (post-launch plateau)
Day 90: 15,000 (month 3 growth)
Evidence: CFD-030 (developer SaaS benchmarks show 5-10% landing-to-signup), CFD-031 (our onboarding tested with 8% conversion)
Product Type Calibration: Fast Follow = 8-10% expected (higher than average because users understand category)
Tracking:
Event: signup_completed { source, campaign_id, user_segment }
Dashboard: Launch Dashboard > Acquisition panel
Alert: Conversion rate <5%
Action Thresholds:
Red: <100 Day 1 (messaging/channel mismatch — escalate GTM)
Yellow: <400 Day 1 (funnel friction — investigate landing page)
Green: >500 Day 1
GTM Connection: GTM-002, GTM-004 (Landing Page), GTM-005 (Email), GTM-008 (Ads)
v0.3 KPI Link: KPI-001 (Trial Signups baseline from Outcome Definition)
---
KPI-103: Activation Rate (First Value Achievement)
Tier: Tier 1 (Critical)
Category: Activation
Stage: Launch (v0.9)
Owner: Product Team
Definition: % of signups who complete first core action (generate code suggestion) within 24h
Unit: percentage
Source: Mixpanel + Application events
Targets:
Day 1: 40% (from CFD-035 developer tool benchmarks)
Day 7: 45% (slight improvement with onboarding refinement)
Day 30: 50% (post-launch optimizations)
Day 90: 55% (mature product experience)
Evidence: CFD-035 (activation benchmarks for dev tools: 30-50%), CFD-015 (our UJ-001 usability test showed 45% completed core action)
Product Type Calibration: Fast Follow = higher baseline (users already understand AI coding assists)
Tracking:
Event: first_value_achieved { user_id, action_type, time_to_value_seconds }
Dashboard: Launch Dashboard > Activation panel
Alert: Drops below 30% (onboarding broken)
Action Thresholds:
Red: <25% (product experience broken — pause marketing, investigate UJ-001)
Yellow: <35% (friction in onboarding — iterate SCR-001/002)
Green: >45% (strong PMF signal)
GTM Connection: Quality indicator for all GTM- channels (tells us if messaging matches product)
v0.3 KPI Link: KPI-002 (Activation Rate from Outcome Definition)
---
KPI-104: Day 7 Retention
Tier: Tier 1 (Critical)
Category: Retention
Stage: Launch (v0.9)
Owner: Product Team
Definition: % of Day 0 signups who return and take an action on Day 7
Unit: percentage
Source: Mixpanel cohort analysis
Targets:
Day 7: 25% (from CFD-040 B2B SaaS benchmarks)
Day 30: 20% of original (cohort retention)
Day 90: 15% of original (monthly cohort)
Evidence: CFD-040 (B2B SaaS D7 retention benchmarks 20-30%), CFD-015 (our beta test: 22% D7 retention with 50 users)
Product Type Calibration: Fast Follow = critical (users can easily switch back to competitors) — retention signal validates PMF
Tracking:
Event: session_start { user_id, cohort_day }
Dashboard: Launch Dashboard > Retention panel
Alert: Day 7 retention <15% (fundamental problem)
Action Thresholds:
Red: <15% (product-market fit issue — consider pivot in features, messaging)
Yellow: <20% (value delivery problem — investigate UJ-/feature completeness)
Green: >30% (strong retention, ready for growth)
GTM Connection: Quality indicator for all GTM- channels
v0.3 KPI Link: KPI-003 (Retention Rate from Outcome Definition)Launch metrics are not vanity numbers—they are decision criteria. Each metric should answer: "Is this working? Should we double down or pivot?" If a metric doesn't inform action, don't track it.
| Layer | What to Measure | Timeframe |
|---|---|---|
| Reach | How many saw us | Day 0-7 |
| Acquisition | How many signed up | Day 0-30 |
| Activation | How many got value | Day 1-14 |
| Retention | How many came back | Week 2-4 |
| Revenue | How many paid | Week 2-8 |
| Referral | How many shared | Week 3+ |
Review v0.3 Outcome Definition KPIs
Define launch-specific metrics
Set targets per timeframe
Configure tracking infrastructure
Create visibility
Create/Update KPI- entries for launch
KPI-XXX: [Launch Metric Name]
Tier: [Tier 1 | Tier 2 | Tier 3]
Category: [Reach | Acquisition | Activation | Retention | Revenue | Referral]
Stage: Launch (v0.9)
Owner: [Who monitors this metric]
Definition: [Exact calculation formula]
Unit: [count | percentage | currency | ratio]
Source: [Where data comes from]
Targets:
Day 1: [target]
Day 7: [target]
Day 30: [target]
Day 90: [target]
Evidence: [CFD-XXX or benchmark that justifies targets]
Product Type Calibration: [How product type affects expectations]
Tracking:
Event: [analytics event name if applicable]
Dashboard: [Where to view this metric]
Alert: [When to get notified]
Action Thresholds:
Red: [Below this = urgent intervention]
Yellow: [Below this = investigate]
Green: [Above this = on track]
GTM Connection: [GTM-XXX channels this measures]
v0.3 KPI Link: [KPI-YYY from Outcome Definition if applicable]Example KPI- entries:
KPI-101: Website Visitors (Launch Week)
Tier: Tier 3 (Leading)
Category: Reach
Stage: Launch (v0.9)
Owner: Growth Team
Definition: Unique visitors to marketing site
Unit: count
Source: Google Analytics / Plausible
Targets:
Day 1: 5,000
Day 7: 25,000
Day 30: 50,000
Day 90: 100,000
Evidence: CFD-025 (competitor launch benchmarks)
Product Type Calibration: Fast Follow = higher baseline expected
Tracking:
Event: page_view (landing pages)
Dashboard: Launch Dashboard > Reach panel
Alert: <1,000 on Day 1
Action Thresholds:
Red: <2,500 Day 7 (50% of target)
Yellow: <20,000 Day 7 (80% of target)
Green: >25,000 Day 7
GTM Connection: GTM-002 (Product Hunt), GTM-007 (Website)
v0.3 KPI Link: N/A (launch-specific)KPI-102: Trial Signups
Tier: Tier 2 (Conversion)
Category: Acquisition
Stage: Launch (v0.9)
Owner: Product Team
Definition: Completed signup flow (email verified)
Unit: count
Source: Application database + Mixpanel
Targets:
Day 1: 500
Day 7: 2,000
Day 30: 5,000
Day 90: 15,000
Evidence: CFD-030 (industry signup rate benchmarks 5-10%)
Product Type Calibration: Fast Follow = 8-10% expected conversion
Tracking:
Event: signup_completed
Dashboard: Launch Dashboard > Acquisition panel
Alert: Conversion rate <5%
Action Thresholds:
Red: <100 Day 1 (messaging/channel mismatch)
Yellow: <400 Day 1 (funnel friction)
Green: >500 Day 1
GTM Connection: GTM-002, GTM-004 (Landing Page)
v0.3 KPI Link: KPI-001 (Trial Signups, general)KPI-103: Activation Rate (First Value)
Tier: Tier 1 (Critical)
Category: Activation
Stage: Launch (v0.9)
Owner: Product Team
Definition: % of signups who complete first value action within 24h
Unit: percentage
Source: Mixpanel + Application events
First Value Action: Complete first [core action - e.g., generate code suggestion]
Targets:
Day 1: 40%
Day 7: 45%
Day 30: 50%
Day 90: 55%
Evidence: CFD-035 (activation benchmarks for dev tools 30-50%)
Product Type Calibration: Fast Follow = higher baseline (users know the category)
Tracking:
Event: first_value_achieved
Dashboard: Launch Dashboard > Activation panel
Alert: Drops below 30%
Action Thresholds:
Red: <25% (onboarding broken)
Yellow: <35% (friction points)
Green: >45%
GTM Connection: Measures effectiveness of all GTM- channels
v0.3 KPI Link: KPI-002 (Activation Rate, general)KPI-104: Day 7 Retention
Tier: Tier 1 (Critical)
Category: Retention
Stage: Launch (v0.9)
Owner: Product Team
Definition: % of Day 0 signups who return on Day 7
Unit: percentage
Source: Mixpanel cohort analysis
Targets:
Day 7: 25%
Day 30: 20% (of Day 0)
Day 90: 15% (of Day 0)
Evidence: CFD-040 (B2B SaaS retention benchmarks)
Product Type Calibration: Fast Follow = retention critical (easy to switch back)
Tracking:
Event: session_start (Day 7 cohort)
Dashboard: Launch Dashboard > Retention panel
Alert: Day 7 retention <15%
Action Thresholds:
Red: <15% (critical product-market fit issue)
Yellow: <20% (value delivery problem)
Green: >30% (strong PMF signal)
GTM Connection: Quality indicator for all GTM- traffic
v0.3 KPI Link: KPI-003 (Retention Rate, general)Track conversion at each stage:
REACH → ACQUISITION → ACTIVATION → RETENTION → REVENUE → REFERRAL
100% 10% 50% 25% 20% 10%| Stage | Key Metric | Benchmark |
|---|---|---|
| Reach → Acquisition | Signup Rate | 5-15% |
| Acquisition → Activation | Activation Rate | 30-60% |
| Activation → Retention | D7 Retention | 20-40% |
| Retention → Revenue | Conversion Rate | 2-10% |
| Revenue → Referral | NPS / Referral Rate | 10-30% |
Expectations vary by product type (from v0.2 BR-):
| Product Type | Acquisition | Activation | Retention | Revenue |
|---|---|---|---|---|
| Fast Follow | High (known category) | High (familiar UX) | Medium (easy to switch) | Quick |
| Slice | Medium (niche) | High (focused value) | High (workflow fit) | Medium |
| Innovation | Low (education needed) | Low (learning curve) | High (if activated) | Slow |
| Component | Purpose | Tool Examples |
|---|---|---|
| Product Analytics | User behavior | Mixpanel, Amplitude, PostHog |
| Web Analytics | Traffic, sources | GA4, Plausible, Fathom |
| Event Tracking | Specific actions | Segment, custom events |
| Error Tracking | Failures, issues | Sentry, LogRocket |
| Session Recording | User experience | Hotjar, FullStory |
| A/B Testing | Experiments | LaunchDarkly, Statsig |
Define standard events for launch tracking:
# Acquisition Events
signup_started: { source, campaign, referrer }
signup_completed: { source, campaign, user_id }
signup_abandoned: { step, source, reason }
# Activation Events
onboarding_started: { user_id }
onboarding_step_completed: { user_id, step }
first_value_achieved: { user_id, action, time_to_value }
# Engagement Events
feature_used: { user_id, feature, context }
session_start: { user_id, day_number }
session_end: { user_id, duration }
# Conversion Events
upgrade_started: { user_id, plan }
payment_completed: { user_id, plan, amount }┌─────────────────────────────────────────────────────────────┐
│ LAUNCH DASHBOARD Last updated: [time] │
├─────────────────────────────────────────────────────────────┤
│ REACH │ ACQUISITION │ ACTIVATION │
│ Visitors: X │ Signups: Y │ Activated: Z% │
│ Target: X │ Target: Y │ Target: Z% │
│ [trend chart] │ [trend chart] │ [trend chart] │
├─────────────────────────────────────────────────────────────┤
│ RETENTION │ REVENUE │ CHANNELS │
│ D7: X% │ MRR: $Y │ Product Hunt: X │
│ Target: X% │ Target: $Y │ Direct: Y │
│ [cohort chart] │ [revenue chart] │ [breakdown chart] │
└─────────────────────────────────────────────────────────────┘| Pattern | Signal | Fix |
|---|---|---|
| Vanity metrics only | Tracking visitors but not activation | Focus on funnel progression |
| No targets | "We got 1000 signups!" (is that good?) | Set explicit targets per timeframe |
| Lagging only | Only tracking revenue | Add leading indicators (activation) |
| No action thresholds | Metrics exist but no response plan | Define red/yellow/green zones |
| Over-instrumentation | 200 events, can't find signal | Focus on 10-15 key events |
| No attribution | Don't know which channel works | Track source for all signups |
Before proceeding to Feedback Loop Setup:
| Consumer | What It Uses | Example |
|---|---|---|
| Feedback Loop Setup | KPI- thresholds trigger feedback collection | KPI-103 <30% → investigate with CFD- |
| Daily Standup | KPI- dashboard for launch status | "Activation at 42%, on track" |
| Pivot Decisions | KPI- data informs strategy | KPI-104 <15% → fundamental problem |
| Investor Updates | KPI- for launch performance | "Day 30: 5000 signups, 45% activated" |
| v1.0 Planning | KPI- baselines for growth targets | KPI-102 baseline → 10% MoM growth |
references/metric-examples.mdassets/kpi-launch-template.mdreferences/dashboard-design.mdreferences/event-schema.md© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4 other files (references, assets) in .claude/skills/prd-v09-launch-metrics of mattgierhart/PRD-driven-context-engineering.
Open the folder on GitHubat commit 30ed1b0
Prd V09 Launch Metrics next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prd V09 Launch Metrics this skillmattgierhart/PRD-driven-context-engineering | 180 | — | ~4.7k | Automated safety check: Pass | MIT | |
| Utility Pm Criticproduct-on-purpose/pm-skills | 716 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Evaluate Artifactandreaskelm/pm-brain | 234 | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Notion Pmborghei/Claude-Skills | 891 | — | ~1.7k | Automated safety check: Pass | MIT | |
| PlaidBuildGreatProducts/plaid | 218 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Product Manager SkillsDigidai/product-manager-skills | 185 | — | ~6.1k | Automated safety check: Pass | CC-BY-NC-4.0 |
product-on-purpose/pm-skills
Run adversarial review on a PM artifact via the pm-critic sub-agent.
andreaskelm/pm-brain
Evaluate quality of a PM artifact or substantive session output using the shared evaluation procedure — gut check, red/green flags, optional full scored review.
borghei/Claude-Skills
Notion expert for product management workflows. An agent skill from borghei/Claude-Skills.
BuildGreatProducts/plaid
Product Led AI Development — guides founders from idea to launched product.
Digidai/product-manager-skills
PM skill for Claude Code, Codex, Cursor, and Windsurf. An agent skill from Digidai/product-manager-skills.
genkovich/sdd
A skill your agent uses to turn a raw feature idea into a reviewed spec.md — a lightweight Socratic interview front (capture the idea, deep-dive the problem) merged with a full product spec…
mattgierhart/PRD-driven-context-engineering
Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).
mattgierhart/PRD-driven-context-engineering
Extracts durable insights from temp/ files to SoT during EPIC Phase E.
mattgierhart/PRD-driven-context-engineering
Validates and registers new SoT IDs with cross-reference integrity.
mattgierhart/PRD-driven-context-engineering
Creates new Source of Truth (SoT) files when existing templates don't fit your needs.
mattgierhart/PRD-driven-context-engineering
Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.
mattgierhart/PRD-driven-context-engineering
Transform validated pain points into articulated user value statements for PRD v0.1 Spark.
Define success criteria and tracking setup for launch during PRD v0.9 Go-to-Market. Prd V09 Launch Metrics is an agent skill from mattgierhart/PRD-driven-context-engineering.9 Go-to-Market.
Prd V09 Launch Metrics fits situations like: requests to define launch metrics; set up tracking; user asks how do we measure launch success?; success criteria.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a claude-code`. Or copy the skill folder (.claude/skills/prd-v09-launch-metrics in mattgierhart/PRD-driven-context-engineering) into .claude/skills/prd-v09-launch-metrics in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a codex`. Or copy the skill folder (.claude/skills/prd-v09-launch-metrics in mattgierhart/PRD-driven-context-engineering) into .agents/skills/prd-v09-launch-metrics in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v09-launch-metrics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prd-v09-launch-metrics, .gemini/skills/prd-v09-launch-metrics, .github/skills/prd-v09-launch-metrics and .opencode/skills/prd-v09-launch-metrics in your project.
SKILL.md names no scripts, command-line tools or credentials: Prd V09 Launch Metrics is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, WebSearch, WebFetch.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Prd V09 Launch Metrics is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.7k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Prd V09 Launch Metrics: Utility Pm Critic (product-on-purpose/pm-skills, 716 stars), Evaluate Artifact (andreaskelm/pm-brain, 234 stars), Notion Pm (borghei/Claude-Skills, 891 stars) and Plaid (BuildGreatProducts/plaid, 218 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.
Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.