pm-claude-skills 61.2.2 → 61.3.0

package/README.md

@@ -1,4 +1,4 @@
-# 🧠 PM Skills — 751 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
+# 🧠 PM Skills — 754 Professional Agent Skills for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes
 
 [![In the official Anthropic plugin directory](https://img.shields.io/badge/Anthropic%20Plugin%20Directory-Published-D97757?logo=anthropic&logoColor=white)](#-quick-start)
 [![Stars](https://img.shields.io/github/stars/mohitagw15856/pm-claude-skills?style=social)](https://github.com/mohitagw15856/pm-claude-skills/stargazers)
@@ -12,7 +12,7 @@
 [![License](https://img.shields.io/badge/license-MIT-lightgrey)](LICENSE)
 [![Sponsor](https://img.shields.io/badge/sponsor-❤️-ff69b4)](https://github.com/sponsors/mohitagw15856)
 
-**A library of 751 skills — each one a plain `SKILL.md` file that teaches your AI assistant to do one professional task properly.** Decode a lease before you sign it. Write a PRD your team can execute. Simulate the promotion committee before the real one meets. Check the weather with zero API keys. Generic AI gives you filler; these give you the structure a senior professional actually uses.
+**A library of 754 skills — each one a plain `SKILL.md` file that teaches your AI assistant to do one professional task properly.** Decode a lease before you sign it. Write a PRD your team can execute. Simulate the promotion committee before the real one meets. Check the weather with zero API keys. Generic AI gives you filler; these give you the structure a senior professional actually uses.
 
 Works natively in **Claude Code** and **Hermes Agent**, with ready-to-paste exports for **ChatGPT, Gemini, Cursor, Codex** and 8 more tools. *(PM stands for Professional, not just Product Management.)*
 
@@ -30,7 +30,7 @@ No `npm install` needed — `npx pm-claude-skills …` always runs the latest. `
 
 ## 📚 The skills
 
-Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules — not vibes), a concrete output template, quality checks, and anti-patterns. All 751 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
+Every skill follows the same discipline: what it produces, the inputs it needs, a real framework (severity scales, decision rules — not vibes), a concrete output template, quality checks, and anti-patterns. All 754 pass the [SkillSpec](SKILLSPEC.md) L3 gate and a security audit in CI.
 
 ### For everyone — life's paperwork and decisions
 
@@ -155,7 +155,7 @@ The whole library on one poster — start path, standout features, and install o
 
 ## 🆕 Latest
 
-**v61.2.2 — long-form video:** **[youtube-script](skills/youtube-script/SKILL.md)** — a full YouTube script (explainer/tutorial/video essay) engineered for watch-time: title + thumbnail concepts, a timed cold open, retention beats with B-roll cues, and chapter timestamps. Sibling to [short-form-script](skills/short-form-script/SKILL.md); for other languages, [professional-translator](skills/professional-translator/SKILL.md). *Earlier — v61.2, the builder's toolkit:* prove quality against real references, red-team robustness, test skills before a PR, run them offline, and sign what they produce. *v61.1, the demand side:* **[find](https://mohitagw15856.github.io/pm-claude-skills/find.html)** (task→skill router) with an honest per-skill **measured / no-claim** badge, per-skill versioning, and **[SkillSpec as an adoptable standard](conformance/REGISTRY.md)** (earnable `--badge` + public registry). Full history: **[CHANGELOG](CHANGELOG.md)** · [releases](https://github.com/mohitagw15856/pm-claude-skills/releases)
+**v61.3.0 — most-requested:** three skills built straight from the demand queue — **[reference-check-script](skills/reference-check-script/SKILL.md)** (rigorous candidate reference calls with a scoring rubric), **[deprecation-comms-plan](skills/deprecation-comms-plan/SKILL.md)** (the customer-comms program for sunsetting an API/feature), and **[community-moderation-policy](skills/community-moderation-policy/SKILL.md)** (a fair, enforceable moderation policy + enforcement ladder for a user community). *Earlier — v61.2.2:* **[youtube-script](skills/youtube-script/SKILL.md)** (long-form video). *v61.2, the builder's toolkit;* *v61.1, the demand side:* **[find](https://mohitagw15856.github.io/pm-claude-skills/find.html)** (task→skill router) with an honest **measured / no-claim** badge and **[SkillSpec as an adoptable standard](conformance/REGISTRY.md)**. Full history: **[CHANGELOG](CHANGELOG.md)** · [releases](https://github.com/mohitagw15856/pm-claude-skills/releases)
 
 ## 🤝 Contributing
 
@@ -171,4 +171,4 @@ MIT — use them, fork them, ship them at work. Skills are judgment, and judgmen
 
 ---
 
-*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 751 skills · 90 bundles · 31 professions · every commit gated. The long version of this README — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*
+*Built by [Mohit](https://github.com/mohitagw15856) with Claude. 754 skills · 90 bundles · 31 professions · every commit gated. The long version of this README — every feature, wave, and frontier bet — lives in the **[Showcase](docs/SHOWCASE.md)**.*

package/exports/README.md

@@ -8,7 +8,7 @@ by hand; edit the source skill and run:
 node scripts/build-exports.mjs
 ```
 
-Currently exporting **751 skills** to:
+Currently exporting **754 skills** to:
 
 - **ChatGPT — Custom GPT instructions** → `exports/chatgpt/`
 - **Google Gemini — Gem instructions** → `exports/gemini/`

package/exports/aider/README.md

@@ -3,7 +3,7 @@
 > Auto-generated from `skills/*/SKILL.md` by `scripts/build-exports.mjs`.
 > **Do not edit these files by hand** — edit the source skill and regenerate.
 
-751 skills exported. Copy a `.md rule` into the tool to use it.
+754 skills exported. Copy a `.md rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -126,6 +126,7 @@
 | College App Parent Guide | `pm-parents` | `pm-parents/college-app-parent-guide/college-app-parent-guide.md` |
 | College Cost | `pm-calculators` | `pm-calculators/college-cost/college-cost.md` |
 | Community Management Playbook | `pm-social` | `pm-social/community-management-playbook/community-management-playbook.md` |
+| Community Moderation Policy | `pm-social` | `pm-social/community-moderation-policy/community-moderation-policy.md` |
 | Company Brief | `pm-jobsearch` | `pm-jobsearch/company-brief/company-brief.md` |
 | Company Event Ops | `pm-cowork` | `pm-cowork/company-event-ops/company-event-ops.md` |
 | Comparative Market Analysis | `pm-realestate` | `pm-realestate/comparative-market-analysis/comparative-market-analysis.md` |
@@ -203,6 +204,7 @@
 | Demo Script | `pm-cowork` | `pm-cowork/demo-script/demo-script.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/dependency-audit.md` |
 | Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/dependency-conflict-resolver.md` |
+| Deprecation Comms Plan | `pm-devrel` | `pm-devrel/deprecation-comms-plan/deprecation-comms-plan.md` |
 | Design Critique | `pm-design` | `pm-design/design-critique/design-critique.md` |
 | Design Handoff Brief | `pm-advanced` | `pm-advanced/design-handoff-brief/design-handoff-brief.md` |
 | Design System Audit | `pm-design` | `pm-design/design-system-audit/design-system-audit.md` |
@@ -541,6 +543,7 @@
 | Red-Team Review | `pm-cross` | `pm-cross/red-team-review/red-team-review.md` |
 | Redundancy Consultation | `pm-hr` | `pm-hr/redundancy-consultation/redundancy-consultation.md` |
 | Refactoring Plan | `pm-craft` | `pm-craft/refactoring-plan/refactoring-plan.md` |
+| Reference Check Script | `pm-recruiting` | `pm-recruiting/reference-check-script/reference-check-script.md` |
 | Reference Letter | `pm-lifeadmin` | `pm-lifeadmin/reference-letter/reference-letter.md` |
 | Reference Request Kit | `pm-layoff` | `pm-layoff/reference-request-kit/reference-request-kit.md` |
 | Referral Program | `pm-growth` | `pm-growth/referral-program/referral-program.md` |

package/exports/aider/pm-devrel/deprecation-comms-plan/deprecation-comms-plan.md

@@ -0,0 +1,65 @@
+# Deprecation Comms Plan Skill
+
+Deprecations go wrong in two ways: too fast (customers get broken and churn angry) or too quiet (they find out when it breaks). This skill plans the wind-down as a *communications program*, not an announcement — enough runway, messaging matched to how much each customer depends on the thing, a real migration path, and a plan for the accounts that will need a human.
+
+## Working from a brief
+
+Given what's being deprecated and why, **produce the full plan** — infer the risk tiers from usage and contract exposure. Right-size the runway to how hard the migration is (an internal flag flip is weeks; a public API is many months). If there's no migration path yet, flag that as a blocker before any announcement.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **What's being deprecated** and **why** (cost, security, strategy, replaced-by)
+- **Who depends on it** — rough usage, and which segments/contracts are exposed
+- **The replacement / migration path** (or that there isn't one yet)
+- **Hard constraints** — a forcing date (security, legal, contract), team capacity
+
+## Output Format
+
+### Deprecation policy in one line
+The principle you're committing to (e.g. _"announce → N months deprecated (works, warns) → sunset, with a migration path live before we announce"_).
+
+### Timeline
+
+| Phase | Date / window | What changes | What customers can still do |
+|---|---|---|---|
+| Announce | | nothing breaks; docs + warnings | full use, start migrating |
+| Deprecated | | warnings, no new adoption | migrate |
+| Sunset | | turned off | must have migrated |
+
+Include grace periods and any extension policy for large accounts.
+
+### Tiered messaging
+Segmented by dependence, not one blast:
+- **Tier 1 — heavy/contractual users:** proactive, human (CSM/AM), often a call + tailored plan.
+- **Tier 2 — active users:** direct email + in-product warning + migration guide.
+- **Tier 3 — light/dormant:** changelog, docs banner, deprecation headers.
+
+For each: the core message (what, when, why, what to do), the ask, and the escalation path.
+
+### Migration guide outline
+The structure of the how-to: before/after, step-by-step, code/config examples, a mapping table (old → new), FAQ, and where to get help.
+
+### Channel plan
+Which channels fire at which phase — email, in-product, docs/changelog, API deprecation headers/`Sunset` header, status page, community/social — and the cadence (announce, reminders at intervals, final notice).
+
+### Internal escalation playbook
+The at-risk account list, who owns each, the CSM talking points, the "customer can't migrate in time" decision tree, and the exception/extension approval path.
+
+## Quality Checks
+
+- [ ] A migration path exists and is referenced everywhere before any customer message goes out
+- [ ] Runway is sized to migration difficulty, with grace periods stated
+- [ ] Messaging is tiered by dependence; Tier-1 accounts get a human, not a blast
+- [ ] Every message says what, when, why, and the exact next step
+- [ ] The channel cadence includes reminders and a final notice, not a single announcement
+- [ ] High-risk accounts have a named owner and an escalation/extension path
+
+## Anti-Patterns
+
+- Too little runway for the migration actually required
+- A silent breaking change, or burying it in a changelog nobody reads
+- Announcing before the migration path is live
+- One-size messaging that treats a whale like a dormant free user
+- No plan for the accounts that physically can't migrate in time
+- "Why" that blames the customer or the old system instead of owning the change

package/exports/aider/pm-recruiting/reference-check-script/reference-check-script.md

@@ -0,0 +1,62 @@
+# Reference Check Script Skill
+
+A reference check fails when it's a formality — you call, they say "great to work with," you tick the box. This skill writes a call that actually de-risks the hire: questions that make it *safe and easy* for a referee to be honest, follow-ups that open the gap between polite and true, and a rubric that turns what you hear into a defensible signal.
+
+## Working from a brief
+
+Given the role and what you need to validate, **write the full script** — tailor the questions to the specific concerns (the shaky interview signal, the seniority stretch, the manager-vs-IC question). Default to a ~20–25 minute call structure.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **Role** and level, and the **1–3 things to validate or de-risk** (the open questions from interviews)
+- **Referee relationship** to the candidate (former manager / peer / report / client)
+- **Reference type** — candidate-provided or back-channel (changes how candid you probe)
+
+## Output Format
+
+### Framing (how to open)
+A 2–3 sentence opener that sets candor: confidential, no scripted "sales pitch" needed, you're calibrating not gatekeeping. The single most important move — referees mirror the tone you set.
+
+### Question set (in order)
+Grouped, with the *intent* of each noted:
+1. **Relationship & context** — how they worked together, for how long, on what.
+2. **Scope & performance** — what the candidate actually owned; where they ranked among peers.
+3. **Strengths** — with a concrete example ("tell me about a time…").
+4. **Growth areas** — asked as _"where did they most need to grow / what coaching helped?"_ (not "weaknesses").
+5. **Working style** — how they handle conflict, feedback, ambiguity, pressure.
+6. **The rehire question** — _"Would you hire them again? For what kind of role?"_ — and listen to the hesitation.
+
+### Probing follow-ups
+The second question that opens the gap: "Can you give me an example?" · "How did that compare to others at that level?" · "What would their harshest fair critic say?" · silence (let them fill it).
+
+### Scoring rubric
+
+| Signal | 🟢 Green | 🟡 Yellow | 🔴 Red |
+|---|---|---|---|
+| Specificity | concrete examples | generic praise | evasive / can't recall |
+| Rehire | enthusiastic, unprompted | qualified | hesitation or no |
+| Growth honesty | candid, coachable | vague | defensive / dodged |
+
+Plus a one-line **overall read** and any follow-up to run (e.g. a back-channel if listed refs are all glowing-but-generic).
+
+### Legal & fairness guardrails
+Ask about job performance only. Do **not** ask about age, health/disability, family/pregnancy, religion, national origin, or other protected characteristics. Keep it consistent across candidates so it's comparable and defensible.
+
+## Quality Checks
+
+- [ ] The opener explicitly invites candor (not a box-tick)
+- [ ] Questions are open and non-leading — no "they were a great team player, right?"
+- [ ] At least one question forces a concrete example and one comparative ranking
+- [ ] The rehire question is included and its hesitation is scored, not just its answer
+- [ ] The rubric converts what's heard into 🟢🟡🔴 with an overall read
+- [ ] Protected-class questions are explicitly excluded; the script is consistent across candidates
+
+## Anti-Patterns
+
+- Leading questions that hand the referee the answer
+- Accepting "they were great" without a follow-up for a specific example
+- Only calling candidate-selected references (all curated to be positive)
+- Treating the call as confirmation, not investigation
+- Asking anything about protected characteristics
+- No rubric — a vibe instead of a comparable, documented signal

package/exports/aider/pm-social/community-moderation-policy/community-moderation-policy.md

@@ -0,0 +1,59 @@
+# Community Moderation Policy Skill
+
+A moderation policy fails when it's vague ("be respectful") or applied inconsistently — members can't predict what's allowed, and mods burn out making judgment calls with no backing. This skill writes a policy that is *enforceable*: concrete rules with examples, a ladder that matches consequence to behavior, and the process that makes enforcement feel fair even to the person on the receiving end.
+
+## Working from a brief
+
+Given the community (platform, size, purpose, audience), **write the full policy** — tune severity and tone to the space (a professional Slack ≠ a gaming Discord). Keep the public-facing rules short and human; put the operational detail in the moderator guidelines.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **The community** — platform, rough size, purpose, and audience norms
+- **The values / what "good" looks like** here, and the behaviors you most want to prevent
+- **Team** — how many moderators, volunteer or staff, tools available
+- **Legal/brand constraints** — platform ToS, regulated topics, company brand line
+
+## Output Format
+
+### Code of conduct (public-facing)
+Short, plain, and specific. The core rules stated positively where possible, each with a **one-line example of what crosses the line** so it's not ambiguous. Cover the usual: harassment, hate speech, spam/self-promo, off-topic, NSFW, illegal content — scoped to this community.
+
+### Enforcement ladder
+Consequence matched to behavior and repetition:
+
+| Level | Trigger | Action | Who can apply |
+|---|---|---|---|
+| 1 | first minor / borderline | friendly warning, edit/remove | any mod |
+| 2 | repeat / clear violation | formal warning, temp mute | any mod |
+| 3 | serious or repeated | temp ban (e.g. 7 days) | senior mod |
+| 4 | severe / incorrigible | permanent ban | admin |
+| **Zero-tolerance** | threats, doxxing, CSAM, targeted harassment | immediate ban + report | admin, no warning |
+
+### Appeals process
+How a member contests an action: where to appeal, who reviews (not the acting mod), the timeline, and what can/can't be overturned. Appeals are what make the ladder feel legitimate.
+
+### Moderator guidelines (internal)
+- **Consistency** — decide by the rule, not the person; document every Level 2+ action.
+- **Conflicts** — don't moderate a thread you're personally in; hand off.
+- **Edge cases** — borderline calls, sarcasm/context, brigading and coordinated behavior, when to lock vs remove.
+- **Transparency** — what's communicated to the member vs. handled quietly; a mod log.
+- **Mod wellbeing** — rotation for heavy content, escalation for threats to mods.
+
+## Quality Checks
+
+- [ ] Every rule is concrete enough to predict a call, with an example of the line
+- [ ] The ladder ties specific triggers to specific actions and who may apply them
+- [ ] Severe cases (threats, doxxing, CSAM) are zero-tolerance and route to reporting
+- [ ] An appeals path exists and is reviewed by someone other than the acting mod
+- [ ] Mod guidelines cover consistency, conflicts of interest, and documentation
+- [ ] Tone and severity fit this community; it aligns with the platform ToS
+
+## Anti-Patterns
+
+- Vague rules ("don't be a jerk") with no examples — unenforceable and arbitrary-feeling
+- A single "ban" hammer with no graduated steps for minor issues
+- Inconsistent enforcement by mood or by who the member is
+- No appeals process (every action feels final and unjust)
+- Unwritten rules enforced as if everyone knew them
+- Warning-laddering genuine threats or doxxing instead of acting immediately

package/exports/chatgpt/README.md

@@ -3,7 +3,7 @@
 > Auto-generated from `skills/*/SKILL.md` by `scripts/build-exports.mjs`.
 > **Do not edit these files by hand** — edit the source skill and regenerate.
 
-751 skills exported. Copy a `SYSTEM_PROMPT.md` into the tool to use it.
+754 skills exported. Copy a `SYSTEM_PROMPT.md` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -126,6 +126,7 @@
 | College App Parent Guide | `pm-parents` | `pm-parents/college-app-parent-guide/SYSTEM_PROMPT.md` |
 | College Cost | `pm-calculators` | `pm-calculators/college-cost/SYSTEM_PROMPT.md` |
 | Community Management Playbook | `pm-social` | `pm-social/community-management-playbook/SYSTEM_PROMPT.md` |
+| Community Moderation Policy | `pm-social` | `pm-social/community-moderation-policy/SYSTEM_PROMPT.md` |
 | Company Brief | `pm-jobsearch` | `pm-jobsearch/company-brief/SYSTEM_PROMPT.md` |
 | Company Event Ops | `pm-cowork` | `pm-cowork/company-event-ops/SYSTEM_PROMPT.md` |
 | Comparative Market Analysis | `pm-realestate` | `pm-realestate/comparative-market-analysis/SYSTEM_PROMPT.md` |
@@ -203,6 +204,7 @@
 | Demo Script | `pm-cowork` | `pm-cowork/demo-script/SYSTEM_PROMPT.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/SYSTEM_PROMPT.md` |
 | Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/SYSTEM_PROMPT.md` |
+| Deprecation Comms Plan | `pm-devrel` | `pm-devrel/deprecation-comms-plan/SYSTEM_PROMPT.md` |
 | Design Critique | `pm-design` | `pm-design/design-critique/SYSTEM_PROMPT.md` |
 | Design Handoff Brief | `pm-advanced` | `pm-advanced/design-handoff-brief/SYSTEM_PROMPT.md` |
 | Design System Audit | `pm-design` | `pm-design/design-system-audit/SYSTEM_PROMPT.md` |
@@ -541,6 +543,7 @@
 | Red-Team Review | `pm-cross` | `pm-cross/red-team-review/SYSTEM_PROMPT.md` |
 | Redundancy Consultation | `pm-hr` | `pm-hr/redundancy-consultation/SYSTEM_PROMPT.md` |
 | Refactoring Plan | `pm-craft` | `pm-craft/refactoring-plan/SYSTEM_PROMPT.md` |
+| Reference Check Script | `pm-recruiting` | `pm-recruiting/reference-check-script/SYSTEM_PROMPT.md` |
 | Reference Letter | `pm-lifeadmin` | `pm-lifeadmin/reference-letter/SYSTEM_PROMPT.md` |
 | Reference Request Kit | `pm-layoff` | `pm-layoff/reference-request-kit/SYSTEM_PROMPT.md` |
 | Referral Program | `pm-growth` | `pm-growth/referral-program/SYSTEM_PROMPT.md` |

package/exports/chatgpt/pm-devrel/deprecation-comms-plan/SYSTEM_PROMPT.md

@@ -0,0 +1,65 @@
+# Deprecation Comms Plan Skill
+
+Deprecations go wrong in two ways: too fast (customers get broken and churn angry) or too quiet (they find out when it breaks). This skill plans the wind-down as a *communications program*, not an announcement — enough runway, messaging matched to how much each customer depends on the thing, a real migration path, and a plan for the accounts that will need a human.
+
+## Working from a brief
+
+Given what's being deprecated and why, **produce the full plan** — infer the risk tiers from usage and contract exposure. Right-size the runway to how hard the migration is (an internal flag flip is weeks; a public API is many months). If there's no migration path yet, flag that as a blocker before any announcement.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **What's being deprecated** and **why** (cost, security, strategy, replaced-by)
+- **Who depends on it** — rough usage, and which segments/contracts are exposed
+- **The replacement / migration path** (or that there isn't one yet)
+- **Hard constraints** — a forcing date (security, legal, contract), team capacity
+
+## Output Format
+
+### Deprecation policy in one line
+The principle you're committing to (e.g. _"announce → N months deprecated (works, warns) → sunset, with a migration path live before we announce"_).
+
+### Timeline
+
+| Phase | Date / window | What changes | What customers can still do |
+|---|---|---|---|
+| Announce | | nothing breaks; docs + warnings | full use, start migrating |
+| Deprecated | | warnings, no new adoption | migrate |
+| Sunset | | turned off | must have migrated |
+
+Include grace periods and any extension policy for large accounts.
+
+### Tiered messaging
+Segmented by dependence, not one blast:
+- **Tier 1 — heavy/contractual users:** proactive, human (CSM/AM), often a call + tailored plan.
+- **Tier 2 — active users:** direct email + in-product warning + migration guide.
+- **Tier 3 — light/dormant:** changelog, docs banner, deprecation headers.
+
+For each: the core message (what, when, why, what to do), the ask, and the escalation path.
+
+### Migration guide outline
+The structure of the how-to: before/after, step-by-step, code/config examples, a mapping table (old → new), FAQ, and where to get help.
+
+### Channel plan
+Which channels fire at which phase — email, in-product, docs/changelog, API deprecation headers/`Sunset` header, status page, community/social — and the cadence (announce, reminders at intervals, final notice).
+
+### Internal escalation playbook
+The at-risk account list, who owns each, the CSM talking points, the "customer can't migrate in time" decision tree, and the exception/extension approval path.
+
+## Quality Checks
+
+- [ ] A migration path exists and is referenced everywhere before any customer message goes out
+- [ ] Runway is sized to migration difficulty, with grace periods stated
+- [ ] Messaging is tiered by dependence; Tier-1 accounts get a human, not a blast
+- [ ] Every message says what, when, why, and the exact next step
+- [ ] The channel cadence includes reminders and a final notice, not a single announcement
+- [ ] High-risk accounts have a named owner and an escalation/extension path
+
+## Anti-Patterns
+
+- Too little runway for the migration actually required
+- A silent breaking change, or burying it in a changelog nobody reads
+- Announcing before the migration path is live
+- One-size messaging that treats a whale like a dormant free user
+- No plan for the accounts that physically can't migrate in time
+- "Why" that blames the customer or the old system instead of owning the change

package/exports/chatgpt/pm-recruiting/reference-check-script/SYSTEM_PROMPT.md

@@ -0,0 +1,62 @@
+# Reference Check Script Skill
+
+A reference check fails when it's a formality — you call, they say "great to work with," you tick the box. This skill writes a call that actually de-risks the hire: questions that make it *safe and easy* for a referee to be honest, follow-ups that open the gap between polite and true, and a rubric that turns what you hear into a defensible signal.
+
+## Working from a brief
+
+Given the role and what you need to validate, **write the full script** — tailor the questions to the specific concerns (the shaky interview signal, the seniority stretch, the manager-vs-IC question). Default to a ~20–25 minute call structure.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **Role** and level, and the **1–3 things to validate or de-risk** (the open questions from interviews)
+- **Referee relationship** to the candidate (former manager / peer / report / client)
+- **Reference type** — candidate-provided or back-channel (changes how candid you probe)
+
+## Output Format
+
+### Framing (how to open)
+A 2–3 sentence opener that sets candor: confidential, no scripted "sales pitch" needed, you're calibrating not gatekeeping. The single most important move — referees mirror the tone you set.
+
+### Question set (in order)
+Grouped, with the *intent* of each noted:
+1. **Relationship & context** — how they worked together, for how long, on what.
+2. **Scope & performance** — what the candidate actually owned; where they ranked among peers.
+3. **Strengths** — with a concrete example ("tell me about a time…").
+4. **Growth areas** — asked as _"where did they most need to grow / what coaching helped?"_ (not "weaknesses").
+5. **Working style** — how they handle conflict, feedback, ambiguity, pressure.
+6. **The rehire question** — _"Would you hire them again? For what kind of role?"_ — and listen to the hesitation.
+
+### Probing follow-ups
+The second question that opens the gap: "Can you give me an example?" · "How did that compare to others at that level?" · "What would their harshest fair critic say?" · silence (let them fill it).
+
+### Scoring rubric
+
+| Signal | 🟢 Green | 🟡 Yellow | 🔴 Red |
+|---|---|---|---|
+| Specificity | concrete examples | generic praise | evasive / can't recall |
+| Rehire | enthusiastic, unprompted | qualified | hesitation or no |
+| Growth honesty | candid, coachable | vague | defensive / dodged |
+
+Plus a one-line **overall read** and any follow-up to run (e.g. a back-channel if listed refs are all glowing-but-generic).
+
+### Legal & fairness guardrails
+Ask about job performance only. Do **not** ask about age, health/disability, family/pregnancy, religion, national origin, or other protected characteristics. Keep it consistent across candidates so it's comparable and defensible.
+
+## Quality Checks
+
+- [ ] The opener explicitly invites candor (not a box-tick)
+- [ ] Questions are open and non-leading — no "they were a great team player, right?"
+- [ ] At least one question forces a concrete example and one comparative ranking
+- [ ] The rehire question is included and its hesitation is scored, not just its answer
+- [ ] The rubric converts what's heard into 🟢🟡🔴 with an overall read
+- [ ] Protected-class questions are explicitly excluded; the script is consistent across candidates
+
+## Anti-Patterns
+
+- Leading questions that hand the referee the answer
+- Accepting "they were great" without a follow-up for a specific example
+- Only calling candidate-selected references (all curated to be positive)
+- Treating the call as confirmation, not investigation
+- Asking anything about protected characteristics
+- No rubric — a vibe instead of a comparable, documented signal

package/exports/chatgpt/pm-social/community-moderation-policy/SYSTEM_PROMPT.md

@@ -0,0 +1,59 @@
+# Community Moderation Policy Skill
+
+A moderation policy fails when it's vague ("be respectful") or applied inconsistently — members can't predict what's allowed, and mods burn out making judgment calls with no backing. This skill writes a policy that is *enforceable*: concrete rules with examples, a ladder that matches consequence to behavior, and the process that makes enforcement feel fair even to the person on the receiving end.
+
+## Working from a brief
+
+Given the community (platform, size, purpose, audience), **write the full policy** — tune severity and tone to the space (a professional Slack ≠ a gaming Discord). Keep the public-facing rules short and human; put the operational detail in the moderator guidelines.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **The community** — platform, rough size, purpose, and audience norms
+- **The values / what "good" looks like** here, and the behaviors you most want to prevent
+- **Team** — how many moderators, volunteer or staff, tools available
+- **Legal/brand constraints** — platform ToS, regulated topics, company brand line
+
+## Output Format
+
+### Code of conduct (public-facing)
+Short, plain, and specific. The core rules stated positively where possible, each with a **one-line example of what crosses the line** so it's not ambiguous. Cover the usual: harassment, hate speech, spam/self-promo, off-topic, NSFW, illegal content — scoped to this community.
+
+### Enforcement ladder
+Consequence matched to behavior and repetition:
+
+| Level | Trigger | Action | Who can apply |
+|---|---|---|---|
+| 1 | first minor / borderline | friendly warning, edit/remove | any mod |
+| 2 | repeat / clear violation | formal warning, temp mute | any mod |
+| 3 | serious or repeated | temp ban (e.g. 7 days) | senior mod |
+| 4 | severe / incorrigible | permanent ban | admin |
+| **Zero-tolerance** | threats, doxxing, CSAM, targeted harassment | immediate ban + report | admin, no warning |
+
+### Appeals process
+How a member contests an action: where to appeal, who reviews (not the acting mod), the timeline, and what can/can't be overturned. Appeals are what make the ladder feel legitimate.
+
+### Moderator guidelines (internal)
+- **Consistency** — decide by the rule, not the person; document every Level 2+ action.
+- **Conflicts** — don't moderate a thread you're personally in; hand off.
+- **Edge cases** — borderline calls, sarcasm/context, brigading and coordinated behavior, when to lock vs remove.
+- **Transparency** — what's communicated to the member vs. handled quietly; a mod log.
+- **Mod wellbeing** — rotation for heavy content, escalation for threats to mods.
+
+## Quality Checks
+
+- [ ] Every rule is concrete enough to predict a call, with an example of the line
+- [ ] The ladder ties specific triggers to specific actions and who may apply them
+- [ ] Severe cases (threats, doxxing, CSAM) are zero-tolerance and route to reporting
+- [ ] An appeals path exists and is reviewed by someone other than the acting mod
+- [ ] Mod guidelines cover consistency, conflicts of interest, and documentation
+- [ ] Tone and severity fit this community; it aligns with the platform ToS
+
+## Anti-Patterns
+
+- Vague rules ("don't be a jerk") with no examples — unenforceable and arbitrary-feeling
+- A single "ban" hammer with no graduated steps for minor issues
+- Inconsistent enforcement by mood or by who the member is
+- No appeals process (every action feels final and unjust)
+- Unwritten rules enforced as if everyone knew them
+- Warning-laddering genuine threats or doxxing instead of acting immediately

package/exports/cline/README.md

@@ -3,7 +3,7 @@
 > Auto-generated from `skills/*/SKILL.md` by `scripts/build-exports.mjs`.
 > **Do not edit these files by hand** — edit the source skill and regenerate.
 
-751 skills exported. Copy a `.md rule` into the tool to use it.
+754 skills exported. Copy a `.md rule` into the tool to use it.
 
 | Skill | Bundle | Path |
 |---|---|---|
@@ -126,6 +126,7 @@
 | College App Parent Guide | `pm-parents` | `pm-parents/college-app-parent-guide/college-app-parent-guide.md` |
 | College Cost | `pm-calculators` | `pm-calculators/college-cost/college-cost.md` |
 | Community Management Playbook | `pm-social` | `pm-social/community-management-playbook/community-management-playbook.md` |
+| Community Moderation Policy | `pm-social` | `pm-social/community-moderation-policy/community-moderation-policy.md` |
 | Company Brief | `pm-jobsearch` | `pm-jobsearch/company-brief/company-brief.md` |
 | Company Event Ops | `pm-cowork` | `pm-cowork/company-event-ops/company-event-ops.md` |
 | Comparative Market Analysis | `pm-realestate` | `pm-realestate/comparative-market-analysis/comparative-market-analysis.md` |
@@ -203,6 +204,7 @@
 | Demo Script | `pm-cowork` | `pm-cowork/demo-script/demo-script.md` |
 | Dependency Audit | `pm-engineering` | `pm-engineering/dependency-audit/dependency-audit.md` |
 | Dependency Conflict Resolver | `pm-engineering` | `pm-engineering/dependency-conflict-resolver/dependency-conflict-resolver.md` |
+| Deprecation Comms Plan | `pm-devrel` | `pm-devrel/deprecation-comms-plan/deprecation-comms-plan.md` |
 | Design Critique | `pm-design` | `pm-design/design-critique/design-critique.md` |
 | Design Handoff Brief | `pm-advanced` | `pm-advanced/design-handoff-brief/design-handoff-brief.md` |
 | Design System Audit | `pm-design` | `pm-design/design-system-audit/design-system-audit.md` |
@@ -541,6 +543,7 @@
 | Red-Team Review | `pm-cross` | `pm-cross/red-team-review/red-team-review.md` |
 | Redundancy Consultation | `pm-hr` | `pm-hr/redundancy-consultation/redundancy-consultation.md` |
 | Refactoring Plan | `pm-craft` | `pm-craft/refactoring-plan/refactoring-plan.md` |
+| Reference Check Script | `pm-recruiting` | `pm-recruiting/reference-check-script/reference-check-script.md` |
 | Reference Letter | `pm-lifeadmin` | `pm-lifeadmin/reference-letter/reference-letter.md` |
 | Reference Request Kit | `pm-layoff` | `pm-layoff/reference-request-kit/reference-request-kit.md` |
 | Referral Program | `pm-growth` | `pm-growth/referral-program/referral-program.md` |

package/exports/cline/pm-devrel/deprecation-comms-plan/deprecation-comms-plan.md

@@ -0,0 +1,65 @@
+# Deprecation Comms Plan Skill
+
+Deprecations go wrong in two ways: too fast (customers get broken and churn angry) or too quiet (they find out when it breaks). This skill plans the wind-down as a *communications program*, not an announcement — enough runway, messaging matched to how much each customer depends on the thing, a real migration path, and a plan for the accounts that will need a human.
+
+## Working from a brief
+
+Given what's being deprecated and why, **produce the full plan** — infer the risk tiers from usage and contract exposure. Right-size the runway to how hard the migration is (an internal flag flip is weeks; a public API is many months). If there's no migration path yet, flag that as a blocker before any announcement.
+
+## Required Inputs
+
+Ask for (if not provided, else infer and label the assumption):
+- **What's being deprecated** and **why** (cost, security, strategy, replaced-by)
+- **Who depends on it** — rough usage, and which segments/contracts are exposed
+- **The replacement / migration path** (or that there isn't one yet)
+- **Hard constraints** — a forcing date (security, legal, contract), team capacity
+
+## Output Format
+
+### Deprecation policy in one line
+The principle you're committing to (e.g. _"announce → N months deprecated (works, warns) → sunset, with a migration path live before we announce"_).
+
+### Timeline
+
+| Phase | Date / window | What changes | What customers can still do |
+|---|---|---|---|
+| Announce | | nothing breaks; docs + warnings | full use, start migrating |
+| Deprecated | | warnings, no new adoption | migrate |
+| Sunset | | turned off | must have migrated |
+
+Include grace periods and any extension policy for large accounts.
+
+### Tiered messaging
+Segmented by dependence, not one blast:
+- **Tier 1 — heavy/contractual users:** proactive, human (CSM/AM), often a call + tailored plan.
+- **Tier 2 — active users:** direct email + in-product warning + migration guide.
+- **Tier 3 — light/dormant:** changelog, docs banner, deprecation headers.
+
+For each: the core message (what, when, why, what to do), the ask, and the escalation path.
+
+### Migration guide outline
+The structure of the how-to: before/after, step-by-step, code/config examples, a mapping table (old → new), FAQ, and where to get help.
+
+### Channel plan
+Which channels fire at which phase — email, in-product, docs/changelog, API deprecation headers/`Sunset` header, status page, community/social — and the cadence (announce, reminders at intervals, final notice).
+
+### Internal escalation playbook
+The at-risk account list, who owns each, the CSM talking points, the "customer can't migrate in time" decision tree, and the exception/extension approval path.
+
+## Quality Checks
+
+- [ ] A migration path exists and is referenced everywhere before any customer message goes out
+- [ ] Runway is sized to migration difficulty, with grace periods stated
+- [ ] Messaging is tiered by dependence; Tier-1 accounts get a human, not a blast
+- [ ] Every message says what, when, why, and the exact next step
+- [ ] The channel cadence includes reminders and a final notice, not a single announcement
+- [ ] High-risk accounts have a named owner and an escalation/extension path
+
+## Anti-Patterns
+
+- Too little runway for the migration actually required
+- A silent breaking change, or burying it in a changelog nobody reads
+- Announcing before the migration path is live
+- One-size messaging that treats a whale like a dormant free user
+- No plan for the accounts that physically can't migrate in time
+- "Why" that blames the customer or the old system instead of owning the change