Communitygithub.com

majiayu000/claude-skill-registry

Run portfolio support like an on-call ops function with measurable outcomes: intake requests, ship intros, recruiting help, board prep, and close-the-loop tracking. Every request gets a resolution and outcome measurement.

Qu'est-ce que claude-skill-registry ?

claude-skill-registry is a Claude Code agent skill that run portfolio support like an on-call ops function with measurable outcomes: intake requests, ship intros, recruiting help, board prep, and close-the-loop tracking. Every request gets a resolution and outcome measurement.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/majiayu000/claude-skill-registry/tree/HEAD/skills/business/portfolio-support-ops

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

Portfolio support ops

When to use

Use this skill when:

  • A portfolio company asks for help (hiring, customers, partners, strategy)
  • You're prepping for a board meeting or quarterly check-in
  • You want to systematize support so it compounds over time

Inputs you should request (only if missing)

  • The specific request (what outcome, by when)
  • Company stage and immediate priorities
  • Target ICP / customer list (if request is GTM)
  • Hiring priorities and role specs (if request is recruiting)
  • Any constraints (confidentiality, competitor conflicts)

Outputs you must produce

  1. Clarified request (what "done" means, measurable)
  2. Action plan (owner, next step, due date, SLA)
  3. Delivered help (intros made, candidates sourced, docs delivered)
  4. Close-the-loop note (did it work? outcome measured)
  5. Updated help menu (company priorities refreshed)

Hard rule: Every request gets a resolution within SLA and an outcome measurement.

Templates:

  • assets/help-menu.md
  • assets/request-intake.md
  • assets/intro-template.md
  • assets/board-prep.md

SLA by request type

TypePriorityResponse SLAResolution SLAOutcome measurement
Fundraising supportP04 hours48 hoursMeetings scheduled, term sheets received
Key hire closingP04 hours1 weekOffer accepted Y/N
Customer escalationP04 hours48 hoursIssue resolved Y/N
Customer introP124 hours1 weekIntro made, meeting held, outcome
Recruiting pipelineP124 hours2 weeksCandidates submitted, interviews, hires
Partner introP124 hours1 weekIntro made, partnership status
Strategy/advisoryP248 hours1 weekDeliverable shipped, feedback received
Market intelP248 hours1 weekReport delivered, usefulness rated

Procedure

1) Build a "help menu" per company (refresh quarterly)

Every portfolio company gets a living doc with:

# [Company] Help Menu
Last updated: YYYY-MM-DD

## Current priorities (this quarter)
1. [Priority 1]
2. [Priority 2]
3. [Priority 3]

## Hiring needs
| Role | Ideal profile | Urgency | Status |
|---|---|---|---|
| | | P0/P1/P2 | Open/Filled |

## Customer targets
| Account | Buyer persona | Why they need this | Intro path |
|---|---|---|---|

## Partnership targets
| Partner | Type | Value to company | Status |
|---|---|---|---|

## Key metrics (baseline)
| Metric | Current | Target | Trend |
|---|---|---|---|

## Board meeting schedule
- Next board: [date]
- Materials due: [date]

## Support log (last 5)
| Date | Request | Outcome | Impact |
|---|---|---|---|

2) Intake requests with structured format

For every request, capture:

FieldValue
Company
Requester
Request typeHiring / Customer / Partner / Strategy / Fundraising / Other
Goal (one sentence)
"Done" looks like
Deadline
PriorityP0 / P1 / P2
Owner
SLAResponse: X hours, Resolution: X days
Next step
Constraints

3) Execute value actions with tracking

Customer intros (highest leverage):

  1. Confirm the target account and buyer persona
  2. Check your network for warm paths (1st degree > 2nd degree > cold)
  3. Send structured intro request to connector:
    • Why the match is relevant now
    • What the ask is (15-min chat, design partner, pilot, etc.)
    • Suggested time window
  4. Track: Intro made -> Meeting held -> Outcome (pilot/deal/pass)

Recruiting support:

  1. Confirm role scorecard (must-have vs nice-to-have)
  2. Source 10-20 candidate targets (companies + titles)
  3. Identify warm paths (your network, portfolio network)
  4. Track pipeline weekly:
    • Candidates identified
    • Outreach sent
    • Responded
    • Screened
    • Interviewed
    • Offers
    • Accepted

Fundraising support:

  1. Review materials (deck, data room)
  2. Build target investor list with warm paths
  3. Make intros with context (why this investor, why now)
  4. Track: Intros made -> Meetings -> Follow-ups -> Term sheets

4) Close the loop with outcome measurement

After every request resolution, document:

FieldValue
Request ID
Resolution date
Within SLA?Yes / No
OutcomeSuccess / Partial / Failed
ImpactHigh / Medium / Low
Evidence
Founder feedback
Learnings

Impact definitions:

  • High: Directly contributed to revenue, hire, or funding
  • Medium: Advanced a priority, saved founder time
  • Low: Helpful but not critical path

5) Board meeting support

Before the meeting (1 week out):

  • Review the deck
  • Pull 5 questions that matter (not softballs)
  • Prepare a 1-page competitive/market update
  • Identify 1-2 ways you can help this quarter

After the meeting (within 48 hours):

  • Capture action items with owners and dates
  • Send follow-up with your commitments
  • Update help menu based on new priorities

6) Quarterly review per company

Every quarter, review:

  • Requests handled: count by type
  • SLA performance: % within SLA
  • Outcomes: % success rate
  • Impact: High/Medium/Low distribution
  • NPS: Would founder recommend your support?

Measuring support effectiveness

Track at the fund level:

MetricTargetHow to measure
Response SLA hit rate>90%% requests responded within SLA
Resolution SLA hit rate>80%% requests resolved within SLA
Outcome success rate>70%% requests with Success outcome
High-impact rate>30%% requests rated High impact
Founder NPS>50Quarterly survey
Intros -> meetings>60%% intros that result in meeting
Candidates -> interviews>20%% sourced candidates interviewed

Salesforce logging (recommended)

Track portfolio support in Salesforce via Activities on the Account:

  • Log each support request as a Task (open until resolved)
  • Log each action (intro, candidate submission) as an Activity
  • Tag by type: hiring / customer / partner / strategy / fundraising
  • Record outcome and impact in Activity notes
  • Link to Contacts for intros made

If you need API workflows, use salesforce-crm-ops.

References

  • Mark Suster has useful public writing on boards and how they function in practice.

Edge cases

  • If the ask is vague: ask "What does success look like next week?" before proceeding.
  • If you can't help quickly: provide an alternative (another operator, another firm, or a small experiment) within SLA.
  • If the founder doesn't close the loop: proactively check in at resolution SLA deadline.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

majiayu000/claude-skill-registry

Builds, edit or validate Agent Skill through conversational discovery. Use when the user requests to "Create an Agent", "Optimize an Agent" or "Edit an Agent".

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD agents while maintaining compliance

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Edit existing BMAD modules while maintaining coherence

majiayu000/claude-skill-registry

Analyzes current state and user query to answer BMad questions or recommend the next workflow or agent. Use when user says what should I do next, what do I do now, or asks a question about BMad

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Build AI agents with Google ADK Python (Agent Development Kit). Use for multi-agent systems, workflow agents (sequential/parallel/loop), Vertex AI deployment, tool integration, human-in-the-loop.

majiayu000/claude-skill-registry

Portfolio allocation and rebalancing optimizer. Manages asset allocation across stocks/cash/bonds, performs periodic rebalancing, and ensures diversification according to market regime and risk tolerance.

majiayu000/claude-skill-registry

Create a hilarious and ultra-realistic video of an anthropomorphic animal acting like a human vlogger in a real-world setting.

majiayu000/claude-skill-registry

Speech-to-text transcription and translation via OpenAI Audio API -- models, response formats, timestamps, prompting, streaming, chunking, and diarization

majiayu000/claude-skill-registry

This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.

majiayu000/claude-skill-registry

小省导购员数字人带货版即梦视频提示词生成系统,基于四大智能体协同(提示词生成师、质量管控师、知识库运维师、跨环节适配师),按照"主体+运动+场景+(镜头语言+光影+氛围)"公式输出中英文双版提示词,适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性,支持知识库智能复用和跨工具适配(Suno音乐、AI绘画),为数字人带货视频提供高质量提示词生成服务。

majiayu000/claude-skill-registry

Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Analyze images/audio/video with Gemini API (better vision than Claude). Generate images (Imagen 4), videos (Veo 3). Use for vision analysis, transcription, OCR, design extraction, multimodal AI.

majiayu000/claude-skill-registry

Conduct domain and industry research. Use when the user says "lets create a research report on [domain or industry]

majiayu000/claude-skill-registry

Conduct market research on competition and customers. Use when the user says "create a market research report about [business idea]".

majiayu000/claude-skill-registry

Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]".

majiayu000/claude-skill-registry

Skill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.

Skills associés