Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Portfolio Setup

ASecurity

Stand up centralized multi-repo, multi-person activity tracking for a team. Use when a team works across several GitHub repos and needs one place to see who did what — and a supervisor needs a manage-the-team roll-up that a single-repo activity log can't provide. Walks choosing a hub repo, writing team-portfolio.json (repos + roster + cross-repo projects), wiring the scheduled GitHub Action and the on-demand command, picking a GitHub token, and optionally enabling a hand-maintained narrative ...

7 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentspythongoshellgitapi

Works with

api

Security Analysis

A100/100

Scanned 9/23/2026

$npx -y skills add mcorbett51090/RavenClaude --skill portfolio-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Portfolio Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Portfolio Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mcorbett51090-portfolio-setup/badge)](https://www.skillsdirectory.com/skills/mcorbett51090-portfolio-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: portfolio-setup
description: "Stand up centralized multi-repo, multi-person activity tracking for a team. Use when a team works across several GitHub repos and needs one place to see who did what — and a supervisor needs a manage-the-team roll-up that a single-repo activity log can't provide. Walks choosing a hub repo, writing team-portfolio.json (repos + roster + cross-repo projects), wiring the scheduled GitHub Action and the on-demand command, picking a GitHub token, and optionally enabling a hand-maintained narrative layer."
---

# Skill: Portfolio setup

Goal: a working centralized tracker in well under an hour. The hard truth up front —
**a per-repo activity log can never see the repo next door.** GitHub already attributes
every commit, PR, and issue to a person across all repos; this plugin just reads it and
rolls it up. So the design is "one small hub that pulls from GitHub," not "a log inside
each repo."

## Step 0 — Decide where the hub lives

The hub is one repo that holds the config + the generated reports + the dashboard. It
does **not** need to be a repo anyone codes in. Options, smaller-blast-radius first:

- **A dedicated `team-portfolio` repo** (recommended) — clean, nothing else touches it,
  easy to give a supervisor read access without granting anything else.
- **An existing "home base" repo** the team already reads.

The repos being *tracked* need no changes at all — they're read through the API.

## Step 1 — Write the config

Copy [`templates/team-portfolio.json`](../../templates/team-portfolio.json) to the hub
repo root as `team-portfolio.json` and edit:

- `repos` — every `owner/name` to monitor (public or private).
- `team` — one entry per person: `login` (GitHub username), `name`, optional `role`.
- `supervisor` — optional; frames the roll-up as a manage-the-team view.
- `projects` — cross-repo projects (see the `cross-repo-project-tracking` skill).
- `window_days` — default lookback for the weekly tracker (7 is typical).

**Never put a token in this file.** It is read from the environment only.

## Step 2 — Pick a token

The collector reads `PORTFOLIO_TOKEN` → `GITHUB_TOKEN` → `GH_TOKEN`.

| Situation | Token |
| --- | --- |
| All tracked repos are public | the Action's built-in `GITHUB_TOKEN` is enough |
| Any private repo, or repos in another account/org | a **fine-grained PAT** with read on those repos, stored as the `PORTFOLIO_TOKEN` secret |

Least privilege: read-only, scoped to exactly the tracked repos.

## Step 3 — Automate it (scheduled + on-demand)

- **Scheduled:** copy [`templates/portfolio-tracker.yml`](../../templates/portfolio-tracker.yml)
  into the hub repo at `.github/workflows/portfolio-tracker.yml`. It refreshes weekly
  (Mondays) + nightly and commits the reports + dashboard back — the diff is the record.
- **On-demand:** run `/portfolio-refresh` (or the three scripts directly) anytime you want
  the current picture.

## Step 4 — Verify with the sample, then go live

Prove the renderers work before any token is involved, using the bundled fixture:

```shell
PLUGIN=~/RavenClaude/plugins/team-portfolio
python3 "$PLUGIN/scripts/portfolio-report.py"    --activity "$PLUGIN/templates/sample-activity.json" --out-dir /tmp/reports
python3 "$PLUGIN/scripts/portfolio-dashboard.py" --activity "$PLUGIN/templates/sample-activity.json" --out /tmp/portfolio.html
```

Then do a real collect against your config (Step 1) with a token in the environment.

## Step 5 — Optional narrative layer

If your manager wants context beyond the raw counts (decisions, blockers, "why"), set
`narrative.enabled: true` and drop one `*.md` per note into `narrative.dir` (template:
[`templates/activity-narrative.md`](../../templates/activity-narrative.md)). The report
generator folds them into the weekly tracker under a **Notes** heading. Leave it off to
stay purely GitHub-driven.

## What the supervisor reads

- `reports/weekly-tracker.md` — per-person, per-repo summary for the window.
- `reports/project-status.md` — cross-repo project roll-up.
- `portfolio.html` — interactive dashboard (open locally or publish to GitHub Pages).

## Anti-patterns

- Putting a token in `team-portfolio.json` (it goes in env/secrets — always).
- Adding a tracking log *inside each tracked repo* (the original problem — it can't see
  across repos; that's the whole reason for the hub).
- A PAT with org-admin scope when read-only on a handful of repos is all that's needed.

Attribution

mcorbett51090mcorbett51090
View sourceSee grades on GitHubMore from mcorbett51090 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →