portfolio-aggregator

星标4

分支0

更新时间2026年7月18日 15:25

Roll up findings across many subjects into one organization-level view — top waste patterns by frequency, teams/services ranked by open high-severity findings, SCI-term distribution, and portfolio-wide quick wins. Use this skill whenever the user has findings files from multiple audits/repos/teams and asks for the big picture, an engineering-org sustainability posture, a CTO/leadership rollup, or "where should we focus first across everything". Part of Lean Agentic AI Skills; a transformer emitting a portfolio findings summary.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

来源

navveenb

navveenb/lean-agentic-ai-skills

打开 GitHub 仓库查看创作者相关仓库

下载

Portfolio Aggregator

Transformer skill — the CTO consumer. Input: many findings files (different subjects, producers, dates). Output: a portfolio summary (structured JSON + prose) that lean-report-writer, lean-deck-builder, or lean-dashboard can render at org level.

Single audits answer "what's wrong here"; the portfolio answers "what's wrong everywhere, and what one fix pays off most times". Frequency across subjects is the signal no single audit can see.

Subject type: emit subject.type: "organization" in findings.

Aggregation procedure

Normalize and inventory — subjects, producers, audit dates; flag stale audits (older than a stated freshness window) so the rollup doesn't present last year's posture as current.
Pattern frequency — group findings by pattern URL / finding id family across subjects: "images without modern formats: present in 14 of 20 audited sites" is the portfolio's headline material. Counts are real; report them with the denominator always attached.
Posture table — per subject/team: open findings by severity, quick-win count, last-audit date. Ranked by open high-severity count — with the fairness rule below.
SCI-term distribution — where the portfolio's levers sit (mostly E? no one touching I?) — this often reveals that nobody owns scheduling/region decisions.
Leverage list — fixes that recur across many subjects (a shared platform fix, a paved-road change, one CI template) ranked by (frequency × severity ÷ effort). The portfolio's job is finding the one change that closes twenty findings.
Trend layer (when findings-diff outputs or dated audit pairs exist) — org-level resolved/new counts per period.

Fairness & honesty rules

More audits ⇒ more findings: never rank teams without normalizing for audit coverage and subject count, and say so on the ranking itself — otherwise the team that audited most looks worst, which teaches teams to stop auditing. Different producers have different signature densities; cross-domain comparisons (a web team vs a data team) are noted as apples-to-oranges. No composite org score — the module's no-single-number rule holds hardest exactly here, where the temptation is greatest. Methodologies are heterogeneous by nature at portfolio level: the summary carries a methodology appendix listing each source audit's scope.

Not this skill's job

Producing audits, rendering the deck/report/dashboard (consumers take this skill's output), assigning the work (findings-to-tickets per subject).

同仓库更多 Skills

同仓库

agentic-loop-auditor

navveenb/lean-agentic-ai-skills

Audit agent frameworks and agentic workflows for token-burning loop pathologies — unbounded retries, excessive planning depth, tool-call thrashing, context snowballing, missing loop budgets and kill switches. Use this skill whenever the user shares agent configs or traces (LangChain/LangGraph, CrewAI, AutoGen, custom loops), complains an agent is slow or expensive, or is designing any autonomous/multi-step agent. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

ai-eval-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit AI evaluation infrastructure for wasted compute — full benchmark suites re-run on unchanged cases, LLM-as-judge grading without caching, oversized judge models, redundant eval passes per commit, and missing result reuse. Use this skill whenever the user shares eval harness configs or CI eval steps, complains that evals are slow or expensive, mentions LLM-as-judge costs, or runs benchmark suites on every change. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

api-efficiency-audit

navveenb/lean-agentic-ai-skills

Audit API design for chattiness and over-fetching — REST endpoints requiring N calls per screen, GraphQL resolvers with N+1 fan-out, default-everything payloads, missing pagination and field selection, provider-side polling where webhooks serve, and uncompressed responses. Use this skill whenever the user shares API schemas (OpenAPI, GraphQL SDL), resolver code, endpoint designs, or asks why clients make too many calls or payloads are heavy. Part of Lean Agentic AI Skills; emits lean-findings.json.

2026-07-184

caching-strategy-designer

navveenb/lean-agentic-ai-skills

Design caching layers so work is done once, not per request — HTTP/CDN caching, application-level caches (Redis/Memcached), computed-result caching, and cache-invalidation strategy. Use this skill whenever the user wants to add caching, asks why the same work is recomputed, designs a read-heavy system, or an audit skill (db-efficiency-audit, web-carbon-audit) flags uncached repeated work. Part of Lean Agentic AI Skills; emits a cache design plus lean-findings.json.

2026-07-184

carbon-aware-scheduler

navveenb/lean-agentic-ai-skills

Design time-shifting of flexible workloads (batch jobs, CI, training, backups, crons) to hours and regions when grid electricity is cleanest, using carbon-intensity signals like Electricity Maps, WattTime, or the Carbon Aware SDK. Use this skill whenever the user mentions carbon-aware computing, scheduling flexible/deferrable jobs, demand shifting, running workloads when energy is clean, or asks how to reduce the carbon intensity (not just amount) of their compute. Part of Lean Agentic AI Skills; emits schedule designs plus lean-findings.json.

2026-07-184

carbon-budget-designer

navveenb/lean-agentic-ai-skills

Design per-feature and per-service efficiency budgets — page-weight budgets, token budgets per AI feature, query budgets per endpoint, GPU-hour budgets per training project — with owners, review checkpoints, and enforcement hooks. Use this skill whenever the user wants sustainability targets for teams, asks how to keep efficiency from regressing organizationally, mentions performance-budget-style governance for carbon/energy, or is setting engineering standards. Part of Lean Agentic AI Skills; an advisor emitting budget definitions plus lean-findings.json.

2026-07-184

name

portfolio-aggregator

description

Portfolio Aggregator

Single audits answer "what's wrong here"; the portfolio answers "what's wrong everywhere, and what one fix pays off most times". Frequency across subjects is the signal no single audit can see.

Subject type: emit subject.type: "organization" in findings.

Aggregation procedure

Normalize and inventory — subjects, producers, audit dates; flag stale audits (older than a stated freshness window) so the rollup doesn't present last year's posture as current.
Pattern frequency — group findings by pattern URL / finding id family across subjects: "images without modern formats: present in 14 of 20 audited sites" is the portfolio's headline material. Counts are real; report them with the denominator always attached.
Posture table — per subject/team: open findings by severity, quick-win count, last-audit date. Ranked by open high-severity count — with the fairness rule below.
SCI-term distribution — where the portfolio's levers sit (mostly E? no one touching I?) — this often reveals that nobody owns scheduling/region decisions.
Leverage list — fixes that recur across many subjects (a shared platform fix, a paved-road change, one CI template) ranked by (frequency × severity ÷ effort). The portfolio's job is finding the one change that closes twenty findings.
Trend layer (when findings-diff outputs or dated audit pairs exist) — org-level resolved/new counts per period.

Fairness & honesty rules

Not this skill's job

Producing audits, rendering the deck/report/dashboard (consumers take this skill's output), assigning the work (findings-to-tickets per subject).