foundry-dev
claudeSenior engineering: architecture, functional design, protocols, security, integrations, UX/a11y, Angular, Spring Boot, databases, API and service versioning.
17 skills · 19 agents
Everything around the project rather than inside it: positioning and messaging, launch and audience, fundraising narrative and funder targeting, personal reputation, and finding collaborators in your own field.
Plugin foundry-growth from marketplace foundry in fedcal/foundry. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
audit-personal-brandA reproducible audit of what a stranger actually finds when they look you up, run against one named audience and one named decision — surface enumeration in two passes (an unpersonalised one you run, a logged-out one the person runs), a claim ledger in which every assertion is either backed by an ar
build-audienceTurn work that already happened into a publishing cadence that survives — measure the real hours available, mine the repository for artifacts that are already 70% written (ADRs, reverts, incidents, benchmarks, deletions, hard bugs), convert that inventory into a dated editorial backlog, size the cad
find-collaboratorsFind the right person to work with in your own field, in the order that actually works — the gap named as exactly one of skill, capacity, credibility or access with evidence from this repository, the offer and the non-negotiable terms written down before any name is looked at, candidates derived fro
plan-launchPlan a public launch that survives contact with strangers — a hard readiness gate run on a pristine checkout before any date is defended, success thresholds agreed in numbers before the date rather than rationalised after it, channels chosen from evidence of where the audience already is with each c
position-projectDecide who a project is for, the one sentence that claims it, what it is deliberately not, how it differs from the real alternatives including doing nothing, and the messaging hierarchy underneath — starting from what the repository actually does rather than what its author says it does, and ending
prepare-fundraiseDecide whether to raise at all, and only then get ready to ask — a readiness verdict built from an evidence inventory of the repository's real numbers, the right funding type for this shape of project, funder targeting verified live from each programme's own page, a narrative and a deck argument in
audience-builderSustained attention rather than a one-day launch spike — an editorial cadence sized to the hours the person actually has, an artifact backlog mined from engineering work that already happened (the design decision, the incident, the benchmark, the thing that did not work), artifact-to-channel matchin
collaborator-scoutFinding the right people to work with inside your own field, and being findable by them — naming the gap precisely (skill, capacity, credibility or access), writing down what you offer before you look at anyone, deriving candidates from evidence of what people actually published, shipped, answered,
fundraising-strategistMatching a project to the right kind of money and being ready to ask — the raise/no-raise decision first, then funder type (bootstrap and revenue, public grant, angel, venture, sponsorship, corporate or foundation, patronage, debt), readiness assessed as evidence that already exists rather than a st
launch-strategistPlans a launch that can be judged rather than narrated — success thresholds written in numbers before a date exists, readiness gates verified on a clean machine, channels chosen from where the audience already is with each channel's current rules read at runtime, the load-bearing asset set, sequenci
personal-brand-strategistProfessional reputation treated as accumulated, checkable evidence — a reproducible audit of what a stranger finds when they look you up, the portfolio as artifacts a reader can run or read rather than a technology list, what each profile surface is actually for, public writing on subjects where you
positioning-strategistSettles what a project is, who it is for and what it is not, before any copy exists — the real user versus the imagined one, the one-sentence claim tested for falsifiability rather than agreeability, the alternatives that actually compete (including doing nothing and doing it by hand), differentiati
node
Senior engineering: architecture, functional design, protocols, security, integrations, UX/a11y, Angular, Spring Boot, databases, API and service versioning.
17 skills · 19 agents
PMO and agile delivery: roadmaps, backlog, requirements, risk, Scrum events, flow metrics and forecasting, and tracker operations across GitHub, Jira, Linear and GitLab.
12 skills · 10 agents
Kernel: governed memory, token economy, I/O contracts, orchestration, guard hooks and the Foundry MCP server. Required by every other Foundry plugin.
8 skills · 4 agents · 1 MCP server · hooks
Delivery and deploy: GitHub Actions pipelines, containers and Kubernetes, Terraform/OpenTofu, cloud and PaaS targets, release engineering.
5 skills · 6 agents
Test strategy, TDD enforcement, contract and E2E testing, performance engineering, observability and SRE practice.
5 skills · 6 agents
Project cost engineering, business cases and financial plans, AI/token cost control, grant and public funding reporting.
5 skills · 5 agents
Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives
1 command
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
hooks
Expose the plugin-safe Claude Code subset of Agentic Awesome Skills through a single marketplace entry.
200 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.