Plugin marketplace

sheahan-skills

Claude Code skills Max Sheahan built for his own work and cleaned up to share: writing and voice tools, designed documents, a security suite for launching sites, a session manager for a markdown vault, a map workflow, a YouTube recut pipeline, and news scoring.

0 · maxsheahan/claude-skills14 pluginsMITupdated 3 days ago

Add this marketplace

Then install any plugin below by name — each page has its exact command.

Session manager for a markdown vault: hooks that deliver rules, today's daily, open todos, newest lessons and the project hub into every session and re-deliver them after compaction, drift checks on every prompt, session wrap and daily logs, a per-session ledger, ruling capture, per-object decision records, agenda and weekly review, vault scaffolding, and vault health (audit, grooming, canon size budgets).

15 skills · 3 agents · hooks

0

Check whether a finished draft sounds like the person it is supposed to sound like: build a voice profile, score a draft against it, and get one verdict. The grader diagnoses and never edits.

4 skills · 4 agents

0

App-layer security for your builds: ASVS-lite checks (credentialed CORS, stack traces in responses, debug routes, sign-out that only clears the browser, object writes without an ownership reference), outbound-fetch guard against SSRF, abuse and spend (uncapped paid APIs, unset caps that mean unlimited, open proxies, per-client ceilings, caller-set LLM params), auth gates that open on their own (a guard skipped when a secret is unset, identity from a bare header, Access trusted only at the edge, open better-auth sign-up), AI route metering (a daily counter reserved before every paid call, with a drop-in guard template), authorization inside MCP tools (every tool-reachable query scoped to the signed-in identity, no identity from tool arguments, privileged tools gated), and tests proven by removing each protection. Requires secure-core.

7 skills

0

One adapter per supported platform, each stating what it checks and what it cannot see: Cloudflare Pages and Workers (headers on every path, no secrets in [vars], previews off production data, edge hardening), Next.js on OpenNext (server actions, NEXT_PUBLIC_ secrets, static-export headers), Fly and Supabase (RLS, service-role key, [env] secrets, exposed ports), Google Apps Script (web app access, scopes, keys in code), Railway (environment dumps, count-only variable reads), and the Cloudflare account itself through the API or a snapshot (zone SSL, TLS, HTTPS, HSTS, DNSSEC; dangling pages.dev CNAMEs; members without 2FA; preview secrets; orphan KV; data Workers exposed on workers.dev). Requires secure-core.

6 skills

0

The secure-launch front door: maps a repo's attack surface (routes, auth, outbound fetches, paid APIs and their spend caps, secrets by name, data stores, deploy targets), runs every applicable check in the suite, and writes one findings ledger where each check is PASS, FAIL or UNKNOWN. Required by every other secure-launch plugin.

3 skills · 1 command

0

Keep secret values out of repos and out of captured sessions: a gitleaks scan proven on planted keys, values never printed; a staged PreToolUse guard that blocks commands which print secrets; a capture-folder scanner; and a per-provider rotation runbook with a shape check that never displays the value. Requires secure-core.

3 skills

0

Capture a writing voice from a corpus and reproduce it in drafts.

3 skills

0

Research a person into a sourced PDF brief, and lay out documents that look designed, not generated.

2 skills

0

Score how a news article is written, not what it covers: a checklist scale from Informing to Manipulating, and an earlier tone scale from Practical to Hysterical.

2 skills

0

secure-ai

claude

AI-feature security for your builds: static checks for how an app feeds and trusts a model (a model key in browser code, caller input in the system prompt, secrets inside prompt text, model output reaching raw HTML, eval, a shell or string-built SQL, Markdown that can load attacker images, tools that fetch a URL the model chose), and a red-team probe that sends twelve prompt-injection probes to a LOCAL dev server and grades the replies by canary and markup, with no model in the grading. Requires secure-core.

2 skills

0

Dependency risk without auto-bumps: production npm audit with per-advisory reachability triage recorded in the repo, lockfile presence, GitHub Actions pinned to SHAs with secrets scoped per step, wrangler pinned, and a check that the BUILT code resolves and loads under plain Node (vitest resolves differently). Requires secure-core.

2 skills

0

Enforce the secure-launch ledger: a gate that refuses on FAIL and on any UNKNOWN the owner has not accepted, and drop-in templates (GitHub Actions workflow, deploy-script gate, pre-push hook) vendored into a repo only on request. Requires secure-core.

1 skill

0

Critique a nonfiction draft for the tells that make competent prose read as generated.

1 skill

0

Gated recut pipeline for YouTube: rebuild a retention-first edit from raw footage, matching a reference edit's filler and pause cuts, with intro and outro cards, a music bed, burned karaoke captions, denoise, zooms, privacy masks, and preflight and QA gates so no render is handed over unchecked.

1 skill

0

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins14 plugins