jev-capability-advisor SKILL.md skillA

jev-capability-advisor from stark-ai-de/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add stark-ai-de/agent-skills/jev-capability-advisor@v0.3.3

Pins v0.3.3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
stark-ai-de/agent-skills
Path
skills/skill-maintenance/jev-capability-advisor/SKILL.md
Versions recorded
5
Latest version
v0.3.3, committed Sep 28, 2026
First version recorded
Sep 26, 2026
Size
20,465 bytes
Repository stars
8
License
Apache-2.0

Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user requests capability advice, candidate inspection, selection evaluation, or reusable host integration. Native client selection remains the default and fallback.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Jev Capability Advisor

## Goal

Return a task-specific recommendation from capabilities actually available in the current client. The default `general` profile can recommend one to three capabilities; explicit `next_skill` recommends one skill without assessing remaining work. The client retains discovery, activation, permissions, and execution.

## Network prerequisite

Recommendations need host-authorized HTTPS access to `api.typesafe.ai:443` and
existing TypeSafe credentials. Installation, hook trust, processing consent and
network permission are separate. The user or administrator owns permissions;
the skill never edits sandbox, firewall, proxy or approval policy. Use an
applicable native approval route only when needed. A denial ends the attempt:
no alternate route, repeated prompt or automatic retry. Follow the
[network and failure contract](references/network-access.md) for actionable,
secret-free messages. Without usable API access, no Jev recommendation was
produced; native selection and local `Inspect` are not Jev advice.

The contract is the same on native Windows, macOS and Linux; WSL is a separate
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add stark-ai-de/agent-skills/jev-capability-advisor@sha256:5f209ae35fe01412

The line at the top of this page pins the label v0.3.3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mnkh3c7cgaqusx3j.svg)](https://markdownregistry.com/a/art_mnkh3c7cgaqusx3j)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Sep 26, 2026 and Sep 28, 2026, more than one a day.

versioncommittedcommitsizeaudit
v0.3.3 latest2026-09-28 de81dc9 20,465 BA view · diff
v0.3.22026-09-28 2ce9f0c 18,761 BA view · diff
v0.3.12026-09-26 2855684 18,605 BA view · diff
v0.3.02026-09-26 8243b65 18,215 BA view · diff
v0.2.02026-09-26 9d42b7b 12,994 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (20465 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

stark-ai-de/agent-skills · 8 stars · license Apache-2.0 · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mnkh3c7cgaqusx3j
GET https://markdownregistry.com/api/v1/resolve?ref=stark-ai-de/agent-skills/jev-capability-advisor
GET https://markdownregistry.com/api/v1/blob/5f209ae35fe01412c8ca7b4c3efcc306b59a81bde6113774796b5f9542aa2770

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from stark-ai-de/agent-skills

AGENTS.md AGENTS.md file
stark-ai-de/agent-skills · AGENTS.md
git:20261016.b17a98e · audit A · 8 stars
codex-context-guard SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/codex-operations/codex-context-guard/SKILL.md · Prevent Codex context-window exhaustion during long-running refactors, repo audits, migrations, debugging sessions, or…
v0.1.0 · audit A · 8 stars
change-impact SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/change-impact/SKILL.md · Find forgotten follow-up changes outside a behavior-changing diff in tests, examples, documentation, configuration, and…
v0.2.0 · audit A · 8 stars
debugging-diagnosis SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/debugging-diagnosis/SKILL.md · Diagnose and fix bugs through reproduction, minimization, hypotheses, instrumentation, targeted fixes, and regression…
v0.1.0 · audit A · 8 stars
issue-plan-slicer SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/issue-plan-slicer/SKILL.md · Convert a spec, roadmap item, or rough plan into independently implementable issue slices with scope, dependencies…
v0.1.0 · audit A · 8 stars
prd-writer SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/prd-writer/SKILL.md · Write a concise PRD or implementation brief from current context, separating problem, solution, user stories…
v0.1.0 · audit A · 8 stars
prototype-spike SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/prototype-spike/SKILL.md · Build or plan an explicitly throwaway prototype to answer a design, API, UX, performance, or integration question, then…
v0.1.0 · audit A · 8 stars
repo-map-zoom-out SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/repo-map-zoom-out/SKILL.md · Map unfamiliar code areas before implementation by identifying entry points, ownership boundaries, callers, data flow…
v0.1.0 · audit A · 8 stars
review-fix-swarm SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/review-fix-swarm/SKILL.md · Run a bounded post-implementation multi-agent review, bug-fix, behavior-preserving simplification, and re-review loop…
v0.1.0 · audit A · 8 stars
test-first-implementation SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/engineering-workflows/test-first-implementation/SKILL.md · Implement behavior with a red-green-refactor loop, observable tests, and small vertical slices. Use when the user asks…
v0.1.0 · audit A · 8 stars
grill-plan SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/productivity/grill-plan/SKILL.md · Relentlessly question a plan, design, migration, release, or repo maintenance proposal until assumptions, risks…
v0.1.0 · audit A · 8 stars
handoff SKILL.md skill
stark-ai-de/agent-skills · incubator/skills/productivity/handoff/SKILL.md · Write a compact handoff document so a fresh agent, thread, or session can continue. Use when context is long, the user…
v0.1.1 · audit A · 8 stars

Every file in stark-ai-de/agent-skills

Other files named jev-capability-advisor

jev-capability-advisor SKILL.md skill
stark-ai-de/agent-skills · plugins/stark-ai-developer/skills/jev-capability-advisor/SKILL.md · Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user…
v0.3.3 · audit A · 8 stars

Browse by kind, by grade A, or by owner.