lh-next-step SKILL.md skillA

lh-next-step from jrodrigopuca/local-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jrodrigopuca/local-agents/lh-next-step@v1.2

Pins v1.2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jrodrigopuca/local-agents
Path
generalist/skills/lh-next-step/SKILL.md
Versions recorded
2
Latest version
v1.2, committed Oct 14, 2026
First version recorded
Oct 14, 2026
Size
5,435 bytes
Repository stars
2
License
Apache-2.0

Decision model for choosing what to do next: continue, re-plan, stop, or escalate to the user. Trigger: load after a step fails or surprises you, before ending a turn on a task that took more than one step, when resuming one ("seguimos con lo de ayer"), or when a task will outlast the session or a context compaction and its state must live in a file. Ordering the steps before the first one is lh-decomposition. Not needed when the next action is obvious and reversible.

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

Act-vs-stop and "ask only what only the user knows" are base rules. This
skill is the cascade that applies them when the next step is not obvious.

## Critical Patterns

### 1. The decision cascade

Run these questions in order; the first "yes" decides.

```
1. Did reality contradict the task's framing?        → STOP, report the mismatch
2. Is the next action irreversible or outward-facing → STOP, confirm with user
   (delete, publish, send, force-push)?
3. Is the goal already met (per acceptance criteria)?→ VERIFY once more, then REPORT
4. Did the last step fail?                           → DIAGNOSE (don't retry blind)
5. Is a load-bearing assumption still unverified?    → VERIFY IT next
6. Otherwise                                          → cheapest step that most
                                                        reduces remaining uncertainty
```

### 2. Failure is information, not an obstacle

When a step fails, the next step is **diagnosis**, never a blind retry and never
an immediate workaround. Ask: did it fail because the action was wrong, the plan
was wrong, or the understanding was wrong? Each answer routes differently:

| Failure level | Next step |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jrodrigopuca/local-agents/lh-next-step@sha256:66e9d2105bf802c7

The line at the top of this page pins the label v1.2, 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_r4ioagzedz5wuk6q.svg)](https://markdownregistry.com/a/art_r4ioagzedz5wuk6q)

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

Versions

The registry has recorded 2 versions of this file, all committed on Oct 14, 2026.

versioncommittedcommitsizeaudit
v1.2 latest2026-10-14 5b652d2 5,435 BA view · diff
v1.22026-10-14 9571e8f 5,330 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 (5435 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

jrodrigopuca/local-agents · 2 stars · license Apache-2.0 · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_r4ioagzedz5wuk6q
GET https://markdownregistry.com/api/v1/resolve?ref=jrodrigopuca/local-agents/lh-next-step
GET https://markdownregistry.com/api/v1/blob/66e9d2105bf802c7789a0618d28b3e8380b3e16980b988687e396aded88ec45c

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 jrodrigopuca/local-agents

AGENTS.md AGENTS.md file
jrodrigopuca/local-agents · AGENTS.md
git:20261022.50892c2 · audit A · 2 stars
AGENTS.md@apple-dev AGENTS.md file
jrodrigopuca/local-agents · apple-dev/AGENTS.md · Use this agent for Swift, iOS, and macOS development as a mentor — it teaches you to solve alone (Socratic first)…
git:20261014.9571e8f · audit A · 2 stars
lh-code-review SKILL.md skill
jrodrigopuca/local-agents · apple-dev/skills/lh-code-review/SKILL.md · Reviewing Swift/SwiftUI code as mentor: the severity system, the Apple-specific defect checklist, and…
v1.1 · audit A · 2 stars
lh-debugging SKILL.md skill
jrodrigopuca/local-agents · apple-dev/skills/lh-debugging/SKILL.md · Debugging Apple-platform issues as taught method: crashes, leaks, hangs, and weird behavior — Socratic first, tools…
v1.1 · audit A · 2 stars
lh-shipping SKILL.md skill
jrodrigopuca/local-agents · apple-dev/skills/lh-shipping/SKILL.md · Getting apps into users' hands: signing, provisioning, TestFlight, App Review, and macOS-specific distribution…
v1.1 · audit A · 2 stars
lh-state-architecture SKILL.md skill
jrodrigopuca/local-agents · apple-dev/skills/lh-state-architecture/SKILL.md · SwiftUI state management and app architecture: ownership, MVVM shape, navigation, dependency injection, project…
v1.1 · audit A · 2 stars
AGENTS.md@architect AGENTS.md file
jrodrigopuca/local-agents · architect/AGENTS.md · Use this agent for software architecture guidance, design patterns, expensive-to-reverse technical decisions…
git:20261021.e01dd0b · audit A · 2 stars
lh-design-review SKILL.md skill
jrodrigopuca/local-agents · architect/skills/lh-design-review/SKILL.md · How to review a codebase's architecture or a proposed design: dependency direction, boundary integrity, coupling…
v1.1 · audit A · 2 stars
lh-mentoring SKILL.md skill
jrodrigopuca/local-agents · architect/skills/lh-mentoring/SKILL.md · Turning a correction into learning without lecturing. Trigger: load when a real misconception would hurt the user…
v1.1 · audit A · 2 stars
lh-tradeoffs SKILL.md skill
jrodrigopuca/local-agents · architect/skills/lh-tradeoffs/SKILL.md · Method for analyzing and presenting expensive-to-reverse technical decisions: drivers, options, tradeoff table…
v1.1 · audit A · 2 stars
AGENTS.md@data-ml AGENTS.md file
jrodrigopuca/local-agents · data-ml/AGENTS.md · Use this agent for data pipelines, ML modeling, and LLM integration — ingestion/quality, honest evaluation, and…
git:20261014.9571e8f · audit A · 2 stars
lh-data-pipelines SKILL.md skill
jrodrigopuca/local-agents · data-ml/skills/lh-data-pipelines/SKILL.md · Moving data reliably: ingestion, transformation, quality validation, storage, and pipeline design. Trigger: load when…
v1.1 · audit A · 2 stars

Every file in jrodrigopuca/local-agents

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