hermes-ephemeral-delegation SKILL.md skillA

hermes-ephemeral-delegation from gentleman-programming/gentle-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gentleman-programming/gentle-ai/hermes-ephemeral-delegation@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gentleman-programming/gentle-ai
Path
internal/assets/skills/hermes-ephemeral-delegation/SKILL.md
Versions recorded
7
Latest version
v1.0, committed Oct 14, 2026
First version recorded
Jun 14, 2026
Size
4,561 bytes
Repository stars
7,891
License
MIT

Trigger: a mapping need, parallel units, context backstop, high-risk verify, fresh review, or multi-step debug. Delegate via delegate_task for a named reason.

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

## Activation Contract

Load this skill when you are acting as the parent orchestrator and the work ahead has a named reason to delegate:

- A map you need to decide or route that exceeds the inline evidence budget (codebase mapping, approach comparison); never to read files you will read anyway before writing inline
- A writer reason: 2+ independent units of behavior (code, tests, and docs together; each several minutes of work) launched together, or the context backstop; a large task alone is tracked, not delegated
- A high-risk change that needs an independent verifier, or a large task's long suites and builds
- Fresh adversarial review (diffs, PR readiness, incident audit); never restart it automatically for a candidate whose terminal `approved` authority was already burned and that is unchanged since, unless a new independent review is deliberately requested
- Multi-step debugging that would flood the parent context

Do NOT load this skill if you are already inside a delegated child task — you are the executor, not the orchestrator.

## Hard Rules
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gentleman-programming/gentle-ai/hermes-ephemeral-delegation@sha256:df9610c4d4d1444a

The line at the top of this page pins the label v1.0, 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_7cdvumymmywnmsc2.svg)](https://markdownregistry.com/a/art_7cdvumymmywnmsc2)

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

Versions

The registry has recorded 7 versions of this file, between Jun 14, 2026 and Oct 14, 2026, about one every 20 days.

versioncommittedcommitsizeaudit
v1.0 latest2026-10-14 87a3b2e 4,561 BA view · diff
v1.02026-10-05 84ee201 4,486 BA view · diff
v1.02026-10-04 71bca6c 4,296 BA view · diff
v1.02026-10-04 9942baa 3,486 BA view · diff
v1.02026-10-03 66399a5 3,389 BA view · diff
v1.02026-09-24 e219644 3,240 BA view · diff
v1.02026-06-14 4c14984 3,396 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 (4561 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

gentleman-programming/gentle-ai · 7,891 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7cdvumymmywnmsc2
GET https://markdownregistry.com/api/v1/resolve?ref=gentleman-programming/gentle-ai/hermes-ephemeral-delegation
GET https://markdownregistry.com/api/v1/blob/df9610c4d4d1444a29ea0d9859097d887be0b46148367d43aa9223f52d7793db

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 gentleman-programming/gentle-ai

AGENTS.md AGENTS.md file
gentleman-programming/gentle-ai · AGENTS.md
git:20260902.7d1c58f · audit A · 7,891 stars
AGENTS.md@internal/assets/gga AGENTS.md file
gentleman-programming/gentle-ai · internal/assets/gga/AGENTS.md
git:20260228.f867b62 · audit A · 7,891 stars
branch-pr SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/branch-pr/SKILL.md · Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
v2.0 · audit A · 7,891 stars
chained-pr SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/chained-pr/SKILL.md · Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review…
v1.0 · audit A · 7,891 stars
cognitive-doc-design SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/cognitive-doc-design/SKILL.md · Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or…
v1.0 · audit A · 7,891 stars
comment-writer SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/comment-writer/SKILL.md · Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub…
v1.0 · audit A · 7,891 stars
gentle-ai-bench SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/gentle-ai-bench/SKILL.md · Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and…
v1.0 · audit A · 7,891 stars
go-testing SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/go-testing/SKILL.md · Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
v1.0 · audit A · 7,891 stars
issue-creation SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/issue-creation/SKILL.md · Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from…
v1.6 · audit A · 7,891 stars
judgment-day SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/judgment-day/SKILL.md · Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped…
v1.7 · audit A · 7,891 stars
rdd-defect-workflow SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/rdd-defect-workflow/SKILL.md · Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill…
v1.0 · audit A · 7,891 stars
skill-creator SKILL.md skill
gentleman-programming/gentle-ai · internal/assets/skills/skill-creator/SKILL.md · Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
v1.0 · audit A · 7,891 stars

Every file in gentleman-programming/gentle-ai

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