agent-prompt-improver SKILL.md skillA

agent-prompt-improver from michelkerkmeester/skilled-agent-harness_spec-driven-loops is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add michelkerkmeester/skilled-agent-harness_spec-driven-loops/agent-prompt-improver@git:20260930.c479c4b

Pins git:20260930.c479c4b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
michelkerkmeester/skilled-agent-harness_spec-driven-loops
Path
.hermes/skills/agent-prompt-improver/SKILL.md
Versions recorded
5
Latest version
git:20260930.c479c4b, committed Sep 30, 2026
First version recorded
Sep 15, 2026
Size
25,093 bytes
Repository stars
39
License
MIT

Prompt-improver specialist: framework selection, CLEAR validation, dispatch-ready packages.

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

<!-- generated by sync-skills-hermes.cjs; do not edit -->
> Agent persona `prompt-improver` from `.hermes/agents/prompt-improver.md` (the shared agent files), mirrored as a
> preloadable skill because Hermes has no agent flag. Preload with `-s agent-prompt-improver` and adopt it for the session.

# The Prompt-Improver Agent: Prompt Escalation Specialist

Read-only prompt-engineering specialist for high-stakes external CLI prompt construction. This agent selects the best-fit framework, applies DEPTH at the right energy level, validates the result with CLEAR, and returns a structured prompt package that the caller can dispatch directly.

**CRITICAL**: This agent is LEAF-only and read-only. It never edits files, never delegates, never executes the enhanced prompt, and never returns unstructured prompt advice.

**BOUNDARY PRINCIPLE**: Prompt polish must not hide missing inputs, ambiguity, contradictions, integration assumptions, or partial-success states. Surface those limits in `ESCALATION_NOTES` or use the blocked package.

**IMPORTANT**: Use only `.skilled/agents/*.md` as the canonical runtime path reference. Runtime mirrors are downstream packaging surfaces.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add michelkerkmeester/skilled-agent-harness_spec-driven-loops/agent-prompt-improver@sha256:35d216012a2323e0

The line at the top of this page pins the label git:20260930.c479c4b, 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_koquwkqifvgakh65.svg)](https://markdownregistry.com/a/art_koquwkqifvgakh65)

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

Versions

The registry has recorded 5 versions of this file, between Sep 15, 2026 and Sep 30, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260930.c479c4b latest2026-09-30 c479c4b 25,093 BA view · diff
git:20260929.f9fb96c2026-09-29 f9fb96c 25,095 BA view · diff
git:20260921.dc655b42026-09-21 dc655b4 25,087 BA view · diff
git:20260917.c7b71c92026-09-17 c7b71c9 24,813 BA view · diff
git:20260915.20195122026-09-15 2019512 24,822 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 (25093 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

michelkerkmeester/skilled-agent-harness_spec-driven-loops · 39 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_koquwkqifvgakh65
GET https://markdownregistry.com/api/v1/resolve?ref=michelkerkmeester/skilled-agent-harness_spec-driven-loops/agent-prompt-improver
GET https://markdownregistry.com/api/v1/blob/35d216012a2323e0f93db5ef717ff27eed772ce5b474a845d8d6e3c7d42d61b0

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 michelkerkmeester/skilled-agent-harness_spec-driven-loops

agent-ai-council SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-ai-council/SKILL.md · AI Council scoped-write planning architect: diverse AI lenses, multi-round deliberation, ai-council artifact writes…
git:20260917.c7b71c9 · audit A · 39 stars
agent-code SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-code/SKILL.md · Application-code implementation specialist via sk-code. LEAF, dispatched only by @orchestrate.
git:20261010.3617968 · audit A · 39 stars
agent-context SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-context/SKILL.md · Production context agent — comprehensive retrieval with canonical continuity recovery and structured Context Packages
git:20260917.c7b71c9 · audit A · 39 stars
agent-debug SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-debug/SKILL.md · User-invoked fresh-perspective debugger: 5-phase root-cause methodology, never auto-dispatched.
git:20261010.3617968 · audit A · 39 stars
agent-deep-research SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-deep-research/SKILL.md · Autonomous deep research agent executing single iteration cycles with externalized state
git:20260919.d94166b · audit A · 39 stars
agent-deep-review SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-deep-review/SKILL.md · LEAF deep-review iteration agent: one dimension/pass, P0/P1/P2 findings, JSONL state.
git:20261010.77df558 · audit A · 39 stars
agent-design SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-design/SKILL.md · Design specialist across the four sk-design modes: values and behavior, Style Reference measurement, charts and…
git:20261003.4189380 · audit A · 39 stars
agent-markdown SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-markdown/SKILL.md · Template-first markdown/documentation executor; handles /create:* commands, spec docs, and scoped markdown authoring
git:20260926.038ce76 · audit A · 39 stars
agent-orchestrate SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-orchestrate/SKILL.md · Senior orchestration agent: task decomposition, delegation, quality eval, delivery synthesis.
git:20261010.3617968 · audit A · 39 stars
agent-review SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/agent-review/SKILL.md · Code review specialist with pattern validation, quality scoring, and standards enforcement for PRs and code changes
git:20261010.3cf65c5 · audit A · 39 stars
cli-classifier SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/cli-classifier/SKILL.md · Routes typed classifier judgment requests to the hosted Jev transport via mode-registry.json; future classifiers join…
v0.8.2.0 · audit A · 39 stars
cli-claude-code SKILL.md skill
michelkerkmeester/skilled-agent-harness_spec-driven-loops · .hermes/skills/cli-claude-code/SKILL.md · Claude Code CLI executor for Anthropic-backed reasoning, edits, reviews, and structured cross-AI handoff.
v1.5.3.0 · audit A · 39 stars

Every file in michelkerkmeester/skilled-agent-harness_spec-driven-loops

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