system-prompt-doctor SKILL.md skillA
This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
system-prompt-doctor from getedgehq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add getedgehq/skills/system-prompt-doctor@git:20260920.deb764aPins git:20260920.deb764a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- getedgehq/skills
- Path
evals/system-prompt-doctor/2026-09-19/system-prompt-doctor-conflicting-agent/runs/system-prompt-doctor-conflicting-agent/s2/with.meta/skill/system-prompt-doctor/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260920.deb764a, committed Sep 20, 2026
- Size
- 3,271 bytes
- Repository stars
- 5
- License
- Apache-2.0
Audit, optimize, and benchmark a user-owned system prompt, developer prompt, CLAUDE.md, AGENTS.md, or agent instruction file against representative tasks. Use when the user wants to improve an agent's core instructions, make an agent more reliable, reduce instruction bloat, fix tool-use or ask-vs-act behavior, or prove whether a revised system prompt is actually better.
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
# System Prompt Doctor Do not optimize a system prompt by taste. Optimize it against behavior. ## Scope This skill works on prompts/instruction files the user owns or can provide, including: - system/developer prompts - `CLAUDE.md` - `AGENTS.md` - reusable agent instruction files - agent persona/policy prompts Do not claim access to hidden platform system prompts that the runtime does not expose. ## Workflow 1. **Capture the contract.** Record the target model, prompt surface, task family, tools, hard constraints, output shape, failure cases, latency/cost limits, and what must not change. 2. **Build the eval before editing.** Prefer real historical failures and corrections. Otherwise create 8 to 20 representative cases plus hard negatives and at least a 20% holdout split. 3. **Baseline the current prompt.** Preserve prompt hash, model/version, outputs, scores, token usage, tool behavior, and failures. 4. **Audit instruction architecture.** Find contradictions, duplicate rules, vague defaults, missing completion criteria, tool-policy gaps, bad ask-vs-act calibration, stale examples, and context that should live outside the system prompt. …
Read the whole file at its exact version.
How to install
mdr add getedgehq/skills/system-prompt-doctor@sha256:b2e8a0451cfa25adThe line at the top of this page pins the label git:20260920.deb764a, 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.
[](https://markdownregistry.com/a/art_gy65idslz5auoajd)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 20, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3271 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
getedgehq/skills · 5 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gy65idslz5auoajd GET https://markdownregistry.com/api/v1/resolve?ref=getedgehq/skills/system-prompt-doctor GET https://markdownregistry.com/api/v1/blob/b2e8a0451cfa25ada70a6dd64c55d42896e0e859bef9eaf3beed3e518d11d304
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 getedgehq/skills
Every file in getedgehq/skills