DESIGN.md@docs/internal/researchA
DESIGN.md@docs/internal/research from product-on-purpose/agent-skills-toolkit is a DESIGN.md file: the design rules coding agents follow in that repo.
mdr add product-on-purpose/agent-skills-toolkit/docs/internal/research/DESIGN.md@git:20260610.74583ccPins git:20260610.74583cc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- DESIGN.md file
- Repository
- product-on-purpose/agent-skills-toolkit
- Path
docs/internal/research/DESIGN.md- Versions recorded
- 1
- Latest version
- git:20260610.74583cc, committed Jun 10, 2026
- Size
- 17,856 bytes
- Repository stars
- 3
- License
- Apache-2.0
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
# Competitive landscape: verified comparison and best-in-class gap analysis - DESIGN ## TL;DR - **What:** A verified, dated, primary-source comparison of `agent-skills-toolkit` against the 6-8 tools that actually compete with a tiered library Standard, plus the public matrix and a best-in-class gap analysis that come out of it. - **Why:** The existing research base (seven cross-LLM reports in `_local/standards-comparison/`) contradicts itself on load-bearing facts and contains likely-fabricated tools and stats. For a project whose entire identity is deterministic rigor, "verified" cannot be a label we inherit from those reports - it must be a process we run. - **How:** Co-design one schema where every dossier field maps 1:1 to a matrix column, verify each tool against primary sources into a dated profile, then distill the matrix, the gap analysis, and the public surfaces as views of that one dataset. - **Status:** Approved design, re-based on v1.5.0 + the eval-target corpus run (2026-06-09; see section 3b). Next: implementation plan via writing-plans. - **Date:** 2026-06-09 - **Deciders:** maintainer (jprisant), with Claude (Opus 4.8) …
Read the whole file at its exact version.
How to install
mdr add product-on-purpose/agent-skills-toolkit/docs/internal/research/DESIGN.md@sha256:21d101b2bb7f3748The line at the top of this page pins the label git:20260610.74583cc, 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_bzzzn7qpd62gjrrl)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jun 10, 2026.
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (17856 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
product-on-purpose/agent-skills-toolkit · 3 stars · license Apache-2.0 · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bzzzn7qpd62gjrrl GET https://markdownregistry.com/api/v1/resolve?ref=product-on-purpose/agent-skills-toolkit/docs/internal/research/DESIGN.md GET https://markdownregistry.com/api/v1/blob/21d101b2bb7f3748c6aaf20862555d078feae50889832020a1edd3d61186ceb9
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: what DESIGN.md is and how agents use it · which agent file does what.