evolvable-software SKILL.md skillA
evolvable-software from harsh51191/evolvable-software is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add harsh51191/evolvable-software/evolvable-software@git:20261003.56aac15Pins git:20261003.56aac15 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- harsh51191/evolvable-software
- Path
skills/evolvable-software/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261003.56aac15, committed Oct 3, 2026
- First version recorded
- Oct 3, 2026
- Size
- 10,879 bytes
- Repository stars
- 2
- License
- MIT
Assess how ready a software product is to evolve itself safely, and how much of that AI drives, using the EVOLVE framework. Reports a Software Autonomy Level (L0 to L5) for three loops (request to release, issue to fix, opportunity to expansion), how far AI itself carries each loop, the critical controls that fail, exactly what blocks the next level, a six-capability profile, AI Readiness for products with AI features, and a prerequisite-ordered remediation plan, with every score tied to…
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
# EVOLVE: Self-Evolution Readiness Evaluation ## Purpose Answer one question from evidence: **how ready is this product to evolve itself safely?** Three loops make the question concrete: - **Request → Release:** can it take a request, implement it properly and release it? - **Issue → Fix:** can it find problems users face, fix them and ship the fix? - **Opportunity → Expansion:** can it notice adjacent needs and propose or launch them? Each loop gets a Software Autonomy Level from L0 (manual) to L5 (self-directing). A loop's level is the lowest of four parts: its own stages, a shared release spine, an architecture foundation and a governance ceiling. The headline SAL is the lower of Request → Release and Issue → Fix; Expansion is reported beside it. Beside each loop, the scorer reports how far AI itself carries it, from the AI-qualified readings. The six-capability profile explains the levels: | Capability | Asks | |---|---| | Elastic (ARC) | Does the architecture scale, survive failure and recover its data? | | Velocity (DEL) | Can a change be built, verified and released quickly and safely? | | Open (MAL) | Can the product be reshaped without a code release? | …
Read the whole file at its exact version.
How to install
mdr add harsh51191/evolvable-software/evolvable-software@sha256:d4cc44620bf31126The line at the top of this page pins the label git:20261003.56aac15, 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_cg6bm4gcaiqqvfuo)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, all committed on Oct 3, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.56aac15 latest | 2026-10-03 | 56aac15 | 10,879 B | A | view · diff |
| git:20261003.8cd46c4 | 2026-10-03 | 8cd46c4 | 9,937 B | A | view · diff |
| git:20261003.6f25396 | 2026-10-03 | 6f25396 | 9,989 B | A | view · diff |
| git:20261003.c5a3509 | 2026-10-03 | c5a3509 | 10,041 B | A | view |
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 (10879 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
harsh51191/evolvable-software · 2 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cg6bm4gcaiqqvfuo GET https://markdownregistry.com/api/v1/resolve?ref=harsh51191/evolvable-software/evolvable-software GET https://markdownregistry.com/api/v1/blob/d4cc44620bf31126ca48e5384173a1ce1c819c026c6ae6db5474913a33c4f176
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.