improve-agent SKILL.md skillA
improve-agent from stempeck/agentfactory is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add stempeck/agentfactory/improve-agent@git:20260916.8d1a006Pins git:20260916.8d1a006 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- stempeck/agentfactory
- Path
internal/cmd/install_skills/improve-agent/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260916.8d1a006, committed Sep 16, 2026
- First version recorded
- May 31, 2026
- Size
- 15,831 bytes
- Repository stars
- 3
- License
- AGPL-3.0
Improve an agent's formula TOML based on post-execution learnings. Use after a formula run required manual intervention, produced incorrect artifacts, or left cleanup work for the operator. Classifies the failure type, scans for sibling vulnerabilities, selects the appropriate fix pattern, and surgically inserts corrective steps into the formula.
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
# Improve Agent Formula Surgical improvement of a formula TOML based on observed execution failures or required manual intervention. ## Invocation `/improve-agent <formula-path>` or `/improve-agent <agent-name>` If agent-name given, resolve to `$AF_ROOT/.agentfactory/store/formulas/<agent-name>.formula.toml`. ## Phase 1: Gather Evidence Collect what went wrong. Ask the user if not already clear from conversation context: 1. **What manual work was required after the formula ran?** 2. **Which files/paths were affected?** 3. **What was the expected state vs actual state?** Record as a structured gap: ``` GAP: <one-line description> EXPECTED: <what should have happened> ACTUAL: <what happened instead> MANUAL FIX: <what the operator had to do> AFFECTED PATHS: <specific files/directories> ``` ## Phase 1.5: Context Review Phase 1 collects what the operator noticed. This phase collects what the run **measured** — the per-step context figures the formula's own step records carry. Do it before reading the formula, so Phase 2 already knows which steps are suspect. 1. **Find this run's instance.** Read `.runtime/improvement_pending` (relative to your own agent …
Read the whole file at its exact version.
How to install
mdr add stempeck/agentfactory/improve-agent@sha256:e87b5455a36ceab0The line at the top of this page pins the label git:20260916.8d1a006, 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_kvnacbin4i46xswu)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between May 31, 2026 and Sep 16, 2026, about one every 54 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.8d1a006 latest | 2026-09-16 | 8d1a006 | 15,831 B | A | view · diff |
| git:20260821.ae0a18c | 2026-08-21 | ae0a18c | 11,097 B | A | view · diff |
| git:20260531.70c9520 | 2026-05-31 | 70c9520 | 7,156 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 (15831 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
stempeck/agentfactory · 3 stars · license AGPL-3.0 · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_kvnacbin4i46xswu GET https://markdownregistry.com/api/v1/resolve?ref=stempeck/agentfactory/improve-agent GET https://markdownregistry.com/api/v1/blob/e87b5455a36ceab0b674589efbbde5845d63d9eb9124be91f177a4d5cf059a43
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 stempeck/agentfactory
Every file in stempeck/agentfactory