self-learn SKILL.md skillA
self-learn from dongnguyenvie/bashcut-agent-kit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dongnguyenvie/bashcut-agent-kit/self-learn@git:20261015.07749c7Pins git:20261015.07749c7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dongnguyenvie/bashcut-agent-kit
- Path
skills/self-learn/SKILL.md- Versions recorded
- 9
- Latest version
- git:20261015.07749c7, committed Oct 15, 2026
- First version recorded
- Oct 6, 2026
- Size
- 8,593 bytes
- Repository stars
- 6
- License
- MIT
Turn problems hit while editing in BashCut into lasting fixes: lessons (symptom, cause, fix), preferences, project facts, project skills, or a proposed kit change. Use after a failed or redone step, a user correction, or at session end. Triggers: "rút kinh nghiệm", "học từ lỗi này", "nhớ lần sau", "lần sau đừng", "cập nhật skill", "self-learn".
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
# Self-learn
A problem solved in chat but not written down **will happen again**.
Run it once the problem is solved (you need the real cause), not mid-step. At the end of a session, sweep for
anything missed, starting from `bashcut run log --kind correction`: in Claude Code the kit's hook keeps there,
quoted, every user message that reads like a correction (also across a compaction). They are candidates: most
become one lesson, some are one-off instructions. Then `bashcut knowledge verdicts`: a command whose changes were
undone or edited two or more times is a candidate too; one verdict is not a preference.
After a process audit (`bc:review`, "Process audit"), start from its lessons (from the checklist and run log, not
your memory), then add what the user corrected.
Worth recording: the user corrects you ("không, dùng X", "thật ra…", "X chứ không phải Y") or rejects a proposed
action; says to remember ("nhớ là…", "lần sau đừng…"); a `bashcut` command fails or a result had to be redone. A
question, a one-off instruction for this clip or vague feedback ("chưa ổn") is not a lesson.
## 1. Write the lesson
…Read the whole file at its exact version.
How to install
mdr add dongnguyenvie/bashcut-agent-kit/self-learn@sha256:869d009a71ccd061The line at the top of this page pins the label git:20261015.07749c7, 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_h6xdhtjwcpanzzlu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Oct 6, 2026 and Oct 15, 2026, about one every day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.07749c7 latest | 2026-10-15 | 07749c7 | 8,593 B | A | view · diff |
| git:20261012.0e5b4b4 | 2026-10-12 | 0e5b4b4 | 11,598 B | A | view · diff |
| git:20261012.676efba | 2026-10-12 | 676efba | 11,357 B | A | view · diff |
| git:20261012.42b420c | 2026-10-12 | 42b420c | 10,396 B | A | view · diff |
| git:20261009.3398630 | 2026-10-09 | 3398630 | 9,527 B | A | view · diff |
| git:20261006.c22fa26 | 2026-10-06 | c22fa26 | 9,326 B | A | view · diff |
| git:20261006.233f0e9 | 2026-10-06 | 233f0e9 | 9,076 B | A | view · diff |
| git:20261006.3f41ae3 | 2026-10-06 | 3f41ae3 | 9,531 B | A | view · diff |
| git:20261006.ecf1c91 | 2026-10-06 | ecf1c91 | 8,724 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 (8593 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
dongnguyenvie/bashcut-agent-kit · 6 stars · license MIT · pushed 2026-10-18 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_h6xdhtjwcpanzzlu GET https://markdownregistry.com/api/v1/resolve?ref=dongnguyenvie/bashcut-agent-kit/self-learn GET https://markdownregistry.com/api/v1/blob/869d009a71ccd0611d7c20414b3411514dc8f0084f91ba19794e86bf513cd046
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.