dsh-engineering-skills
Engineering-discipline skills distilled from a large production agent-system codebase: systematic code review, CI failure triage, shell safety, redundancy/boundary auditing, and cross-repo pattern absorption.
Five markdown skills for AI coding agents (DeepSeek Harness, Claude Code, Codex, or any agent that reads SKILL.md). They are methodology-first — no code to install, no runtime, no lock-in: copy the skills/ directory and the agent loads them.
Skills
| Skill | What it does |
|---|---|
| code-review-methodology | 18-dimension, 3-pass code review framework: execution/integration → architecture/systems → reliability/correctness, plus multi-angle iterative review, E2E-test review angles, migration review angles, and 12+ derived rules |
| ci-diagnosis-and-fix | Systematic triage and repair when GitHub Actions CI turns wholesale red: find the failing run → pull the failing step's log → classify the root cause → fix → verify |
| shell-safety | Hard ban on interactive CLI commands (more/less/pause/choice/start /WAIT) that freeze headless agent sessions, with non-interactive equivalents, a mandatory timeout rule, and a pre-flight checklist |
| redundancy-and-boundary-audit | Repo-level duplication triage with a falsifiable sync test and A/B/C classification (true duplicate / same-name-different-concept / same-shape-different-domain), plus boundary, naming, and multi-angle verification |
| repo-analysis | 5-phase cross-repository architecture audit: scan → pattern extraction (7-primitive taxonomy) → gap mapping → value judgment → structured output, with a batch flow for 5+ repos |
Install
From PyPI — the pack also ships as a data-only Python package with an installer CLI:
pip install "dsh-engineering-skills"
dsh-engineering-skills list # see the 5 skills
dsh-engineering-skills install ~/.deepseek/skills # copy into an agent skills dir
The wheel contains the same SKILL.md files (packaged as data-files, no code
dependencies); the CLI just copies them into any agent's skills directory.
From source / generic agents — copy the skills into your agent's skills directory:
# DeepSeek Harness / generic agent skills dir
cp -r skills/* ~/.deepseek/skills/ # or your profile's skills dir
# Claude Code
cp -r skills/* ~/.claude/skills/
# Codex
cp -r skills/* ~/.codex/skills/
Each skill is a self-contained SKILL.md with YAML frontmatter (name, description, keywords) — no dependencies, no build step.
Why these skills
They come from real incidents and audits, not theory. Notable provenance:
shell-safetyexists because a session froze for 12 minutes onfindstr ... | more +0waiting for a keypress that never arrived.redundancy-and-boundary-auditencodes the A/B/C duplication classification that keeps "same name" from being treated as "duplicate" — a domain model / API DTO pair is legitimate layering, and only asymmetric change is drift.code-review-methodologyaccumulates review angles only after each one caught a real bug (single-pass review finds ~30% of bugs in cross-cutting features).ci-diagnosis-and-fixdocuments the two failure modes that turn CI wholesale red: a nonexistent dependency version, and the old$GITHUB_OUTPUTsyntax on newer runners.
Validation
python scripts/validate_skills.py # checks frontmatter + body of every SKILL.md
License
MIT © 2026 Chen (Jarry) Pan
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file dsh_engineering_skills-0.1.0.tar.gz.
File metadata
- Download URL: dsh_engineering_skills-0.1.0.tar.gz
- Upload date:
- Size: 26.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
83c3371d4f3bcf0b1da3f26cdc8123d45bc05ae7d6646d9df8c050b102be15c4
|
|
| MD5 |
a0bdb7c1e8c308216839ac71ab2108ba
|
|
| BLAKE2b-256 |
c1ab5c2b1e06c87d6d18ce054f11237ed835a065c845b36006251ba7b0f5f2a2
|
File details
Details for the file dsh_engineering_skills-0.1.0-py3-none-any.whl.
File metadata
- Download URL: dsh_engineering_skills-0.1.0-py3-none-any.whl
- Upload date:
- Size: 27.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a9ef3ef82d828041ec3a87f2fab51e8f1307b622c0055c595fb61c90e9580aa0
|
|
| MD5 |
1e5648484a3af144d117bbab80689d14
|
|
| BLAKE2b-256 |
8569d7e9250f38c5e0b3e6ab22e41233b81fbb5b7a2ea4d5c4d4e9b94610b574
|