Skip to main content

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-safety exists because a session froze for 12 minutes on findstr ... | more +0 waiting for a keypress that never arrived.
  • redundancy-and-boundary-audit encodes 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-methodology accumulates review angles only after each one caught a real bug (single-pass review finds ~30% of bugs in cross-cutting features).
  • ci-diagnosis-and-fix documents the two failure modes that turn CI wholesale red: a nonexistent dependency version, and the old $GITHUB_OUTPUT syntax 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

dsh_engineering_skills-0.1.0.tar.gz (26.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dsh_engineering_skills-0.1.0-py3-none-any.whl (27.4 kB view details)

Uploaded Python 3

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

Hashes for dsh_engineering_skills-0.1.0.tar.gz
Algorithm Hash digest
SHA256 83c3371d4f3bcf0b1da3f26cdc8123d45bc05ae7d6646d9df8c050b102be15c4
MD5 a0bdb7c1e8c308216839ac71ab2108ba
BLAKE2b-256 c1ab5c2b1e06c87d6d18ce054f11237ed835a065c845b36006251ba7b0f5f2a2

See more details on using hashes here.

File details

Details for the file dsh_engineering_skills-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for dsh_engineering_skills-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a9ef3ef82d828041ec3a87f2fab51e8f1307b622c0055c595fb61c90e9580aa0
MD5 1e5648484a3af144d117bbab80689d14
BLAKE2b-256 8569d7e9250f38c5e0b3e6ab22e41233b81fbb5b7a2ea4d5c4d4e9b94610b574

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page