mathodology-dev-test-release
starsforks
How to install mathodology-dev-test-release?
sweetcornna/mathodology/mathodology-dev-test-release
$npx -y skills add sweetcornna/mathodology --skill mathodology-dev-test-releaseUse when validating the Mathodology skills-only repository or preserving archived knowledge about the former development, testing, deployment, packaging, and release workflows.
SKILL.md
| 1 | # Mathodology Dev Test Release Archive |
| 2 | |
| 3 | ## Scope |
| 4 | |
| 5 | This branch is skills-only. Its active validation checks are skill, metadata, link, backup, and tracked-file whitelist checks. |
| 6 | |
| 7 | The former application build, CI, Docker, native service, packaging, installer, and release files are not present on this branch. Treat those workflows as archived knowledge unless recovered from Git history. |
| 8 | |
| 9 | ## Active Workflow Validation |
| 10 | |
| 11 | For award-level modeling workflows, this skill owns final gates rather than application builds: |
| 12 | |
| 13 | - phase log exists and covers Phases 0-8 |
| 14 | - every prompt requirement maps to a paper section or package file |
| 15 | - every reported number maps to code, data, derivation, or documented manual calculation |
| 16 | - every phase has specialist handoffs, lead synthesis, and an independent critic gate |
| 17 | - all blocker and high-severity critic findings are fixed before final packaging |
| 18 | - model selection considers at least three routes with rejection reasons for alternatives |
| 19 | - sensitivity or robustness evidence exists for important assumptions and key results |
| 20 | - final paper, editable source if required, code, data notes, figures, tables, README, AI-use statement, and checklist are present |
| 21 | - no local caches, secrets, raw scratch files, or unrelated artifacts are in the final package |
| 22 | |
| 23 | Codex should run these gates with a dedicated critic or packaging agent. |
| 24 | |
| 25 | Claude Code should run `mathodology-submission-packager` and then `mathodology-critic`. |
| 26 | |
| 27 | ## Active Validation |
| 28 | |
| 29 | Shared repository validation lives in ONE place: `scripts/validate_repo.py` |
| 30 | (pure standard library, no PyYAML). Do not re-inline these checks as heredocs in |
| 31 | docs or other skills; add or change a gate in the script. |
| 32 | |
| 33 | Run every maintenance gate from the repository root: |
| 34 | |
| 35 | ```bash |
| 36 | python3 .claude/skills/mathodology-dev-test-release/scripts/validate_repo.py all |
| 37 | ``` |
| 38 | |
| 39 | Run one gate by naming it: `skills`, `metadata`, `links`, `whitelist`, `agents`, |
| 40 | `sync`, or `selftest`. The script prints per-check `PASS`/`FAIL` lines and exits |
| 41 | non-zero on any failure. |
| 42 | |
| 43 | - `skills` / `metadata`: every `.claude/skills/*/SKILL.md` frontmatter (name == |
| 44 | dir, lowercase-hyphen, `Use when` description) and every `agents/openai.yaml` |
| 45 | default prompt mentioning `$<dirname>`. |
| 46 | - `links`: relative markdown links, inline `.claude/...` paths, and |
| 47 | `mathodology-<x>` name references in tracked docs resolve. |
| 48 | - `whitelist`: only skills-repository files are tracked. |
| 49 | - `agents`: every `.claude/agents/*.md` frontmatter (name == stem, description, |
| 50 | tools, and any `model` in opus/sonnet/haiku/inherit). |
| 51 | - `sync`: each en/zh doc twin agrees on heading and code-block counts, and code |
| 52 | blocks are byte-identical after dropping CJK lines. |
| 53 | - `selftest`: proves each checker can both pass and fail on tempdir fixtures. |
| 54 | |
| 55 | From a global skill install, run `scripts/validate_repo.py` from this skill's |
| 56 | directory instead of the repo-relative path. |
| 57 | |
| 58 | ## Backup Check |
| 59 | |
| 60 | Create and verify a skills-only backup: |
| 61 | |
| 62 | ```bash |
| 63 | bash .claude/skills/mathodology-whole-project/scripts/create-source-backup.sh |
| 64 | ``` |
| 65 | |
| 66 | Then check the printed backup directory: |
| 67 | |
| 68 | ```bash |
| 69 | shasum -a 256 -c SHA256SUMS |
| 70 | tar -tzf mathodology-skills-<timestamp>.tar.gz | rg '^(AGENTS.md|\\.claude/skills/)' |
| 71 | tar -tzf mathodology-skills-<timestamp>.tar.gz | rg '^(apps/|crates/|packages/|scripts/|config/|installer/|tests/|data/|\\.github/)' |
| 72 | ``` |
| 73 | |
| 74 | The last command should produce no matches. |
| 75 | |
| 76 | ## Archived Dev And Release Knowledge |
| 77 | |
| 78 | The former project used a multi-language application stack with service builds, contract generation, tests, deployment files, and release packaging. Those files were removed from the current branch. |
| 79 | |
| 80 | If the user needs to rebuild or audit those workflows, first recover the relevant historical tree in a separate branch or worktree. Do not treat old commands as valid gates in the skills-only checkout. |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
