Verify template

Skill jajupmochi/agent-harness/skills/general/verify-template

Run the project's CI gates locally before claiming work is done. Customize the body to match the project's actual lint/test commands. Use before opening a PR or marking a phase complete.From its SKILL.md

Install

npx -y skills add jajupmochi/agent-harness --skill verify-template

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 8 commands, including `uv run ruff check <SRC_DIRS>` and 7 more.

SKILL.md

2.1 KB, 496 tokens by cl100k_base, as published. Nobody here has run it

/verify

Run the full verification gate for this project. Stop on first failure and report it plainly.

Customize this skill per project — the body below is a template. Replace with the project's actual commands. Common templates:

Default Python (uv + ruff + pytest)

uv run ruff check <SRC_DIRS>
uv run ruff format --check <SRC_DIRS>
uv run mypy <SRC_DIRS>            # if mypy is configured
uv run pytest -m "not slow and not download" -v

Replace <SRC_DIRS> with the project's source dirs (e.g., src/ tests/ or <package-name>/ tests/ plugins/).

Default Node.js (TypeScript)

npx tsc --noEmit
npx prettier --check .
npx eslint .                       # if eslint is configured
npx vitest run                     # or npx jest

Static site (HTML / CSS / JSON i18n)

# Validate JSON
for f in locales/*.json data/*.json; do jq empty "$f" || { echo "Invalid: $f"; exit 1; }; done

# i18n parity (if applicable)
python3 scripts/check_i18n_parity.py

# Optional: HTML validation
npx html-validate index*.html

Notes for the agent

Stop on the first failure. Report which step failed and the relevant tool output.
These should mirror the actual CI workflow — if ruff format --check fails, run ruff format to fix, then re-run /verify.
Don't run if there are no edits in flight (skip if working tree is clean and HEAD == upstream).
For research packages, tests should run on CPU and complete in <30 s if possible.

Customization checklist

When using this template in a new project:

Replace <SRC_DIRS> with the project's source directories
Adjust pytest flags (markers, parallelism)
Add or remove mypy step based on whether the project uses it
If pre-commit is configured, prefer pre-commit run --all-files over invoking ruff directly
Drop the templates that don't apply (e.g., remove the Node.js block in a Python project)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 496 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

Read full output and check exit codein 45 of 1524, across 40 files
Verify output confirms the claimin 44 of 1524, across 39 files
Identify the command that proves the claimin 43 of 1524, across 39 files
Execute the full verification commandin 36 of 1524, across 30 files
Produce a verification reportin 34 of 1524, across 18 files
Review git diff changesin 30 of 1524, across 16 files
Fix build failures immediatelyin 29 of 1524, across 9 files
Group findings by severityin 28 of 1524
State claim only with evidencein 27 of 1524, across 22 files
Verify regression tests with red-green cyclein 26 of 1524, across 22 files
Run the full test suitein 26 of 1524, across 25 files
Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

Report relevant tool output
Fix formatting errors if check fails

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.