skore-skills
AGENTS.md144 starsChanged 17 days agoBSD-3-ClauseView on GitHub
Applies repo-wide. - Read the closest AGENTS.md for the area you touch. - Before committing, run the lint task from pixi.toml: pixi run -e lint lint. That is pre-commit run --all-files (ruff, mypy, typos, and the other hooks in .pre-commit-config.yaml). Do not call pre-commit, ruff, or mypy directly, and do not use the ruff binary from the test-py311 environment. - Run relevant tests locally before opening a PR. - PR title: type(scope): Imperative summary. All CI checks must pass before…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- probabl-ai/skillsword for word, first seen Oct 27, 2026
Other versions1 project uses a version of this.
Word for word · 1
- probabl-ai/skills★ 144100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository26 other files it gives its agents.
- add-python-packageSkill
- audit-ml-pipelineSkill
- build-ml-pipelineSkill
- choose-python-librarySkill
- evaluate-ml-pipelineSkill
- explore-ml-dataSkill
- export-ml-notebookSkill
- export-ml-projectSkill
- export-ml-siteSkill
- frame-ml-problemSkill
- manage-ml-backlogSkill
- model-ml-pipelineSkill
- persist-ml-gitSkill
- plot-ml-figureSkill
- research-ml-practiceSkill
- review-ml-choicesSkill
- review-ml-experimentSkill
- search-ml-literatureSkill
- setup-gitSkill
- setup-ml-projectSkill
- setup-python-envSkill
- setup-workspaceSkill
- shape-user-ideaSkill
- smoke-test-ml-pipelineSkill
- sync-ml-reportsSkill
- triage-ml-taskSkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
23 rules. About 0 are common, 16 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈16
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 7
Read the closest AGENTS.md for the area you touch.
- Very specific: line 8
Before committing, run the lint task from pixi.toml: pixi run -e lint lint.
- Distinctive: line 13
Run relevant tests locally before opening a PR.
- Distinctive: line 15
Avoid redundant comments that restate what obvious code already expresses.
- Distinctive: line 22
Update README.md when changing workflow packs, default install behavior, breaking or deprecated catalog ids, or model and harness claims.
- Very specific: line 24
Update tools/README.md or eval/README.md when changing Pixi tasks, version sources, eval authoring, or CI expectations.
- Very specific: line 26
Keep a skill's .catalog.json summary aligned with its SKILL.md description and the README skill overview.
- Very specific: line 28
When skills/*/SKILL.md changes required behavior, update eval/<skill>/prompts.md and regenerate skills/<skill>/evals/evals.json.
- Very specific: line 31
Run pixi run check after changing catalog, skill, plugin, Pixi, or eval metadata.
- Distinctive: line 41
If multiple interpretations exist, present them — don't pick silently.
- Distinctive: line 42
If a simpler approach exists, say so.
- Distinctive: line 43
If something is unclear, stop.
- Distinctive: line 49
No features, abstractions, or configurability beyond what was asked.
- Distinctive: line 50
No error handling for impossible scenarios.
- Distinctive: line 51
If you write 200 lines and it could be 50, rewrite it.
- Distinctive: line 53
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
- Distinctive: line 59
Don't improve adjacent code, comments, or formatting.
- Distinctive: line 60
Don't refactor things that aren't broken.
- Distinctive: line 62
If you notice unrelated dead code, mention it — don't delete it.
- Very specific: line 63
Remove imports/variables/functions that YOUR changes made unused.
- Distinctive: line 65
Every changed line should trace directly to the user's request.
- Distinctive: line 90
Do not land a subcommand or helper uncovered, and do not defer tests to a follow-up.
- Very specific: line 93
Before opening a PR that touches the CLI or its tests, the commit-time pixi run -e lint lint step above must already be clean.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS
Applies repo-wide.
Workflow
- Read the closest
AGENTS.mdfor the area you touch. - Before committing, run the
linttask frompixi.toml:pixi run -e lint lint. That ispre-commit run --all-files(ruff, mypy, typos, and the other hooks in.pre-commit-config.yaml). Do not callpre-commit,ruff, ormypydirectly, and do not use theruffbinary from thetest-py311environment. - Run relevant tests locally before opening a PR.
- PR title:
type(scope): Imperative summary. All CI checks must pass before merge. - Avoid redundant comments that restate what obvious code already expresses.
Documentation
Ship documentation updates in the same PR as user- or contributor-visible changes:
- Update
README.mdwhen changing workflow packs, default install behavior, breaking or deprecated catalog ids, or model and harness claims. - Update
tools/README.mdoreval/README.mdwhen changing Pixi tasks, version sources, eval authoring, or CI expectations. - Keep a skill's
.catalog.jsonsummaryaligned with itsSKILL.mddescription and the README skill overview. - When
skills/*/SKILL.mdchanges required behavior, updateeval/<skill>/prompts.mdand regenerateskills/<skill>/evals/evals.json.
Run pixi run check after changing catalog, skill, plugin, Pixi, or eval
metadata.
Coding Discipline
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them — don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features, abstractions, or configurability beyond what was asked.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
- Don't improve adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it — don't delete it.
- Remove imports/variables/functions that YOUR changes made unused.
Every changed line should trace directly to the user's request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
CLI package (src/skore_skills)
Any change under src/skore_skills/ ships pytest in the same PR.
Do not land a subcommand or helper uncovered, and do not defer tests
to a follow-up.
Before opening a PR that touches the CLI or its tests, the commit-time
pixi run -e lint lint step above must already be clean. Then run
pixi run -e test-py311 tests (pytest with --cov=skore_skills).
New subcommands need tests for the happy path, bad argv / missing
inputs, and at least one failure mode. Do not merge if the change
adds branches Codecov would mark uncovered (project/patch drop
beyond the 1% auto threshold in codecov.yml).
Catalog-only edits (skills/, .catalog.json, plugin manifests):
run pixi run check. Do not run the LLM eval suite unless the PR
touches eval/ or skills/*/SKILL.md.
Website (site/)
site/ is an Astro app. The site Pixi environment provides Node.js
and nothing else. Build with pixi run -e site site-build.
Pull requests that change the site are built by .github/workflows/site.yml.
The page reads ../.catalog.json. Catalog edits still go through
pixi run check. Do not run the LLM eval suite for site-only changes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

