Add AI agent guidelines via AGENTS.md and task-specific skills#937
Merged
GlassOfWhiskey merged 1 commit intomasterfrom Apr 17, 2026
Merged
Add AI agent guidelines via AGENTS.md and task-specific skills#937GlassOfWhiskey merged 1 commit intomasterfrom
AGENTS.md and task-specific skills#937GlassOfWhiskey merged 1 commit intomasterfrom
Conversation
ff36e6b to
dcea03b
Compare
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #937 +/- ##
=======================================
Coverage 74.36% 74.36%
=======================================
Files 90 90
Lines 12495 12496 +1
Branches 2192 2193 +1
=======================================
+ Hits 9292 9293 +1
Misses 2682 2682
Partials 521 521 ☔ View full report in Codecov by Sentry. |
bbc512b to
8acd8c8
Compare
edc4c5c to
0c35638
Compare
d5c934c to
fa3d22a
Compare
LanderOtto
approved these changes
Apr 17, 2026
a90f728 to
837101f
Compare
Introduce AGENTS.md with universal rules that apply to every task:
mandatory confirmation before installing packages or committing,
a list of forbidden types (Any, dict[str, Any], etc.), the project
directory tree, and a routing table pointing to task-specific skills.
Add six skill files under .agents/skills/ that expand on specialised
workflows without bloating AGENTS.md:
- code-style/SKILL.md — naming, imports, error handling,
async cleanup, docstring format
- git/SKILL.md — commit message format, type table,
examples from repo history
- testing/SKILL.md — test commands, async fixtures,
CWL conformance test
- mypy/SKILL.md — general mypy workflow, allowed types
- mypy/no-untyped-def/SKILL.md — step-by-step no-untyped-def fixer
- mypy/var-annotated/SKILL.md — step-by-step var-annotated fixer
The design follows a progressive-disclosure principle: AGENTS.md
remains ~55 lines and delegates all task-specific detail to the
appropriate skill file.
837101f to
dd941e8
Compare
AGENTS.mdAGENTS.md and task-specific skills
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Introduce
AGENTS.mdwith universal rules that apply to every task: mandatory confirmation before installing packages or committing, a list of forbidden types (Any,dict[str, Any], etc.), the project directory tree, and a routing table pointing to task-specific skills.Add six skill files under
.agents/skills/that expand on specialised workflows without bloatingAGENTS.md:code-style/SKILL.md— naming, imports, error handling, async cleanup, docstring formatgit/SKILL.md— commit message format, type table, examples from repo historytesting/SKILL.md— test commands, async fixtures, CWL conformance testmypy/SKILL.md— general mypy workflow, allowed typesmypy/no-untyped-def/SKILL.md— step-by-step no-untyped-def fixermypy/var-annotated/SKILL.md— step-by-step var-annotated fixerThe design follows a progressive-disclosure principle:
AGENTS.mdremains ~55 lines and delegates all task-specific detail to the appropriate skill file.