implementation-strategy
Skill363 starsChanged 12 days agoMITView on GitHub
Choose the implementation and numerical evidence for pyfixest estimator, inference, formula, post-estimation, public API, or shared-core changes. Includes invariant refactors; excludes explanations and prose-only edits.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- openai/openai-guardrails-jstheir own version, first seen Sep 10, 2026
- openai/openai-agents-pythontheir own version, first seen Sep 8, 2026
- openai/openai-guardrails-pythontheir own version, first seen Aug 25, 2026
- xavigiro5ta/agentops-governance-templatetheir own version, first seen Jun 12, 2026
- pproenca/unifi-mcptheir own version, first seen Apr 7, 2026
- openai/openai-agents-jstheir own version, first seen Feb 3, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- openai/openai-agents-python★ 31ksame name
- openai/openai-agents-js★ 4ksame name
- openai/openai-guardrails-python★ 265same name
- openai/openai-guardrails-js★ 113same name
- pproenca/unifi-mcp★ 2same name
- xavigiro5ta/agentops-governance-template★ 1same name
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.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- change-verificationSkill
- pr-handoffSkill
- pr-reviewSkill
The file
Files
Implement a pyfixest change
Find the nearest implementation, its callers, and its tests. Use the architecture seams to choose where the change belongs. Apply the scope policy.
Resolve the decisions that affect this change:
- The user-visible outcome or invariant, and the simplest implementation that preserves the relevant contracts. Read "Stable core" for contract changes; an already-authorized design does not need another approval.
- Affected support paths under result boundaries. New estimators need a complete support matrix; existing features need only the affected paths reconsidered. Reject unsupported combinations explicitly.
- For numerical work, an independent reference under reference selection, and whether results must stay invariant. Read "Release contract" for the applicable baseline check; do not silently turn a refactor into a behavior fix.
- Necessary exports, user documentation, and compatibility decisions.
For a small fix, these decisions can be a brief explanation in the ongoing
work. Write a separate plan only when it helps coordinate substantial work or
the user asks for one. Implement once the material choices are clear; reuse
settled decisions. Verify through change-verification and review the final
diff through pr-review, without restarting the workflow at handoff.
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.