agentleFS
haojing8312haojing8312/WorkClaw/.agents/skills/workclaw-implementation-strategy/SKILL.md

workclaw-implementation-strategy

Skill141 starsChanged 7 months agoApache-2.0View on GitHub

Use when changing runtime behavior, routing, provider integration, tool permissions, sidecar protocols, or vendor sync boundaries in WorkClaw before editing code.

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to front-load architecture and compatibility thinking before changing risky parts of WorkClaw.

    line 9
  2. Distinctive:

    Do not use this for isolated copy edits or low-risk docs-only changes.

    line 19
  3. Distinctive:

    Follow-on verification commands that will be required

    line 32
  4. Distinctive:

    Prefer the narrowest change that preserves existing contracts.

    line 51
  5. Distinctive:

    Call out uncertainty before editing instead of guessing.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

WorkClaw Implementation Strategy

Overview

Use this skill to front-load architecture and compatibility thinking before changing risky parts of WorkClaw. The goal is to choose the smallest safe implementation path before code changes begin.

When to Use

  • Runtime behavior or chat orchestration changes
  • Provider catalog, model routing, or integration changes
  • Tool permission or approval-flow changes
  • Sidecar bridge, browser automation, or protocol changes
  • Vendor sync or upstream lane boundary changes
  • IM, employee, or cross-surface routing changes

Do not use this for isolated copy edits or low-risk docs-only changes.

Inspect First

  • apps/runtime/src/
  • apps/runtime/src-tauri/src/
  • apps/runtime/sidecar/src/
  • packages/*/src/
  • Related tests in apps/runtime/src/__tests__/, apps/runtime/src-tauri/tests/, apps/runtime/sidecar/test/, and packages/*/tests/

Required Output

  • Changed surface area and affected modules
  • Compatibility or rollout risks
  • Recommended smallest safe implementation path
  • Follow-on verification commands that will be required
  • Release impact if the change touches packaging, vendors, or externally visible behavior

Output Template

Use this shape:

## Strategy Summary
- Change surface:
- Affected modules:
- Main risk:
- Recommended smallest safe path:
- Required verification:
- Release impact:

Core Pattern

  1. Identify the user-visible behavior or boundary being changed.
  2. Trace which frontend, Tauri, sidecar, and Rust modules participate.
  3. Prefer the narrowest change that preserves existing contracts.
  4. Call out uncertainty before editing instead of guessing.
  5. End with the verification and release-readiness follow-ups the change will require.

Common Mistakes

  • Treating sidecar, Tauri, and frontend changes as isolated when the feature crosses all three.
  • Editing provider or routing behavior without checking test coverage in the adjacent layers.
  • Assuming vendor sync changes are mechanical when they may alter release expectations or upstream compatibility.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.