small-diff
Keep a task's implementation complete, focused, and compatible with parallel work.
Skill by R4yHarris
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/r4yharris-small-diff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/small-diff
What's inside
- Skill name
small-diff- Description
- Keep a task's implementation complete, focused, and compatible with parallel work.
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Small complete diff ## When to use Use while choosing an implementation and before reporting the final changes. ## Steps 1. Map each edit to TASK.md acceptance checks and allowed paths. 2. Reuse existing helpers, naming, formatting, and dependencies. Avoid unrelated refactors, generated files, policy/workflow edits, and vendor changes. 3. Preserve other agents' work. For example, retain existing difficulty and estimate fields when adding task skill metadata; do not replace the template. 4. Include tightly related tests and documentation, then verify behavior after the last edit. A smaller but incomplete change is not a successful result. ## Stop condition Stop when all necessary edits are scoped and verified. If completion requires wider scope or conflicts with another task, report the exact gap without overwriting other work or weakening acceptance checks.
From R4yHarris/github-agent-roster, MIT.
More from R4yHarris/github-agent-roster
- 0.565score
rust-cargo
R4yHarris
Use when building, linting, testing or packaging Rust, changing Cargo manifests, or evaluating a native framework or dependency.
SkillAFreshness: AClaude Code +9 - 0.565score
run-tests
R4yHarris
Use when verifying TASK.md acceptance checks with the task language's approved native runner and recording actual evidence.
SkillAFreshness: AClaude Code +9 - 0.564score
implement
R4yHarris
Use when an agreed TASK.md authorizes software implementation with concrete allowed files and checks.
SkillAFreshness: AClaude Code +9 - 0.564score
incident
R4yHarris
Use when TASK.md requests incident triage, regression diagnosis or an explicitly bounded hotfix.
SkillAFreshness: AClaude Code +9 - 0.564score
research
R4yHarris
Use when a scoped task needs repository discovery, source comparison or an evidence inventory.
SkillAFreshness: AClaude Code +9 - 0.564score
review
R4yHarris
Use when a task requests review preparation or inspection of a scoped diff and its verification evidence.
SkillAFreshness: AClaude Code +9 - 0.564score
rust-implementation
R4yHarris
Use when implementing, porting, testing or reviewing the native Rust Roster runtime and its behavioral contracts.
SkillAFreshness: AClaude Code +9 - 0.564score
docs
R4yHarris
Use when TASK.md requests a design, guide, instructions or other documentation deliverable.
SkillAFreshness: AClaude Code +9 - 0.564score
rust-tokio
R4yHarris
Use when implementing Tokio futures, cancellation, deadlines, owned process I/O or async transport in the Rust runtime.
SkillAFreshness: AClaude Code +9 - 0.561score
implement-task
R4yHarris
Implement a bounded software task from TASK.md in one assigned coder worktree, with acceptance evidence and a contracts publishing handoff.
SkillAFreshness: AClaude Code +9 - 0.558score
result-report
R4yHarris
Report factual changes, checks, and the first remaining gap for the harness result.
SkillAFreshness: AClaude Code +9 - 0.558score
rust-tokio
R4yHarris
Use when implementing Tokio async process I/O, transport, deadlines or revocable cancellation in Rust.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Sep 29, 2026 (29 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/R4yHarris/github-agent-roster
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from R4yHarris
- 0.565score
rust-cargo
R4yHarris
Use when building, linting, testing or packaging Rust, changing Cargo manifests, or evaluating a native framework or dependency.
SkillAFreshness: AClaude Code +9 - 0.565score
run-tests
R4yHarris
Use when verifying TASK.md acceptance checks with the task language's approved native runner and recording actual evidence.
SkillAFreshness: AClaude Code +9 - 0.564score
docs
R4yHarris
Use when TASK.md requests a design, guide, instructions or other documentation deliverable.
SkillAFreshness: AClaude Code +9 - 0.564score
incident
R4yHarris
Use when TASK.md requests incident triage, regression diagnosis or an explicitly bounded hotfix.
SkillAFreshness: AClaude Code +9 - 0.564score
research
R4yHarris
Use when a scoped task needs repository discovery, source comparison or an evidence inventory.
SkillAFreshness: AClaude Code +9 - 0.564score
implement
R4yHarris
Use when an agreed TASK.md authorizes software implementation with concrete allowed files and checks.
SkillAFreshness: AClaude Code +9
Cite this page
small-diff skill. Agent Mart. https://agentmart.dev/skills/r4yharris-small-diff (last updated 2026-10-24)