implement
Implement work from an existing spec or set of tickets, including testing, independent review, and a commit.
Skill by sgpopov
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/sgpopov-implement
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: testing
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/implement
What's inside
- Skill name
implement- Description
- Implement work from an existing spec or set of tickets, including testing, independent review, and a commit.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Implement the work described in the user's spec or tickets. Explicit user instructions take precedence over this workflow. Read the spec, relevant repository instructions, and existing code and tests. Identify the acceptance criteria before editing. Resolve routine details from context; ask only when an ambiguity materially affects scope or behavior. Inspect the current branch and working tree. Preserve existing user changes and keep edits focused on the requested work. Use the /tdd skill for behavior changes where practical. Use previously agreed test boundaries when available; otherwise choose appropriate boundaries from the spec and existing tests. Test observable behavior rather than implementation details. Run focused tests and applicable type checks during implementation. Before finishing, verify each acceptance criterion and run the repository's required checks, including the full test suite. If a check cannot run or fails for an unrelated reason, report the limitation explicitly. Have a subagent use the /code-review skill to review the diff against the spec. Validate its findings, fix relevant issues, and explain any dismissed or deferred findings. If independent review is unavailable, perform a self-review and disclose that limitation. After review fixes, rerun affected checks. Repeat broader checks when the fixes could invalidate their earlier results. Commit only the changes belonging to this task on the current branch, unless the user instructed otherwise. Inspect the staged diff before committing. Do not include unrelated changes or push automatically. Report what was implemented, verification results, any unmet acceptance criteria or remaining issues, and the commit identifier if created. Do not describe incomplete or unverified work as fully complete.
From sgpopov/ai-kit, MIT.
More from sgpopov/ai-kit
- 0.588score
ai-visibility
sgpopov
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
log-analyzer
sgpopov
Analyzes application, access, and structured logs for errors, trends, anomalies, and operational evidence.
SkillBFreshness: B★ 1Claude Code +9 - 0.527score
domain-modeling
sgpopov
Build and sharpen a project's domain model.
SkillBFreshness: B★ 1Claude Code +9 - 0.527score
code-review
sgpopov
Conducts multi-axis code review.
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
resolving-merge-conflicts
sgpopov
Use when you need to resolve an in-progress git merge/rebase conflict.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
to-spec
sgpopov
Creates a spec through user interview, codebase exploration, and module design, then submit as a GitHub issue or save as a local markdown file.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
to-tickets
sgpopov
Breaks a PRD into independently-grabbable issues using tracer-bullet vertical slices.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
git-guardrails-claude-code
sgpopov
Sets up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
nestjs-best-practices
sgpopov
Provides NestJS best practices and architecture patterns for production-ready applications and service monorepos.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
grill-me
sgpopov
Interviews the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
react-best-practices
sgpopov
Provides React and Remix.js performance optimization guidelines.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ubiquitous-language
sgpopov
Extracts a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sgpopov/ai-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sgpopov
- 0.588score
ai-visibility
sgpopov
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
log-analyzer
sgpopov
Analyzes application, access, and structured logs for errors, trends, anomalies, and operational evidence.
SkillBFreshness: B★ 1Claude Code +9 - 0.527score
code-review
sgpopov
Conducts multi-axis code review.
SkillBFreshness: B★ 1Claude Code +9 - 0.527score
domain-modeling
sgpopov
Build and sharpen a project's domain model.
SkillBFreshness: B★ 1Claude Code +9 - 0.516score
resolving-merge-conflicts
sgpopov
Use when you need to resolve an in-progress git merge/rebase conflict.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
git-guardrails-claude-code
sgpopov
Sets up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
implement skill. Agent Mart. https://agentmart.dev/skills/sgpopov-implement (last updated 2026-10-24)