implement
Use when implementing a spec or GitHub ticket in this checkout.
Skill by Kripu77
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/kripu77-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
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
- Use when implementing a spec or GitHub ticket in this checkout.
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Implement
Implement only the ticket you were given.
1. Read CONTEXT-MAP, this repo CONTEXT.md, ADRs, docs/agents if they exist.
2. Find a similar, recently-merged example in this repo (a file or PR doing the same kind of thing) and match its patterns. If none exists, say so in the PR description.
3. Use `/tdd` at pre-agreed seams.
4. Typecheck often. Run focused tests often. Full suite once at the end.
5. `/unslop` against main.
6. Open or update a PR. Do not merge.
7. Stop and ask for `/code-review` then `/loop-on-ci`.
## Review feedback
When you act on a review comment on your PR, resolve its thread. Threads you did not act on, or replied to with a dispute, stay unresolved with a reply.
```bash
# List threads with ids
gh api graphql -f query='query($owner:String!,$name:String!,$pr:Int!){repository(owner:$owner,name:$name){pullRequest(number:$pr){reviewThreads(first:100){nodes{id isResolved comments(first:1){nodes{path body}}}}}}}' -F owner=<owner> -F name=<repo> -F pr=<number>
# Resolve one addressed thread
gh api graphql -f query='mutation($id:ID!){resolveReviewThread(input:{threadId:$id}){thread{isResolved}}}' -F id=<thread-id>
# Reply to a skipped or disputed thread (leave unresolved)
gh api graphql -f query='mutation($id:ID!,$body:String!){addPullRequestReviewThreadReply(input:{pullRequestReviewThreadId:$id,body:$body}){comment{url}}}' -F id=<thread-id> -f body='<why skipped or disputed>'
```
## Extra rules
- No code comments
- Commit one complete thought at a time. The message names that thought. Keep the diff small. If the thought would be huge, split the ticket. No line-count cap.
- Do not refactor adjacent code unless the ticket says so
- No type assertions; follow local TypeScript/Go practice
- PR title: `Type/<issue.number>/<short description>` (Feat, Bug, Arch, Chore, Refactor, General)
- PR description: human, at most 3 sentences, then mermaid. Feature: before and after when a prior shape exists, after-only when net-new. Bug: before and after
- Never merge. A person merges.From Kripu77/software-factory, MIT.
More from Kripu77/software-factory
- 0.586score
mermaid
Kripu77
Generate Mermaid diagrams from user requirements.
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
browser-use
Kripu77
Drive a real browser to QA a running app.
SkillBFreshness: B★ 7Claude Code +9 - 0.583score
to-tickets
Kripu77
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
run-smoke-tests
Kripu77
Run Playwright smoke tests, debug failures, and verify fixes.
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
tdd
Kripu77
Use when implementing features or bug fixes test-first.
SkillBFreshness: B★ 7Claude Code +9 - 0.559score
code-review
Kripu77
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
SkillBFreshness: B★ 7Claude Code +9 - 0.313score
lead
Kripu77
No description from the publisher yet.
SkillBFreshness: B★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 1
- Open issues
- 7
- Last commit (this folder)
- Aug 30, 2026 (2 months ago)
- Last release
- Sep 3, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Kripu77/software-factory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kripu77
- 0.586score
mermaid
Kripu77
Generate Mermaid diagrams from user requirements.
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
browser-use
Kripu77
Drive a real browser to QA a running app.
SkillBFreshness: B★ 7Claude Code +9 - 0.583score
to-tickets
Kripu77
Use when breaking a plan into tracer-bullet GitHub issues with blocking edges.
SkillBFreshness: B★ 7Claude Code +9 - 0.581score
run-smoke-tests
Kripu77
Run Playwright smoke tests, debug failures, and verify fixes.
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
tdd
Kripu77
Use when implementing features or bug fixes test-first.
SkillBFreshness: B★ 7Claude Code +9 - 0.559score
code-review
Kripu77
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
SkillBFreshness: B★ 7Claude Code +9
Cite this page
implement skill. Agent Mart. https://agentmart.dev/skills/kripu77-implement (last updated 2026-10-24)