implement
Full implementation mode - end-to-end feature implementation with phased execution, parallel work streams, verification gates, and atomic commits per phase
Skill by thoreinstein
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/thoreinstein-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
- Full implementation mode - end-to-end feature implementation with phased execution, parallel work streams, verification gates, and atomic commits per phase
- License
- MIT
- Metadata
- author: thoreinstein · version: 1.1.0
- Instructions
- 292 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- compatibility: must be text of at most 500 characters
- allowed-tools: must be a space-separated string
Files (3)
- SKILL.md
- implement-phases.md · references/
- implementation-summary.md · references/templates/
SKILL.md (first lines)
# Implement Execute complete feature implementations using a structured, phased approach with verification gates and atomic commits. ## HARD CONSTRAINTS (NON-NEGOTIABLE) - **SCOPE IS LOCKED** — Only implement what is in the plan from `/analyze`. Nothing more. - **NO SCOPE CREEP** — Do not implement work from other tickets, even if it seems related or helpful. - **TICKET TRACKING IS MANDATORY** — Update ticket status (in-progress/done) as you work. - **EPIC CLOSURE RULES** — Never close an epic while child tickets remain open. - **COMMIT BEFORE CLOSE** — A ticket status can only be changed to 'done' AFTER the code changes for that ticket have been successfully committed. - **VERIFY BEFORE COMMIT** — No code shall be committed until all verification steps (tests, lint, build, etc.) have passed successfully. If any check fails, you MUST resolve the issues and re-verify before attempting to commit. - **NO --NO-VERIFY** — Never, under any circumstances, use the `--no-verify` flag with git commit. Pre-commit hooks must always run and pass. If they fail, fix the code. No exceptions, even if explicitly requested. - **NO BRANCH CREATION** — Never create branches. The agent will already be on the appropriate branch when `/implement` is invoked. Do not run `git checkout -b`, `git branch`, or `git switch -c`. Work on the current branch. ### Scope Creep Self-Check Before writing ANY code, ask: 1. Is this in the implementation plan? → NO = don't implement 2. Is this ticket in scope for this phase? → NO = don't implement 3. Am I adding something "nice to have"? → YES = note as follow-up, don't implement If you discover related work, add it to "Discovered Follow-Up Items" and continue with scoped work. ## When to Use - Building new features end-to-end - Complex multi-component implementations - Features requiring coordination across backend, frontend, and infrastructure - Any implementation benefiting from structured phases and checkpoints ## Ticket Status Management (Beads Projects) ```bash # Starting work on a ticket bd update <ticket-id> --status in-progress # Completing a ticket bd update <ticket-id> --status done # Verify epic children before closing bd show <epic-id> --json # All children must be status:done ``` ### Status Update Rules | Event | Action | | ----- | ------ | | Starting implementation | Mark parent ticket in-progress | | Starting a child ticket in a phase | Mark child in-progress | | Completing a child ticket | Mark child done | | ALL children done → close epic | Mark epic done | **NEVER close an epic while children are still open.** ## Phase Execution Loop Every phase follows this exact sequence: ``` ┌─────────────────────────────────────────────────────────────┐ │ PHASE EXECUTION LOOP │ ├─────────────────────────────────────────────────────────────┤ │ │ │ 1. PLAN → Define work for this phase │ │ Mark phase tickets as in_progress │ │ │ │ 2. WORK → Execute the phase work │ │ ⚠️ ONLY work in the plan — no extras │ │ │ │ 3. VERIFY → Run verification checklist │ │ Tests pass, lints clean, build succeeds │ │ │ │ 4. COMMIT → Create atomic commit for phase │ │ Include ticket IDs in commit message │ │ │ │ 5. UPDATE → Mark completed tickets as done │ │ bd update <ticket-id> --status done │ │ │ │ 6. PROCEED → Only after commit + ticket updates │ │ Move to next phase │ │ │ │ ⚠️ DO NOT PROCEED UNTIL COMMIT SUCCEEDS AND TICKETS │ │ ARE UPDATED │ │ │ │ ⚠️ NEVER mark a ticket done until its changes are │ │ committed. │ │ │ └─────────────────────────────────────────────────────────────┘ ``` ## Phase Overview | Phase | Name | Description | |-------|------|-------------| | 1 | Requirements Analysis | Gather context, clarify requirements, set up tracking | | 2 | Architecture Decision | Evaluate approaches, document decisions (if needed) | | 3 | Parallel Implementation | Execute implementation across work streams | | 4 | Integration | Integrate components, resolve conflicts | | 5 | Verification | Run full verification checklist | | 6 | Documentation & Cleanup | Update docs, clean up tracking, summarize | See `references/implement-phases.md` for detailed phase instructions. ## Task Tracking Setup Define ALL phases upfront before starting implementation: ``` Phase 1: Requirements Analysis - [ ] Gather context - [ ] Clarify requirements - [ ] Commit planning artifacts Phase 2: Architecture Decision (if needed) - [ ] Evaluate approaches - [ ] Document decision - [ ] Commit architecture docs
From thoreinstein/agents, MIT.
More from thoreinstein/agents
- 0.454score
core-web-vitals
addyosmani
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
performance
addyosmani
Optimize web performance for faster loading and better user experience.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
code-review
thoreinstein
Comprehensive code review with security, performance, and maintainability focus.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
debug
thoreinstein
Guide systematic debugging through hypothesis generation, evidence collection, and verification.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
bugfix
thoreinstein
Diagnose and fix bugs using hypothesis-driven debugging, diagnostic instrumentation, architecture-aware analysis, and evidence-based root cause identification
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
content-writer
thoreinstein
Research-driven content writing with citations, iterative outlines, and real-time feedback.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
deploy-checklist
thoreinstein
Generate deployment checklists with pre-flight checks, rollout strategy, and verification steps.
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
refactor
thoreinstein
Analyze code and suggest refactoring opportunities with blast radius assessment, risk evaluation, and recommended order of operations
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
analyze
thoreinstein
Deep analysis mode - thorough multi-phase investigation with expert consultation for complex problems requiring careful examination
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
research
thoreinstein
Research the codebase to find and explain specific topics, answering questions about architecture, configuration, data flows, and implementation details
SkillDFreshness: D★ 3Claude Code +9 - 0.443score
runbook
thoreinstein
Generate operational runbooks for services, procedures, or incident response with step-by-step procedures, troubleshooting guides, and escalation paths
SkillDFreshness: D★ 3Claude Code +9 - 0.442score
figma-design
thoreinstein
Interact with Figma design files via the web browser using the Figma Plugin API.
SkillDFreshness: D★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jan 23, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.1.0
- License
- MIT
- Repository
- github.com/thoreinstein/agents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thoreinstein
- 0.776score
journal
thoreinstein
Use when the user wants to work with their daily note — view today's entry, add a log, do a daily review, or capture quick thoughts.
SkillAFreshness: A★ 102Claude Code +9 - 0.649score
vault
thoreinstein
Use when the user wants to set, change, or create their Obsidian vault, or says "vault", "set vault", "change vault", "create vault", or "new vault".
SkillAFreshness: A★ 102Claude Code +9 - 0.597score
vault-lint
thoreinstein
Use when the user wants a health audit of the vault — stale content, provenance drift, frontmatter compliance, or MOC coverage gaps.
SkillDFreshness: D★ 102Claude Code +9 - 0.597score
moc-update
thoreinstein
Use after creating a new Engineering/ note to suggest which Maps of Content (MOCs) it belongs in.
SkillDFreshness: D★ 102Claude Code +9 - 0.597score
research
thoreinstein
Use when the user asks a question about their vault, wants to explore a topic across notes, or says "research", "find out", "what do I know about", or…
SkillDFreshness: D★ 102Claude Code +9 - 0.597score
wiki-ingest
thoreinstein
Use when the user wants to ingest external sources into the vault — PDFs, markdown files, transcripts, Readwise exports, or any document.
SkillDFreshness: D★ 102Claude Code +9
Cite this page
implement skill. Agent Mart. https://agentmart.dev/skills/thoreinstein-implement (last updated 2026-10-24)