Skip to content
Agentmart
Submit a tool

implement-ticket

Implement one or more tk tickets.

Skill by phobologic

IndexedMIT★ 7
Write a review

Chalk Labs

Need help deploying implement-ticket?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/phobologic-implement-ticket

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.

We use your email only for this newsletter. Privacy

About

Implement one or more tk tickets. Use when the user says "implement ticket X", "work on ticket", "do ticket

No 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-ticket

What's inside

Skill name
implement-ticket
Description
Implement one or more tk tickets. Use when the user says "implement ticket X", "work on ticket", "do ticket
License
MIT
Instructions
101 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Implement Ticket

## Phase 0 — Argument parsing

Parse `$ARGUMENTS`:
- Ticket IDs are space-separated tokens before any `--`
- Everything after `--` is extra instructions that inform the design phase
- Examples:
  - `/implement-ticket 42` — single ticket
  - `/implement-ticket 42 43` — process both, sequentially
  - `/implement-ticket 42 -- focus on error handling, skip migration` — ticket with constraints

## Phase 1 — Ticket selection

**If ticket IDs were provided**: run `tk show-multi <ids>` to load full context.

**If any loaded ticket has `type == "epic"`**:
1. Run `tk query '.parent == "<epic-id>"'` to find its child tickets
2. Filter to only eligible children (status is not `closed` or `in-progress`)
3. If no eligible children remain, inform the user the epic is fully complete or all work is in-progress, and stop
4. Present suggested next tickets with reasoning (same UX as the no-args path: 2–3 picks + full list)
5. Ask the user which child ticket(s) to proceed with
6. Continue the rest of the skill with those child IDs — never implement the epic itself

**If no IDs provided**:
1. Run `tk ready` to get unblocked work
2. Read each ticket's description to understand scope and context
3. Present two things to the user:
   - **Suggested next tickets** (2–3 picks with reasoning — e.g., "unblocks the most
     downstream work", "highest priority", "quickest win based on scope")
   - **Full ready list** for their reference
4. Ask the user which ticket(s) to proceed with

## Phase 2 — Complexity triage

Read the selected ticket(s) and parent epic (if set). Make a judgment call:

**Straightforward** — typo, config change, single clear action with no design ambiguity:
- Describe what you'll do in 1–2 sentences
- Ask the user for a quick go-ahead
- Skip Phases 3–4 and proceed directly to implementation

**Complex** — new feature, tricky bug, or non-obvious design decisions:
- Proceed through the full design and planning flow below

## Phase 3 — Design discussion (complex only)

Before writing any plan:

1. Scan the affected code area with Glob and Grep to understand existing patterns
2. Check for reusable utilities — avoid reinventing what already exists
3. Incorporate any extra instructions from Phase 0 as constraints on the design
4. Identify open questions: ambiguous acceptance criteria, approach tradeoffs,
   constraints from CLAUDE.md or the parent epic
5. Work through each question interactively with the user

This phase ends when design intent is unambiguous.

## Phase 4 — Plan + approval (complex only)

Present a full implementation plan:
- Files to create or modify
- Key decisions made in Phase 3
- Test strategy (what to test, how)
- Schema or migration changes if applicable

Wait for explicit user approval before writing any code.

## Phase 5 — Implementation

Run `tk start <id>` to claim the ticket, then implement according to the approved plan.

## Phase 6 — Tests

1. Run tests scoped to the changed area first (faster feedback)
2. Run the full test suite
3. Fix any failures before continuing — do not proceed with a broken suite

## Phase 7 — Self-review

Before committing, use the Skill tool to invoke the `review` skill. Read its output and triage findings:

- **Critical issues found**: present them to the user, fix them, then repeat Phase 7 until the review is clean
- **High issues found**: present them to the user and ask — fix now, or create a ticket and proceed?
- **Medium findings**: the review skill will auto-create tk tickets; note the ticket IDs in the Phase 8 ticket note
- **No Critical or High issues**: proceed to Phase 8

## Phase 8 — Commit + close

1. Stage relevant files and commit with a message that references the ticket ID
2. `tk add-note <id> "..."` — record design decisions made in Phase 3, approaches
   considered, any gotchas encountered, and any review ticket IDs created in Phase 7
3. `tk close <id>`
4. Run `git status` and confirm it's clean

## Multiple tickets

If multiple ticket IDs were provided, process them one at a time in the order given.
Complete all phases for each ticket before starting the next.

From phobologic/claude_code, MIT.

Signals

Stars
7
Forks
0
Open issues
0
Last commit (this folder)
Mar 30, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from phobologic

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get implement-ticket running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying implement-ticket?

CallGet help
Cite this page

implement-ticket skill. Agent Mart. https://agentmart.dev/skills/phobologic-implement-ticket (last updated 2026-10-24)