ad-implement
Use to implement a fix for a known issue, or to implement a new feature.
Skill by ansidev
Chalk Labs
Need help deploying ad-implement?
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.
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/ansidev-ad-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: marketing
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/ad-implement
What's inside
- Skill name
ad-implement- Description
- Use to implement a fix for a known issue, or to implement a new feature.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Input - A markdown file describing the task, constraints, acceptance criteria, and relevant project context. - If the task is ambiguous, unclear, or missing required context, stop and ask for clarification before implementation starts. ## Main Workflow 1. **Scope and plan check** - Confirm the task is bounded, the success criteria are explicit, and the work can be broken into independent sub-tasks when appropriate. 2. **dispatching-parallel-agents** - Activates with the plan. Dispatches fresh subagents per task in parallel when the work is independent; otherwise keep execution sequential. Each task is reviewed in two stages: spec compliance, then code quality. ## Subagent Workflow 1. **using-git-worktrees** - Activates before implementing a task. Each subagent creates an isolated worktree on a fresh branch for the task, sets up the required project environment, and confirms the baseline is clean before code changes begin. 2. **test-driven-development** - Activates during implementation. Enforces RED-GREEN-REFACTOR: write a failing test that captures the behavior, run it and confirm it fails, implement the minimal fix, run the targeted check and confirm it passes, then refactor if needed. Code written before the failing test is considered invalid and must be deleted or rewritten. 3. **requesting-code-review** - Activates between tasks or milestones. Reviews the delta against the plan and acceptance criteria, reports issues by severity, and blocks progress on critical findings. If evidence is missing, the reviewer must call for a verification step before continuing. 4. **finishing-a-development-branch** - Activates when the task is complete and review is cleared. Verifies the relevant tests/build checks still pass, presents the merge options (rebase then merge/PR/keep/discard), and cleans up the worktree. **The agent checks for relevant skills before any task.** Mandatory workflows, not suggestions. **Required gate:** no task continues past a review checkpoint or implementation milestone unless the relevant verification evidence exists and the required checks have passed.
From ansidev/skills, MIT.
More from ansidev/skills
- 0.570score
kp-issue-finish
ansidev
Use this skill to finish a kanpal issue after the user has manually reviewed and approved the implementation.
SkillAFreshness: AClaude Code +9 - 0.570score
kp-issue-start
ansidev
Use this skill to start working on the solution for the relevant kanpal issue.
SkillAFreshness: AClaude Code +9 - 0.560score
add-knowledge
ansidev
Add knowledge to OpenKnowledge base.
SkillAFreshness: AClaude Code +9 - 0.536score
kp-issue-new
ansidev
Use this skill whenever the user wants to create a new issue in Kanpal.
SkillAFreshness: AClaude Code +9 - 0.524score
wt-commit
ansidev
Use this skill when a task is finished and its changes need to be committed — either in a git worktree on a detached HEAD (commit the pending changes and…
SkillBFreshness: BClaude Code +9 - 0.523score
ad-review-pr
ansidev
Use when reviewing a pull request for correctness, completeness, and quality.
SkillBFreshness: BClaude Code +9 - 0.523score
ad-research
ansidev
Use when research something and save the result to the knowledgebase
SkillBFreshness: BClaude Code +9 - 0.520score
ad-investigate
ansidev
Use when investigating an issue
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 4, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ansidev/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ansidev
- 0.570score
kp-issue-finish
ansidev
Use this skill to finish a kanpal issue after the user has manually reviewed and approved the implementation.
SkillAFreshness: AClaude Code +9 - 0.570score
kp-issue-start
ansidev
Use this skill to start working on the solution for the relevant kanpal issue.
SkillAFreshness: AClaude Code +9 - 0.560score
add-knowledge
ansidev
Add knowledge to OpenKnowledge base.
SkillAFreshness: AClaude Code +9 - 0.536score
kp-issue-new
ansidev
Use this skill whenever the user wants to create a new issue in Kanpal.
SkillAFreshness: AClaude Code +9 - 0.524score
wt-commit
ansidev
Use this skill when a task is finished and its changes need to be committed — either in a git worktree on a detached HEAD (commit the pending changes and…
SkillBFreshness: BClaude Code +9 - 0.523score
ad-research
ansidev
Use when research something and save the result to the knowledgebase
SkillBFreshness: BClaude Code +9
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 ad-implement 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.
Cite this page
ad-implement skill. Agent Mart. https://agentmart.dev/skills/ansidev-ad-implement (last updated 2026-10-24)