implement
Entry point orchestrator for the feature development pipeline.
Skill by autoencoders
Chalk Labs
Need help deploying 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/autoencoders-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: data
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
- Entry point orchestrator for the feature development pipeline. Runs evaluate, define, plan, implement, verify, and validate as a closed loop. Invoke with "/implement [options] idea" to go from half-baked idea to working, validated code. Supports execute mode (full pipeline) and explore mode (preparation with resume). Triggers on "/implement", "implement this", or any message starting with "/implement".
- License
- CC-BY-4.0
- Instructions
- 472 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /implement — Feature Development Pipeline
Single entry point to go from half-baked idea to working, validated code.
## What /implement Is
`/implement` is the **state machine controller** for the full pipeline:
```
evaluate → define → plan → implement → blind-verify → validate → (iterate) → release
```
Primary output: **Working changes + validation decision + iteration log**
Not a document generator. An execution orchestrator.
## Usage
```
/implement [options] <your idea>
```
## Options (Minimal Set)
| Option | Values | Default | Description |
|--------|--------|---------|-------------|
| `--mode` | `execute`, `explore` | `execute` | Full pipeline or preparation-only |
| `--timebox` | `5`, `10`, `20` | `10` | Hard cap on depth (minutes of rigor) |
| `--accept` | `"<bullets>"` | none | User-provided acceptance criteria |
| `--waive-blind` | flag | off | Skip role separation (stamps output) |
| `--resume` | `<bundle>` | none | Continue from explore output |
| `--risk` | `low`, `med`, `high` | inferred | Override risk inference |
## Examples
```bash
# Default: full execution pipeline
/implement add user authentication with OAuth2
# Quick exploration (stops at plan, resumable)
/implement --mode explore add real-time collaboration
# Continue from exploration
/implement --resume <previous-bundle>
# Tight timebox for small feature
/implement --timebox 5 add logout button to header
# Provide acceptance criteria upfront
/implement --accept "[CRITICAL] Returns 401 for invalid tokens; Tokens expire after 1 hour" add JWT auth
# High-risk override (triggers red-team pass)
/implement --risk high migrate to new database schema
```
## Execution Modes
### Execute Mode (default)
Runs full pipeline end-to-end:
```
evaluate → quick-check → define → plan → quick-check → implement
→ early-check → blind-verify → completion-validate
→ (iterate ≤2) → release-plan → post-check
```
Stops only on:
- **Accept**: Working code validated
- **Reject**: Fundamental mismatch, needs re-scope
- **Escalate**: Max iterations hit or unclear problem
### Explore Mode
Produces resumable preparation artifacts:
```
evaluate → quick-check → define → plan → quick-check → STOP
```
Output: Stable "implement plan bundle" containing:
- Evaluation summary
- Acceptance criteria (with [CRITICAL] tags)
- Implementation plan
- Quick-check results
Ends with continuation command:
```
To execute: /implement --resume <bundle-id>
```
**Key rule**: Explore output is complete enough that execute mode does not regenerate it.
## Pipeline Stages
### Stage 1: EVALUATE
Determine if this is worth building.
Output:
```
EVALUATE
────────
Problem: [What pain point]
Why now: [Urgency driver]
Upside: [Value if successful]
Don't-build case: [Counterargument]
Risk: [Low/Med/High] — [Inferred or specified]
Timebox: [5/10/20] — [Depth of rigor]
```
### Stage 2: QUICK-CHECK (Alignment)
Fast sanity check before proceeding.
```
Quick-check: Alignment
──────────────────────From autoencoders/skills, CC-BY-4.0.
More from autoencoders/skills
- 0.414score
feature-implementation
autoencoders
Executes implementation plans with closed-loop verification.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-evaluator
autoencoders
Structured evaluation of proposed features for existing projects.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-planning
autoencoders
Creates detailed implementation plans for approved features.
SkillDFreshness: DClaude Code +9 - 0.414score
scaffold
autoencoders
Unified skill for Python project scaffolding with uv workspaces.
SkillDFreshness: DClaude Code +9 - 0.409score
completion-validation
autoencoders
Reconciles intended feature against blind inference.
SkillDFreshness: DClaude Code +9 - 0.409score
implementation-verification
autoencoders
Blind inference of what was implemented from code changes only.
SkillDFreshness: DClaude Code +9 - 0.396score
hello
autoencoders
A simple test skill that says hi.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 6, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- CC-BY-4.0
- Repository
- github.com/autoencoders/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from autoencoders
- 0.414score
feature-evaluator
autoencoders
Structured evaluation of proposed features for existing projects.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-implementation
autoencoders
Executes implementation plans with closed-loop verification.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-planning
autoencoders
Creates detailed implementation plans for approved features.
SkillDFreshness: DClaude Code +9 - 0.414score
scaffold
autoencoders
Unified skill for Python project scaffolding with uv workspaces.
SkillDFreshness: DClaude Code +9 - 0.409score
completion-validation
autoencoders
Reconciles intended feature against blind inference.
SkillDFreshness: DClaude Code +9 - 0.409score
implementation-verification
autoencoders
Blind inference of what was implemented from code changes only.
SkillDFreshness: DClaude 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 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
implement skill. Agent Mart. https://agentmart.dev/skills/autoencoders-implement (last updated 2026-10-24)