feature-implementation
Executes implementation plans with closed-loop verification.
Skill by autoencoders
Chalk Labs
Need help deploying feature-implementation?
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-feature-implementation
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/feature-implementation
What's inside
- Skill name
feature-implementation- Description
- Executes implementation plans with closed-loop verification. Implements components sequentially, verifies each checkpoint, diagnoses failures, and retries with different approaches up to max-iterations. Use after feature-planning approval. Triggers on "implement this feature", "execute implementation plan", "build this feature", or when transitioning from planning to coding.
- License
- CC-BY-4.0
- Instructions
- 396 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- teemux-debugging.md · references/
SKILL.md (first lines)
# Feature Implementation
Execute implementation plans with self-verification, diagnosis, and controlled retry loops.
## Execution Modes
This skill adapts to the pipeline execution mode:
| Mode | Behavior |
|------|----------|
| `full` | Full implementation with verification loop |
| `fast` | Full implementation with verification loop |
| `prototype` | Full implementation with verification loop |
| `spike` | Implementation only, skip to output (no verification) |
In all modes except `spike`, the full verification loop runs. The rigor happens at the end, not at the gates.
### Spike Mode
In `--mode spike`, skip verification entirely:
```
SPIKE OUTPUT
════════════
Feature: [What was attempted]
Files created/modified:
- [file1] — [what it does]
- [file2] — [what it does]
Status: Code written. No verification performed.
Warning: This is throwaway code. No guarantees it works or matches intent.
Use for learning/experimentation only.
```
## Input Requirements
This skill requires an approved implementation plan containing:
- Component sequence with dependencies
- Verification criteria (locked)
- Stuck detection triggers
- Anti-scope list
If the plan is missing required elements, request them before starting.
In `spike` mode, no plan is required. Just implement based on the request.
## Configuration
```
--max-iterations: 3 (default, configurable per invocation)
```
This controls how many times to retry a failing component before escalating.
## Execution State Machine
```
┌─────────────────────────────────────────────────────────────┐
│ IMPLEMENTATION LOOP │
├─────────────────────────────────────────────────────────────┤
│ │
│ START │
│ │ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ LOAD PLAN │ │
│ │ Set component=1 │ │
│ │ Set attempts=0 │ │
│ └────────┬────────┘ │
│ │ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ IMPLEMENT │◄──────────────────┐ │
│ │ Component N │ │ │
│ └────────┬────────┘ │ │
│ │ │ │
│ ▼ │ │
│ ┌─────────────────┐ │ │
│ │ VERIFY │ │ │
│ │ Run checkpoint │ │ │
│ └────────┬────────┘ │ │
│ │ │ │
│ ┌────┴────┐ │ │
│ │ │ │ │
│ PASS FAIL │ │
│ │ │ │ │
│ │ ▼ │ │
│ │ ┌─────────────────┐ │ │
│ │ │ DIAGNOSE │ │ │
│ │ │ - What failed? │ │ │
│ │ │ - Why? │ │ │
│ │ │ - Same as last? │ │ │
│ │ └────────┬────────┘ │ │
│ │ │ │ │
│ │ ┌────┴────┐ │ │
│ │ │ │ │ │
│ │ attempts attempts │ │
│ │ < max >= max │ │
│ │ │ │ │ │
│ │ │ ▼ │ │
│ │ │ ┌─────────────┐ │ │
│ │ │ │ ESCALATE │ │ │
│ │ │ │ Stop + report│ │ │
│ │ │ └─────────────┘ │ │
│ │ │ │ │
│ │ └─────────────────────────┘ │
│ │ (retry with different approach) │
│ │ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ CHECKPOINT │ │
│ │ Log success │ │
│ │ Next component │ │
│ └────────┬────────┘ │
│ │ │
│ ┌────┴────┐ │From autoencoders/skills, CC-BY-4.0.
More from autoencoders/skills
- 0.414score
feature-planning
autoencoders
Creates detailed implementation plans for approved features.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-evaluator
autoencoders
Structured evaluation of proposed features for existing projects.
SkillDFreshness: DClaude Code +9 - 0.414score
scaffold
autoencoders
Unified skill for Python project scaffolding with uv workspaces.
SkillDFreshness: DClaude Code +9 - 0.409score
implement
autoencoders
Entry point orchestrator for the feature development pipeline.
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-planning
autoencoders
Creates detailed implementation plans for approved features.
SkillDFreshness: DClaude Code +9 - 0.414score
feature-evaluator
autoencoders
Structured evaluation of proposed features for existing projects.
SkillDFreshness: DClaude Code +9 - 0.414score
scaffold
autoencoders
Unified skill for Python project scaffolding with uv workspaces.
SkillDFreshness: DClaude Code +9 - 0.409score
implement
autoencoders
Entry point orchestrator for the feature development pipeline.
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 feature-implementation 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
feature-implementation skill. Agent Mart. https://agentmart.dev/skills/autoencoders-feature-implementation (last updated 2026-10-24)