Skip to content
Skills Library
Management & product · Building & coding

build-implementation

/build-implementation

Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".

Repository
skene ↗
Licence
MIT
Last repository change
26.08.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.08.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".

Triggers from the description

buildimplementgenerate codecreate prompthow do I build this
Original author description

Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".

How it works

  1. Agent behavior rules
  2. Steps
  3. Error handling
  4. Output
Original SKILL.md headings · 46 lines, 286 words
SKILL.md preview
---
name: build-implementation
description: Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".
---

# Build Implementation Prompt

Generate implementation prompts via the Skene CLI. **The CLI generates the plan, not you.**

## Agent behavior rules

- **Autonomous.** Run the CLI, read the output, execute the implementation. No mid-flow questions.
- **CLI is the source of truth.** If `uvx skene build` fails, report the error. Do NOT write your own implementation plan as a substitute.
- **User cannot type into agent terminals.** The agent handles all CLI input.

## Steps

1. **Discover CLI options**
   Run `uvx skene build --help` to see available flags and understand any interactive prompts.

2. **Verify loop selection**
   `ls .skene/active-loop.json 2>/dev/null || ls skene-context/growth-loops/ 2>/dev/null || ls skene/growth-loops/ 2>/dev/null`
   If missing: "Run `/skene-plan` first." Stop.

3. **Generate implementation prompt**
   The CLI may present a menu (e.g. "Select option [1/2/3/4]"). Always pipe the option that shows the full prompt in the terminal (typically `3` for "Show full prompt"):
   ```
   echo 3 | uvx skene build
   ```
   If the menu options differ from expected, check --help output or the terminal output to pick the "show/print prompt" option.

4. **Read the prompt**
   The CLI saves output to `skene-context/growth-loops/` (legacy `skene/growth-loops/`). Read the full implementation prompt from the terminal output or that directory.

5. **Execute the prompt**
   Start implementing the steps from the CLI-generated prompt directly. Present a brief summary of what will be done, then execute. Break large implementations into logical chunks.

6. **Report completion**
   "Implementation complete. Run `/skene-status` to validate."

## Error handling

- **CLI failure**: Report error, suggest fix. Do NOT fabricate implementation plans.
- **Stuck on menu prompt**: Kill terminal, re-run with piped input.
- **Permission errors**: Give user the command for their terminal.

## Output

Summary of what was implemented + "Run `/skene-status` to validate."

Versions

The database has no other skills named build-implementation.

Database snapshot: 13.11.2026 · package version 39d04afbf5da (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90plan-growth-loop
    Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
  • 100prompt-generator
    Generate implementation prompts for phase-based project execution using an orchestration pattern. Use when users request prompts for implementing project phases, need orchestration prompts for multi-step implementations, ask for "/prompt", "generate prompt", "create…
  • 90validate-loop
    Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
  • 90to-spec
    Turn the current conversation context into an implementation-ready spec or spec set. Use when the user wants to capture a design or implementation plan as a SPEC.
  • 100build-test-guide
    Guide users to build and test their MVP using the BMAD Method with PMF context files. Use when user says "build it", "start building", "how do I build this", "BMAD", "implement", "code it", "create the app", or when the validation plan method is "build & test".
  • 91create-tasks
    Generate Claude Code native Tasks from an existing spec. Use when user says "create tasks", "generate tasks from spec", "spec to tasks", "task generation", or wants to decompose a spec into implementation tasks.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.