Skip to content
Skills Library
Management & product · Tool integration

initialize-config

/initialize-config

Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".

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
1
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

Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".

Triggers from the description

skene initset up skeneconfigure skene
Original author description

Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".

How it works

  1. Design principle
  2. Steps
  3. Terminal rules
  4. Error handling
  5. Output
Original SKILL.md headings · 67 lines, 436 words
SKILL.md preview
---
name: initialize-config
description: Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".
---

# Initialize Skene Configuration

Set up Skene automatically. The user runs `/skene-init`, everything gets configured, and they see a one-line summary. **Zero questions unless something is genuinely missing and cannot be inferred.**

**Config reference**: [Configuration guide](https://www.skene.ai/resources/docs/skene/guides/configuration).

## Design principle

Make init invisible. Detect everything from existing config, env vars, and user-level config. Only ask the user if the agent truly cannot figure it out (e.g. API key missing everywhere).

## Steps

1. **Discover CLI options**
   Run `uvx skene config --help` to see what flags are available. Use only flags that appear in the output.

2. **Check what already exists** (run in parallel where possible):
   - `ls .skene.config 2>/dev/null` — project config
   - `ls ~/.config/skene/config 2>/dev/null` — user-level config
   - `echo n | uvx skene config --show` — full resolved config (piped to avoid blocking)
   - `printenv SKENE_API_KEY SKENE_PROVIDER 2>/dev/null` — env vars

3. **Decide what to do** (no user interaction needed):

   **Case A — Config exists and is valid** (provider set, API key present, provider/model match):
   Done. Report summary.

   **Case B — Config exists but has issues** (provider/model mismatch, missing API key, etc.):
   Fix what you can automatically:
   - Provider/model mismatch → update `.skene.config` with correct defaults.
   - API key missing from file but `SKENE_API_KEY` in env → fine, note it.
   - API key missing everywhere → ask user: "Set `SKENE_API_KEY` in your environment, then re-run `/skene-init`."

   **Case C — No config at all**:
   - Run `uvx skene config --init` (check --help first to confirm this flag exists).
   - If that fails with permission error, write `.skene.config` TOML directly.
   - Infer provider from env vars or default to `openai`.
   - Validate with `echo n | uvx skene config --show`.

4. **Final validation**
   ```
   echo n | uvx skene config --show
   ```
   Confirm provider, model, API key. If good, report.

5. **Report result**
   "Skene init complete. Provider: X, model: Y. Run `/skene-analyze` next."

## Terminal rules

The user CANNOT type into agent-spawned terminals. The agent handles ALL input.

- Always pipe `echo n` to `uvx skene config --show` to skip the edit prompt.
- NEVER run `uvx skene config` (no flags) — multi-step interactive. Write `.skene.config` directly.
- Stuck terminal: kill the process and re-run with piped input.
- Genuine blockers only: API key missing everywhere is the only thing that requires user action.

## Error handling

- **Permission error**: Write `.skene.config` manually. If `uvx` itself can't run, tell user to run `pip install uv` in their terminal.
- **API key missing everywhere**: Ask user to set `SKENE_API_KEY`.
- **Provider/model mismatch**: Fix automatically.

## Output

One line: "Skene init complete. Provider: X, model: Y. Run `/skene-analyze` next."

Versions

The database has no other skills named initialize-config.

Database snapshot: 13.11.2026 · package version bd30092db9d7 (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

  • 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".
  • 90deploy-telemetry
    Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
  • 100motion-plg
    Designs or audits a Product-Led Growth motion: checks PLG readiness, defines the First Value Moment, designs the activation funnel, runs the onboarding audit protocol, and specifies the PLG-to-SLG handoff. Use when building PLG from scratch, diagnosing why activation or…
  • 100bmad-init
    Initialize a BMAD planning workspace: pick a scale-adaptive TRACK (Quick Flow / BMad Method / Enterprise) interactively, then scaffold the output folder, a config file, an empty decision-log.md, and a project-context.md "constitution". Use when the user says "initialize BMAD",…
  • 90Project Scaffolding
    This skill should be used when the user wants to set up Claude for a project, create a CLAUDE.md file, scaffold the .claude directory, initialize an AI workflow, configure a project for Claude, set up dev intelligence, initialize a new project, or do a new project setup.…

Feedback and reports

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