joenandez/spectre/spectre-feature-root

Claude Code and agent skill by joenandez/spectre

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Internal initializer for a missing Spectre feature root. Invoke only from a standalone workflow with no confirmed managed root. Do NOT invoke for existing roots, orchestrated calls missing a root, or direct user requests.

Install

npx vskill@latest install joenandez/spectre/spectre-feature-root

SKILL.md

feature-root

Purpose

Create a canonical root with no naming/reuse gate.

Inputs

Work/name hint; KIND=feature|bug (default feature); repo-relative candidate; write authority.

Working Set

Read exact candidates/ignore state only; never select existing work.

Outputs + DONE

Return FEATURE, repo-relative FEATURE_ROOT, warnings. DONE: valid root, neutral marker, tenancy, no phase artifact.

Method / guardrails

  1. Use an explicit caller candidate/descendant. Reject absolute, traversal, symlink-escaping, or unmanaged paths.
  2. Otherwise derive a concise kebab name and choose the first free .spectre/{features|bugs}/<name>[-N]/ per KIND. Never inspect or offer existing roots, ask whether to reuse one, present naming options, or wait for approval; suffixes resolve collisions.
  3. Create feature.json containing only schema_version, created_at, feature, and repo-relative feature_root; no lifecycle, alias, branch, or absolute path.
  4. Unless .spectre/ is ignored, preserve .spectre/.gitignore; require literal manifest.json, bin/, handoffs/, !features/, !bugs/, plus evidence/, checkpoints/, runs/, markers/, working_set.json, cleanup_summary.md, execution_state.md, reviews/task_review_attempt.json, reviews/task_review_safety.json under both features/**/ and bugs/**/. Specs/research/decisions/reviews/proof stay trackable. Never edit root .gitignore; warn on local-only matches.
  5. Write only root initialization.

Handoff

Return values/warnings; caller owns routing.

Escalate-If

Unsafe candidate/escape, marker/root conflict, or insufficient write authority. Naming ambiguity or collision never escalates.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
164
Repository forks
16
7-day trend score
31

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/joenandez/spectre/spectre-feature-root/badge)](https://verified-skill.com/skills/joenandez/spectre/spectre-feature-root)

Something wrong with this skill or its page? Tell us.