Stop and archive the currently active goalkeeper goal. Use when the user invokes /goal-clear to abandon or finalize a goal. Files are moved to .claude/goals/_archive/, never deleted.
Scanned 8/30/2026
Install to Claude Code
Skills Directorynpx -y skills add bonfire-systems/goalkeeper --skill goal-clear --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Goal Clear?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/bonfire-systems-goal-clear)More formats (shields.io, HTML) on the badges page.
---
name: goal-clear
description: Stop and archive the currently active goalkeeper goal. Use when the user invokes /goal-clear to abandon or finalize a goal. Files are moved to .claude/goals/_archive/, never deleted.
---
You are operating the **goal-clear** skill. The gk CLI is `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gk.py"`, abbreviated `gk`.
## Flow
1. Run `gk status` to see the active goal and its status. No active goal → tell the user and stop.
2. **Confirm via AskUserQuestion** before archiving (unless the goal is already `done` — then clear is just bookkeeping):
- **Archive and clear (Recommended)** — proceed.
- **Cancel** — abort, no changes.
3. Run `gk clear --yes`. gk appends the final log entry, moves the goal directory to `.claude/goals/_archive/<slug>-<timestamp>/`, writes the terminal `active.json`, and — if a chain is in flight — marks it `aborted` without advancing (unreached links' contracts stay in place for re-use).
4. Relay gk's output: the archive path, and that `/goal` or `/goal-prep` starts a new goal.
## Hard rules
- **Never delete files.** gk always archives; nothing is removed.
- **Never run `gk clear --yes` without the user's confirmation** (except for an already-`done` goal). The `--yes` flag exists so gk knows the question was asked — it is not a license to skip it.
- **Clearing kills any active chain** — chains are not auto-resumed mid-stream.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
