BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
← Back to the Claude Observatory

compass-skills

Skill Development Usable
Works inClaude Code
Usable Scanned — metadata only

Long-running agent work loses user context, project context, goal alignment, and handoff state at every conversation boundary.

COMPASS Skills gives AI coding agents four local SKILL.md skills: task-clarifier (aligns goals, scope, and acceptance criteria before ambiguous or risky work), task-forest (repo-local task graph with goals, dependencies, and progress), session-handoff-prompt (compresses the current conversation into a paste-ready prompt for a new session), and user-profile-keeper (a local, correctable collaboration-preferences profile). Works with Claude Code and Codex.

696 starsMIT (commercial OK)FreeQuick setup
Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Long-running agent work loses user context, project context, goal alignment, and handoff state at every conversation boundary. COMPASS stores all four locally — a correctable user profile, a repo-local task graph, a continuation prompt, and a clarification gate before ambiguous or risky execution.

Engineering teams building or deploying AI agents that require consistent task execution and goal alignment.

Claude Code Claude Cowork Claude Chat

https://github.com/dongshuyan/compass-skills

By dongshuyan

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → PluginsAdd plugin. Search and click Install. Skills work in Claude Code only.
Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.
Command
npx skills add dongshuyan/compass-skills --skill '*' -a claude-code

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me clarify ambiguous or high-risk tasks into concrete decision criteria before the agent executes
CostFree

Trust Signals Auto-scanned

Stars696Contributors1Last updated2026-08-09LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-18 · scanner v1

Community Pulse New

No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 325 GitHub stars; contributors unknown; last commit 0d ago; license MIT.

Things to check

  • Alpha-status project (self-labeled). Skills are local files — keep references/, scripts/, and agents/ subdirectories intact when installing manually. Evaluated from public trust signals, not hands-on tested.
  • Single maintainer. Consider the risk if this person stops maintaining the project.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
3/5
Versatility
4/5
Reliability
3/5
Security
3/5
Overall score3.25 / 5.00 UsableEvaluatedJun 2026
Scored from trust signals (evidence-eval-v1): 325 GitHub stars; contributors unknown; last commit 0d ago; license MIT.

← Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation →