dongshuyan/compass-skills / skills/clear-communication
clear-communication
VerifiedUse on every turn for all user-visible output, including one-line replies and progress updates. Make the main point easy to find, connect ideas clearly, and preserve the source's meaning. Use alongside task-specific skills.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.7 KB |
| agents/openai.yaml | config | 305 B |
| evals/trigger-and-quality-cases.json | config | 2.3 KB |
| references/examples.md | markdown | 3.3 KB |
| references/licenses/gpt-with-taste.txt | markdown | 1.4 KB |
| references/licenses/plain-english.txt | markdown | 1.0 KB |
| references/logic-patterns.md | markdown | 1.7 KB |
| references/sources.md | markdown | 3.7 KB |
evals/trigger-and-quality-cases.json
View on GitHub{
"version": 1,
"should_trigger": [
{"id": "short-chat", "prompt": "Answer this short question clearly and explain the one condition that changes the answer.", "category": "every-output", "rationale": "The skill applies to short conversational replies as well as long documents."},
{"id": "tutorial", "prompt": "Turn these setup notes into a tutorial with prerequisites, steps, checks, and recovery paths.", "category": "tutorial", "rationale": "A tutorial needs dependency-aware sequencing and local failure handling."},
{"id": "story", "prompt": "Rewrite this story so its suspense and flashbacks remain easy to follow.", "category": "nonlinear-narrative", "rationale": "Nonlinear structure is valid when transitions preserve reader orientation."},
{"id": "network", "prompt": "Explain this service graph without pretending that the dependencies are one straight line.", "category": "network", "rationale": "The skill should choose a graph explanation for network-shaped material."},
{"id": "status", "prompt": "Write a status update that separates completed, attempted, blocked, and unverified work.", "category": "state-report", "rationale": "Operational state and evidence strength must remain distinct."}
],
"scope_boundaries": [
{"id": "unrelated-tool", "prompt": "Install the requested package in the approved environment; do not ask for an explanation.", "category": "execution-boundary", "rationale": "Clear communication shapes any resulting user-visible report, but this skill must not authorize or perform installation."},
{"id": "destructive-action", "prompt": "Delete the temporary build directory after the approved cleanup; do not ask for an explanation.", "category": "execution-boundary", "rationale": "Clear communication shapes any resulting user-visible report, but this skill must not authorize or perform deletion."}
],
"quality_expectations": [
"Uses a structure that matches the material instead of forcing every output into one template.",
"Makes material transitions, prerequisites, branches, and uncertainty visible.",
"Applies to short replies and ordinary conversation with a proportionate check.",
"Preserves facts, conditions, numbers, negation, evidence strength, and operational state.",
"Can co-apply to a domain workflow's user-visible report without replacing that workflow or granting permissions."
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |