prism-status
Skill0 starsChanged 4 months agoMITView on GitHub
Reports PRISM GTR freshness/coverage by calling the `prism_status` MCP tool and formatting a detailed status report. Use when the user explicitly requests `prism_status` or asks to run PRISM status.
In this repository5 other files it gives its agents.
- agent-bridgeSkill
- awsSkill
- debate-shutdownSkill
- debateSkill
- swarmSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 1 is distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this skill only when the user explicitly asks for prism_status (or equivalent phrasing like “run prism status”).
- Very specific: line 14
Call the MCP tool prism_status.
- Very specific: line 15
Always pass root as the current workspace root path.
- Very specific: line 16
If the user provided a specific repository path, use that as root instead.
- Very specific: line 32
If symbolCount is 0: mention that symbol extraction appears empty.
- Very specific: line 33
If fileCount is 0 or missing: mention the index likely failed or pointed at the wrong root.
- Very specific: line 34
If builtAt is noticeably old relative to “now” (use judgment.
- Distinctive: line 38
Do not invent fields that aren’t present in the tool output.
- Very specific: line 39
If the tool call fails, report the failure and suggest re-running prism_refresh (or checking MCP server availability) before retrying …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
PRISM Status
When to use
Use this skill only when the user explicitly asks for prism_status (or equivalent phrasing like “run prism status”).
Workflow
- Call the MCP tool
prism_status.- Always pass
rootas the current workspace root path. - If the user provided a specific repository path, use that as
rootinstead.
- Always pass
- Render a detailed report from the tool output.
- Provide actionable next steps when appropriate (typically
prism_refresh).
Output template (detailed)
Return a response in this shape:
- PRISM version:
<metadata.prism_version>(if present) - Built at:
<data.builtAt> - Files indexed:
<data.fileCount> - Symbols indexed:
<data.symbolCount> - GTR hash:
<data.gtr_hash>
Then add an interpretation block:
- If
symbolCountis0: mention that symbol extraction appears empty; suggest runningprism_refresh, then re-runprism_status. - If
fileCountis0or missing: mention the index likely failed or pointed at the wrongroot; suggest verifyingrootand runningprism_refresh. - If
builtAtis noticeably old relative to “now” (use judgment; default threshold: ~24h): label as “possibly stale” and suggestprism_refresh.
Notes
- Do not invent fields that aren’t present in the tool output.
- If the tool call fails, report the failure and suggest re-running
prism_refresh(or checking MCP server availability) before retryingprism_status.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

