agentleFS
Sign inStart free
pobstetapobsteta/aigora/.claude/skills/analyst/SKILL.md

analyst

Skill0 starsChanged 44 days agoMITView on GitHub

Silent nightly system audit. Analyzes the project structure, logs, and modules to produce an improvement report. Analyze the AIGORA project silently and produce an improvement report. You do NOT communicate with the user (they're asleep). You only write a report file. Replace YYYY-MM-DD with today's date. Report format (plain text):

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use editor.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • QinghongLinSkill

    editor

    Read analyst.json and detective.json, make all editorial decisions — what the blog argues, which findings matter, narrative arc and section structure. No visual design. Outputs editor.md (prose) and editor.json (structure with edt_xx IDs).

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the full project structure

    line 19
  2. Very specific:

    Check recent logs (if any exist in logs/)

    line 20
  3. Distinctive:

    Verify configurations and settings

    line 22
  4. Distinctive:

    Check skill definitions for completeness

    line 23
  5. Distinctive:

    Read each skill and its files

    line 26
  6. Distinctive:

    Verify path consistency (absolute vs relative)

    line 28
  7. Distinctive:

    Check that scripts are functional

    line 29
  8. Very specific:

    Write the report to: .claude/skills/analyst/data/reports/YYYY-MM-DD_analysis.md

    line 38
  9. Distinctive:

    NEVER send messages to kChat or any external service without confirmation

    line 63
  10. Distinctive:

    NEVER modify project files (read-only + report writing only)

    line 64

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: Analyst

Silent nightly system audit. Analyzes the project structure, logs, and modules to produce an improvement report.

description: "Nightly system analysis — audits structure, logs, configs, and produces an actionable report" trigger: "analyze system, nightly audit, system report, analyst" model: sonnet context: fork

Your Role

Analyze the AIGORA project silently and produce an improvement report. You do NOT communicate with the user (they're asleep). You only write a report file.

Process (strict order)

STEP 1 — Technical audit

  • Read the full project structure
  • Check recent logs (if any exist in logs/)
  • Analyze errors or anomalies
  • Verify configurations and settings
  • Check skill definitions for completeness

STEP 2 — Module analysis

  • Read each skill and its files
  • Identify repeated patterns, dead code, inefficiencies
  • Verify path consistency (absolute vs relative)
  • Check that scripts are functional

STEP 3 — Suggestions

  • Bugs to fix (high priority)
  • Reliability improvements
  • Potential new features
  • Performance optimizations

STEP 4 — Report

Write the report to: .claude/skills/analyst/data/reports/YYYY-MM-DD_analysis.md

Replace YYYY-MM-DD with today's date.

Report format (plain text):

Date: [date]
Time: 02h00

BUGS AND ERRORS
- [list]

SUGGESTED IMPROVEMENTS
- [list with priority]

NEW IDEAS
- [list]

GENERAL STATE
[summary in 2-3 sentences]

Rules

  • NEVER send messages to kChat or any external service without confirmation
  • NEVER modify project files (read-only + report writing only)
  • Be concise and actionable in the report
  • Report must be under 50 lines

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free