agentleFS
Sign inStart free
peopleforresterpeopleforrester/claude-dotfiles/skills/learning/instinct-status/SKILL.md

instinct-status

Skill3 starsChanged 7 months agoMITView on GitHub

View learned instincts grouped by domain with confidence levels

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read all instinct files from ~/.claude/instincts/:

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.

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

/instinct-status

Display all learned instincts with their confidence scores, grouped by domain.

Arguments

  • $ARGUMENTS — Optional filter: domain name or confidence threshold (e.g., "code-style" or ">0.5")

Process

1. Load Instincts

Read all instinct files from ~/.claude/instincts/:

~/.claude/instincts/
  prefer-const-assertions.md      (0.7, code-style)
  use-errgroup-for-goroutines.md   (0.5, concurrency)
  validate-inputs-with-zod.md      (0.9, security)

2. Display

## Learned Instincts

### code-style (3 instincts)
  [=======   ] 0.7  prefer-const-assertions
  [=====     ] 0.5  use-named-exports
  [===       ] 0.3  prefer-early-return

### security (2 instincts)
  [=========•] 0.9  validate-inputs-with-zod
  [=======   ] 0.7  check-auth-on-endpoints

### concurrency (1 instinct)
  [=====     ] 0.5  use-errgroup-for-goroutines

### Summary
Total: 6 instincts across 3 domains
Strong (≥0.7): 3 | Moderate (0.5-0.6): 2 | Tentative (<0.5): 1

3. Filters

  • /instinct-status code-style — Show only code-style domain
  • /instinct-status >0.7 — Show only strong instincts
  • /instinct-status inherited — Show only imported instincts

Confidence Legend

BarScoreLevel
[=== ]0.3Tentative — suggested, not enforced
[===== ]0.5Moderate — applied when relevant
[======= ]0.7Strong — auto-applied
[=========•]0.9Near-certain — core behavior

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.

Reviews can't be read right now.

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