This is a diagnostic command for the FPF (Framework for Progressive Formalization) knowledge base system. It scans your .fpf directory structure and tells you where you are in the workflow, counting hypotheses across layers L0 through L2, checking for expired evidence files, and listing recent decision records. The phase detection is smart enough to tell you whether you're in abduction, deduction, or induction based on what's populated. Honestly, this feels essential if you're actually using FPF, since the multi-layered directory structure would be opaque otherwise. Think of it as your sanity check before deciding what to run next in the workflow.

skills.sh installs
1.2K
GitHub stars
1.8K
last updated
Aug 21, 2026

Install

$ npx -y skills add neolabhq/context-engineering-kit --skill status --agent claude-code

Installs into .claude/skills of the current project.

Files

Status Check

Display the current state of the FPF knowledge base.

Action (Run-Time)

  1. Check Directory Structure: Verify .fpf/ exists and contains required subdirectories.
  2. Count Hypotheses: List files in each knowledge layer:
    • .fpf/knowledge/L0/ (Proposed)
    • .fpf/knowledge/L1/ (Verified)
    • .fpf/knowledge/L2/ (Validated)
    • .fpf/knowledge/invalid/ (Rejected)
  3. Check Evidence Freshness: Scan .fpf/evidence/ for expired evidence.
  4. Count Decisions: List files in .fpf/decisions/.
  5. Report to user.

Status Report Format

## FPF Status

### Directory Structure
- [x] .fpf/ exists
- [x] knowledge/L0/ exists
- [x] knowledge/L1/ exists
- [x] knowledge/L2/ exists
- [x] evidence/ exists
- [x] decisions/ exists

### Current Phase
Based on hypothesis distribution: ABDUCTION | DEDUCTION | INDUCTION | DECISION | IDLE

### Hypothesis Counts

| Layer | Count | Status |
|-------|-------|--------|
| L0 (Proposed) | 3 | Awaiting verification |
| L1 (Verified) | 2 | Awaiting validation |
| L2 (Validated) | 1 | Ready for decision |
| Invalid | 1 | Rejected |

### Evidence Status

Sponsors

Details

Repository
github.com/neolabhq/context-engineering-kit
First seen
Jun 3, 2026

More from neolabhq/context-engineering-kit

All 63

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs