
Query
- 848 installs
- 1.3k repo stars
- Updated July 26, 2026
- neolabhq/context-engineering-kit
query is a knowledge retrieval skill that searches the local FPF knowledge base in .fpf/knowledge and .fpf/decisions to display hypothesis details, assurance levels, dependencies, and evidence summaries.
About
query is a neolabhq/context-engineering-kit skill for searching the FPF knowledge base at run time. It scans .fpf/knowledge and .fpf/decisions, then presents hypothesis title, layer (L0/L1/L2), kind, scope, audit R_eff for L1+, dependency graphs, and evidence summaries in table format. Developers reach for query when they need verified hypotheses, decision records, or assurance information while building or iterating on complex systems without manually grepping markdown knowledge files.
- Searches .fpf/knowledge/ and .fpf/decisions/ directories by natural language query
- Displays hypothesis layer (L0/L1/L2), kind, scope, R_eff assurance score, and weakest link
- Shows dependency graphs and evidence summaries when available
- Outputs results in clean markdown tables and structured hypothesis cards
- Helps maintain decision provenance across long-running agent projects
Query by the numbers
- 848 all-time installs (skills.sh)
- +46 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #553 of 3,301 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/neolabhq/context-engineering-kit --skill queryAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 848 |
|---|---|
| repo stars | ★ 1.3k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 26, 2026 |
| Repository | neolabhq/context-engineering-kit ↗ |
How do you query the FPF knowledge base?
Instantly retrieve verified hypotheses, decision records, and evidence from a local FPF knowledge base while building or iterating on complex systems.
Who is it for?
Developers maintaining an FPF knowledge base who need fast hypothesis and decision lookup during iteration.
Skip if: Projects without .fpf/knowledge or .fpf/decisions directories or teams not using FPF decision records.
When should I use this skill?
A developer asks to search FPF hypotheses, decision records, assurance data, or evidence in the local knowledge base.
What you get
Formatted tables of hypotheses with layer, assurance R_eff, dependency graphs, and evidence summaries.
- hypothesis result tables
- dependency and evidence summaries
By the numbers
- Indexes knowledge layers L0, L1, and L2
- Searches two directories: .fpf/knowledge and .fpf/decisions
Files
Query Knowledge
Search the FPF knowledge base and display hypothesis details with assurance information.
Action (Run-Time)
1. Search .fpf/knowledge/ and .fpf/decisions/ by user query. 2. For each found hypothesis, display:
- Basic info: title, layer (L0/L1/L2), kind, scope
- If layer >= L1: read audit section for R_eff
- If has dependencies: show dependency graph
- Evidence summary if exists
3. Present results in table format.
Search Locations
| Location | Contents |
|---|---|
.fpf/knowledge/L0/ | Proposed hypotheses |
.fpf/knowledge/L1/ | Verified hypotheses |
.fpf/knowledge/L2/ | Validated hypotheses |
.fpf/knowledge/invalid/ | Rejected hypotheses |
.fpf/decisions/ | Design Rationale Records |
.fpf/evidence/ | Evidence and audit files |
Output Format
## Search Results for "<query>"
### Hypotheses Found
| Hypothesis | Layer | Kind | R_eff |
|------------|-------|------|-------|
| redis-caching | L2 | system | 0.85 |
| cdn-edge | L2 | system | 0.72 |
### redis-caching (L2)
**Title**: Use Redis for Caching
**Kind**: system
**Scope**: High-load systems, Linux only
**R_eff**: 0.85
**Weakest Link**: internal test (0.85)
**Dependencies**:[redis-caching R:0.85] └── (no dependencies)
**Evidence**:
- ev-benchmark-redis-caching-2025-01-15 (internal, PASS)
### cdn-edge (L2)
**Title**: Use CDN Edge Cache
**Kind**: system
**Scope**: Static content delivery
**R_eff**: 0.72
**Weakest Link**: external docs (CL1 penalty)
**Evidence**:
- ev-research-cdn-2025-01-10 (external, PASS)Search Methods
By Keyword
Search file contents for matching text:
/fpf:query caching
-> Finds all hypotheses with "caching" in title or contentBy Specific ID
Look up a specific hypothesis:
/fpf:query redis-caching
-> Shows full details for redis-caching
-> Displays dependency tree
-> Shows R_eff breakdownBy Layer
Filter by knowledge layer:
/fpf:query L2
-> Lists all L2 hypotheses with R_eff scoresBy Decision
Search decision records:
/fpf:query DRR
-> Lists all Design Rationale Records
-> Shows what each DRR selected/rejectedR_eff Display
For L1+ hypotheses, read the audit section and display:
**R_eff Breakdown**:
- Self Score: 1.00
- Weakest Link: ev-research-redis (0.90)
- Dependency Penalty: none
- **Final R_eff**: 0.85Dependency Tree Display
If hypothesis has depends_on, show the tree:
[api-gateway R:0.80]
└──(CL:3)── [auth-module R:0.85]
└──(CL:2)── [rate-limiter R:0.90]Legend:
R:X.XX= R_eff scoreCL:N= Congruence Level (1-3)
Examples
Search by keyword:
User: /fpf:query caching
Results:
| Hypothesis | Layer | R_eff |
|------------|-------|-------|
| redis-caching | L2 | 0.85 |
| cdn-edge-cache | L2 | 0.72 |
| lru-cache | invalid | N/A |Query specific hypothesis:
User: /fpf:query redis-caching
# redis-caching (L2)
Title: Use Redis for Caching
Kind: system
Scope: High-load systems
R_eff: 0.85
Evidence: 2 filesQuery decisions:
User: /fpf:query DRR
# Design Rationale Records
| DRR | Date | Winner | Rejected |
|-----|------|--------|----------|
| DRR-2025-01-15-caching | 2025-01-15 | redis-caching | cdn-edge |Related skills
How it compares
Use query for structured FPF hypothesis lookup instead of unstructured repo-wide text search.
FAQ
Where does the query skill search?
query searches .fpf/knowledge and .fpf/decisions, including layered paths such as .fpf/knowledge/L0 for proposed hypotheses and deeper layers with audit metadata.
What metadata does query show for each hypothesis?
query returns title, layer, kind, scope, R_eff assurance for L1+, dependency graphs when present, and evidence summaries formatted as tables.
Is Query safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.