Search the FPF knowledge base and display hypothesis details with assurance information
Install
npx skills add https://github.com/neolabhq/context-engineering-kit --skill querySKILL.md
Query Knowledge
Search the FPF knowledge base and display hypothesis details with assurance information.
Action (Run-Time)
- Search
.fpf/knowledge/and.fpf/decisions/by user query. - 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
- 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 content
By Specific ID
Look up a specific hypothesis:
/fpf:query redis-caching
-> Shows full details for redis-caching
-> Displays dependency tree
-> Shows R_eff breakdown
By Layer
Filter by knowledge layer:
/fpf:query L2
-> Lists all L2 hypotheses with R_eff scores
By Decision
Search decision records:
/fpf:query DRR
-> Lists all Design Rationale Records
-> Shows what each DRR selected/rejected
R_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**: 0.85
Dependency 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 files
Query 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
researchmattpocock575KInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.paper-context-resolverlllllllama451KRigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing Renv-and-assets-bootstraplllllllama450KRigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.ai-research-explorelllllllama311KRigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow c