ufawkes-knowledge
Skill2 starsChanged 25 days agoMITView on GitHub
Use when searching uFawkesAI institutional knowledge via qmd — agent orchestration, AI-SDLC pipeline, skill/registry conventions, DORA measurement — or when an answer should come from this repo's docs rather than its code.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- opencode/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- ai-stanceSkill
- context-engineeringSkill
- continuous-evalsSkill
- dev-experienceSkill
- discoverySkill
- documentationSkill
- langSkill
The file
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
- Very specific: line 19
Not indexed: root docs (AGENTS.md, README.md, …).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
uFawkesAI Knowledge (QMD)
Overview
This repo has a project-local QMD index (.qmd/). Run every qmd command from the repo root so the project index is picked up. Search for leads, then retrieve full documents before answering — never answer from snippets alone.
Collections
| Collection | Scope |
uFawkesAI-.agents | .agents/**/*.md — agents, skills, rules, workflows, registry |
uFawkesAI-docs | docs/**/*.md |
Not indexed: root docs (AGENTS.md, README.md, …). Symlinked harness mounts (.claude/skills, .opencode/skills) resolve into .agents/ and are already covered by uFawkesAI-.agents.
Query modes
| Mode | Time | Use for |
qmd search "..." -n 5 | <1s | Default. BM25 keyword search, no LLM |
qmd vsearch "..." -n 5 | ~15s | Semantic / paraphrased questions |
qmd query "..." --no-rerank -n 5 | ~80s | Hybrid last resort (CPU expansion is slow) |
Known issue: plain qmd query (rerank enabled) stalls indefinitely on this machine — always pass --no-rerank.
Typical loop
qmd search "cross-validation pairwise rules" -n 5 # leads: #docid + snippet
qmd get "#abc123" # full doc (line-numbered)
qmd multi-get "#abc123,#def456" --format md # batch fetch
qmd status # health + pending embeddingsAfter editing indexed docs
qmd update && qmd embed # re-embeds all collections; CPU full pass ≈ 8 min
# scope one collection: qmd embed -c uFawkesAI-docsDeep help: qmd skills get qmd --full.
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
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.

