hummbl-io/agent-skills/ask-the-stack

Claude Code and agent skill by hummbl-io/agent-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Query the full knowledge stack (CLP + bibliography + bus + evidence docs) for research-grounded answers

Install

npx vskill@latest install hummbl-io/agent-skills/ask-the-stack

SKILL.md

The same SKILL.md was published earlier as hummbl-io/agent-skills/ask-the-stack.

[ask-the-stack]

Ask the full knowledge stack a question. Returns answers grounded in CLP ledger, bibliography, bus history, and evidence docs -- not model inference alone.

When to Use

  • Before writing a pitch or email: "what do we know about enterprise AI governance failures?"
  • Before a discovery call: "what does our research say about [company's] sector?"
  • When you need sourced claims, not hallucinated ones
  • After overnight ARCANA synthesis: "what did ARCANA conclude about [topic]?"

Execution

Phase 1 -- CLP Ledger Search
bash
python3 -m hummbl_governance.cognition search "$QUERY" --limit 10 --json 2>/dev/null | \
python3 -c "import json,sys; [print(f'[{r[\"source\"]}] {r[\"content\"][:120]}') for line in sys.stdin for r in [json.loads(line)]]" 2>/dev/null || \
python3 -m hummbl_governance.cognition search "$QUERY" --limit 10
Phase 2 -- Bibliography Search

Search ~/PROJECTS/hummbl-bibliography/ for entries matching query terms:

bash
grep -ri "$QUERY" ~/PROJECTS/hummbl-bibliography/ --include="*.json" --include="*.md" -l 2>/dev/null | head -5

If bibliography entries found, grep for title/tier/doi of matching entries.

Phase 3 -- Bus Milestone / SITREP Search
bash
grep -i "$QUERY" ~/.cache/bus/messages.tsv 2>/dev/null | \
grep -E "MILESTONE|SITREP|DISCOVERY" | tail -5 | \
awk -F'\t' '{printf "[%s] %s\n", substr($1,1,16), $5}'
Phase 4 -- Evidence Docs Search
bash
grep -ril "$QUERY" /work/active/hummbl-research/docs/evidence/ 2>/dev/null | head -5

For matched files, show first 3 lines of each.

Phase 5 -- Synthesis

Synthesize findings across all sources.

Output Format

[ask-the-stack] | "<query>"
======================================
## Answer
[2-4 sentence answer grounded in retrieved sources]
## Evidence
| Source | Type | Key Finding |
|--------|------|-------------|
| [ledger entry ID or bus ts] | CLP/Bus/Evidence | [excerpt] |
## Confidence
[HIGH/MEDIUM/LOW] -- based on source quality and coverage
## Gaps
[What the stack doesn't know about this question -- be honest]
## Next Action
[If gaps exist: suggest [daily-research] or [deep-research] on the gap]

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hummbl-io/agent-skills/ask-the-stack/badge)](https://verified-skill.com/skills/hummbl-io/agent-skills/ask-the-stack)

Something wrong with this skill or its page? Tell us.