AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Raven Core

skill-giggsoinc-raven-raven-core · by giggsoinc

Use when writing code, adding imports, creating files, committing,

No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-giggsoinc-raven-raven-core

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-giggsoinc-raven-raven-core)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Raven Core? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Raven Core

Live Config

!cat .raven/manifest.json 2>/dev/null || echo "MANIFEST MISSING — run raven-setup.sh"

Step 0 — Prompt Analysis (fires on EVERY prompt before anything else)

Read the incoming prompt. Detect intent. Route accordingly.

| If prompt mentions... | Route to | Action | |---|---|---| | "find skill" / "search skill" / "what skill" | /raven-search {query} | Run skill search | | "expert" / "L99" / "deep dive" / "world class" | raven-expert | Activate L99 mode | | "security" / "threat model" / "vulnerability" / "CVE" | raven-security | Security review | | "plan" / "phases" / "architecture first" / "scaffold" | raven-plan + /raven-scaffold | Force plan before code | | "review" / "PR" / "code review" | raven-review | Manifest-aware review | | "refactor" / "clean up" / "too long" | raven-refactor | Style enforcement | | "test" / "write tests" / "coverage" | raven-test | Test-first | | "document" / "docstring" / "README" | raven-document | Doc enforcement | | "drama" / "debate" / "stress-test" / "panel" | andie Drama Mode | Expert panel | | JSX / React / npm / node_modules in prompt | WARN + block | "Raven: manifest forbids this framework" | | new import X in code | CVE check | cve-check.py --library X | | "commit" / "push" / "git add" | Pre-commit gate | All 5 checks fire | | "sync libraries" / "requirements changed" / "new dependency" | /raven-sync | Auto-sync requirements → manifest | | no specific match | passive mode | Style + stack rules apply |

Step 1 — Project context

!cat .raven/manifest.json 2>/dev/null | python3 -c "import json,sys; d=json.load(sys.stdin); print('Project:', d.get('project'), '| Mode:', d.get('mode','team'), '| Lang:', d.get('stack',{}).get('language'))" 2>/dev/null || true

Step 2 — Project-specific rules

!cat .raven/manifest.json 2>/dev/null | python3 -c " import json,sys d=json.load(sys.stdin) rules=d.get('project_rules',{}) ff=rules.get('forbidden_frameworks',[]) if ff: print('FORBIDDEN frameworks:', ', '.join(ff)) lic=rules.get('license','') if lic: print('License header required:', lic) cc=rules.get('commit_convention','') if cc: print('Commit convention:', cc) ag=rules.get('require_approval_gates',False) if ag: print('Approval gates: REQUIRED before any file write') " 2>/dev/null || true

Step 3 — Load rules on demand

  • Import/library → rules/stack.md
  • Style check → rules/style.md
  • Architecture → rules/architecture.md
  • Commit gate → rules/commit.md

Dynamic Skill Discovery

If a task needs a capability not in loaded skills:

  1. Say what skill would help
  2. Ask: "Want me to search for a {skill_type} skill?"
  3. If yes → python3 .claude/scripts/skill-search.py --query "{query}"
  4. Show results, ask approval, never install silently

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.