SKILLEMALL.ai
GitHub ↗ RU Sign in

DC council

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

0xNyk/council-of-high-intelligence Agent Skills author: 0xNyk MIT 53 files · 6 scripts body ≈ 13 816 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

PersonaData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
77/100
safety, quality, tests
Safety 60%
87
Quality 40%
63
Run on models
none yet
Process rating
C
62/100
Has gaps
When it triggers w 12
20
Inputs and preconditions w 11
30
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • medium Dangerous commands cmd-autorun-instruction CLAUDE.md:29
    Instructs the agent to auto-run a script on every session
    - Always run `./scripts/council-simulation-checklist.sh` after changes
  • medium Dangerous commands cmd-autorun-instruction CLAUDE.md:30
    Instructs the agent to auto-run a script on every session
    - Always run `./install.sh --dry-run` to verify installation
  • low Dangerous commands cmd-pipe-to-shell configs/provider-model-slots.cursor.example.yaml:10
    Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment; test fixture / example file)
    #   1. Install: curl https://cursor.com/install -fsS | bash
    commentfixture
  • low Exfiltration net-credential-use configs/provider-model-slots.nim.example.yaml:11
    Credential used in a network call (verify the destination is the intended service) (code comment; test fixture / example file)
    #   3. Verify live model IDs: curl -H "Authorization: Bearer $NVIDIA_API_KEY" \
    commentfixture
  • low Dangerous commands cmd-pipe-to-shell SECURITY.md:20
    Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)
    - No `curl | bash` install path — users clone the repo and run `install.sh` locally.
    negated

Files scanned: 52. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 13816 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 62/100

  • 20When it triggers. No condition that starts the skill
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 10 mutating operations with no state check
  • 40Consistency. Frontmatter name (council) differs from the folder (council-of-high-intelligence)
  • 40Execution cost. Instruction body is 13816 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 85Steps. 110 steps, 2 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 4 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (7 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -34 of 5 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 135: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 110 items
  • +3Output format is stated explicitly
  • +4Has examples (26 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.