SKILLEMALL.ai
GitHub ↗ RU Sign in

BB nexus

Orchestrating multi-specialist task chains and scope-adaptive product delivery: classifies intent, selects and executes the minimum viable chain, aggregates results, and verifies acceptance criteria. For multi-domain tasks, build-first delivery, and product lifecycle execution.

simota/agent-skills Agent Skills author: simota 80 files body ≈ 6 109 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Orchestrating multi-specialist task chains and scope-adaptive product delivery: classifies intent, selects and executes the minimum viable chain, aggregates…

As a process B 70/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice

AnalyzerSoftware developmentData and analyticsAI and agentstype 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
B
83/100
safety, quality, tests
Safety 60%
96
Quality 40%
64
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 4

✓ No critical or high findings

Medium and low: 4
  • low Risky intent intent-offensive-security reference/agent-chains.md:259
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Red team assessment requested → Add Breach after Sentinel
  • low Risky intent intent-offensive-security reference/agent-disambiguation.md:109
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | "Penetration test", "DAST", "runtime vulnerability" | **Probe** | Dynamic testing against running app |
    table
  • low Risky intent intent-offensive-security reference/agent-disambiguation.md:110
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (documentation table row)
    | "Red team exercise", "attack scenario", "threat model" | **Breach** | Offensive security assessment |
    table
  • low Risky intent intent-offensive-security reference/agent-disambiguation.md:331
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    **Rule**: Static code scan → Sentinel. Running app penetration test → Probe.
    detector

Files scanned: 80. 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 ≈ 6109 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 70Execution cost. Instruction body is 6109 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 75 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 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)
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +3Description length 278: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 75 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (28 of 79)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.