SKILLEMALL.ai
GitHub ↗ RU Sign in

BF git-repo-to-book

Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.

modbender/skill-library-mcp Agent Skills author: modbender MIT 12 files body ≈ 10 664 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Write a full-length technical book using multi-agent AI orchestration.

As a process F 51/100 · Will not run — References files that are not bundled: path, file.md, diagrams/chapter-NN/image-01.png

GeneratorObsidianGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
64
Run on models
none yet
Process rating
F
51/100
Will not run
References files that are not bundled: path, file.md, diagrams/chapter-NN/image-01.png
Tools and files w 18
0
When it triggers w 12
20
Result and completion w 14
40
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 10664 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: path
  • warning missing-ref reference to a missing file: file.md
  • warning missing-ref reference to a missing file: diagrams/chapter-NN/image-01.png
  • warning missing-ref reference to a missing file: diagrams/chapter-01/diagram-01-architecture.png
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: path, file.md, diagrams/chapter-NN/image-01.png
  • 0Tools and files. 4 referenced file(s) missing: path, file.md, diagrams/chapter-NN/image-01.png
  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 40Execution cost. Instruction body is 10664 tokens: crowds the task out of the window
  • 60Steps. 116 steps, 5 vague phrases
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 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

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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 316: enough signal without eating the budget
  • +4Structure: 50 headings
  • +3Step-by-step instructions: 116 items
  • +4Has examples (50 code blocks)
  • +3All 4 scripts are documented

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