SKILLEMALL.ai
GitHub ↗ RU Sign in

CF knowledge-base

How to work in a Knowledge Base project (the `knowledge-base` starter pack). Read when the project has the three-layer source-grounded layout — `external-sources/` → `research/` → `articles/` — or when asked how this project is organized. Carries the layer model, per-folder rules, status flows, and log discipline so this guidance does NOT live inside template bodies or log.md. The three procedures live elsewhere: ingest in the platform `open-knowledge` skill, research and consolidate as their own sibling skills in this pack. Complements the platform `open-knowledge` skill; does not replace it.

inkeep/open-knowledge Agent Skills author: inkeep GPL-3.0 2 files body ≈ 1 904 tokens Open the sourcegithub.com↗ analyzed 15 h ago

How to work in a Knowledge Base project (the knowledge-base starter pack).

As a process F 20/100 · Will not run — References files that are not bundled: path/to/doc.md, path/doc-a.md, path/doc-b.md

ReferenceWriting and documentstype 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
C
87/100
safety, quality, tests
Safety 60%
100
Quality 40%
68
Run on models
none yet
Process rating
F
20/100
Will not run
References files that are not bundled: path/to/doc.md, path/doc-a.md, path/doc-b.md
Tools and files w 18
0
Steps w 15
0
Result and completion w 14
0
the three weakest of ten parameters · all ten

How to improve

  1. 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: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: path/to/doc.md
  • warning missing-ref reference to a missing file: path/doc-a.md
  • warning missing-ref reference to a missing file: path/doc-b.md
  • warning missing-ref reference to a missing file: external-sources/source-slug.md
  • warning missing-ref reference to a missing file: references/ingest-and-sources.md
  • note frontmatter-key unknown frontmatter key "type"
  • note edit-residue the text marks something as outdated (lines 56, 58): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 20/100

Will not run. References files that are not bundled: path/to/doc.md, path/doc-a.md, path/doc-b.md
  • 0Tools and files. 5 referenced file(s) missing: path/to/doc.md, path/doc-a.md, path/doc-b.md
  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 10 mutating operations with no state check
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1904 tokens
  • 100Progress reporting. Reports progress

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)
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 600: enough signal without eating the budget
  • +4Structure: 9 headings
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.