BF Technical Documentation Engine
Complete technical documentation system — from planning through maintenance. Covers READMEs, API docs, guides, architecture docs, runbooks, and developer portals. Includes templates, quality scoring, and automation.
As a process F 33/100 · Will not run — References files that are not bundled: docs/getting-started.md, docs/api.md, docs/config.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7188 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: docs/getting-started.md - warning
missing-refreference to a missing file: docs/api.md - warning
missing-refreference to a missing file: docs/config.md - warning
missing-refreference to a missing file: docs/troubleshooting.md - warning
missing-refreference to a missing file: CONTRIBUTING.md - warning
missing-refreference to a missing file: LICENSE - warning
missing-refreference to a missing file: link - warning
missing-refreference to a missing file: ...
Process rating: all ten parameters 33/100
Will not run. References files that are not bundled: docs/getting-started.md, docs/api.md, docs/config.md
- 0Tools and files. 8 referenced file(s) missing: docs/getting-started.md, docs/api.md, docs/config.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (Technical Documentation Engine) differs from the folder (afrexai-technical-docs)
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 7188 tokens
- 100Steps. 23 steps
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 215: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (25 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.
External checks
ClawHub: clean
This is an instruction-only technical documentation skill whose project review and document generation behavior matches its stated purpose.
LLM: benign (high) · VirusTotal: benign · 28 May 2026