AF portable-context-os
Buildable Bring Your Own Context system for AI agents. Use for: creating user-owned or org-owned context vaults, scaffolding typed memory systems, generating MCP-native context layers, building portable bundle workflows, migrating context across runtimes, and auditing long-running agent memory systems.
As a process F 54/100 · Will not run — References files that are not bundled: templates/context_manifest.yaml, scripts/build_context_bundle.py, scripts/init_context_os.py
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/context_manifest.yaml - warning
missing-refreference to a missing file: scripts/build_context_bundle.py - warning
missing-refreference to a missing file: scripts/init_context_os.py
Process rating: all ten parameters 54/100
- 0Tools and files. 3 referenced file(s) missing: templates/context_manifest.yaml, scripts/build_context_bundle.py, scripts/init_context_os.py
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (portable-context-os) differs from the folder (hot-swap-context)
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 68 steps
- 100Execution cost. Instruction body is 2412 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 11 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)
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 303: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 68 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.