BF editing-cordis-compositions
Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and checking that an authored preset mounts.
A skill for editing Cordis compositions—agent presets and configurations. Promises to help create, modify, and validate setups, including choosing between host and preset placement. The package holds one instruction file at 1372 tokens, no scripts, no critical errors. Quality scored 81, but process score dropped to 28—no model runs, no sandbox execution, no actual validation tests. Zero findings, linter passes silently.
Works as a reference guide for Cordis inside DeepSeek-harness if you already know the framework. Without real model testing, it's unclear whether it automates anything or just documents the workflow. Install if you need a checklist; skip if you expect working validation.
Use when creating, changing, or validating an agent preset or other Cordis composition for this harness, including deciding host versus preset placement and…
As a process F 28/100 · No process to follow — weak spots: steps, result and completion, when it triggers
How to improve
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 64, 66): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 28/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1372 tokens
- high The skill tells the model to perform an irreversible action with no human approval
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 197: enough signal without eating the budget
- +4Structure: 8 headings
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.