BF context-engineering-collection
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
As a process F 39/100 · Will not run — References files that are not bundled: skills/context-fundamentals/SKILL.md, skills/context-degradation/SKILL.md, skills/context-compression/SKILL.md
The same skill appears in 1 more place: ClawHub
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 2
-
high Obfuscation
uni-zero-widthdocs/agentskills.md:15Zero-width / invisible characters (possible hidden text) (32 occurrences)␀
Medium and low: 1
-
low Instruction override
en-ignore-previousdocs/gemini_research.md:8Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition; security demo / example)Advanced Architectures in Agentic AI: A Comprehensive Technical Analysis of Multi-Agent Systems, Context Dynamics, and Cognitive Orch…n1. Executive Synthesis: The Structural Transition to Agent
detectordemo
Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: skills/context-fundamentals/SKILL.md - warning
missing-refreference to a missing file: skills/context-degradation/SKILL.md - warning
missing-refreference to a missing file: skills/context-compression/SKILL.md - warning
missing-refreference to a missing file: skills/multi-agent-patterns/SKILL.md - warning
missing-refreference to a missing file: skills/memory-systems/SKILL.md - warning
missing-refreference to a missing file: skills/tool-design/SKILL.md - warning
missing-refreference to a missing file: skills/filesystem-context/SKILL.md - warning
missing-refreference to a missing file: skills/hosted-agents/SKILL.md - warning
missing-refreference to a missing file: skills/context-optimization/SKILL.md - warning
missing-refreference to a missing file: skills/evaluation/SKILL.md - warning
missing-refreference to a missing file: skills/project-development/SKILL.md
Process rating: all ten parameters 39/100
- 0Tools and files. 11 referenced file(s) missing: skills/context-fundamentals/SKILL.md, skills/context-degradation/SKILL.md, skills/context-compression/SKILL.md
- 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
- 40Consistency. Frontmatter name (context-engineering-collection) differs from the folder (agent-skills-context)
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 20 steps
- 100Execution cost. Instruction body is 1892 tokens
- 100Running it twice. Mutating operations check current state
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)
- +4No input/output examples
- -48 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 225: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.