SKILLEMALL.ai
GitHub ↗ RU Sign in

DC context-engineering-collection

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.

Not recommendedcritical or high security findings · low grade D
muratcankoylan/Agent-Skills-for-Context-Engineering Agent Skills author: muratcankoylan MIT 80 files · 18 scripts body ≈ 2 715 tokens Open the sourcegithub.com↗ analyzed 6 d ago

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems.

As a process C 50/100 · Has gaps — References files that are not bundled: skills/context-fundamentals/SKILL.md, skills/context-degradation/SKILL.md, skills/context-compression/SKILL.md

AnalyzerAI and agentstype 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
D
69/100
safety, quality, tests
Safety 60%
71
Quality 40%
67
Run on models
none yet
Process rating
C
50/100
Has gaps
References files that are not bundled: skills/context-fundamentals/SKILL.md, skills/context-degradation/SKILL.md, skills/context-compression/SKILL.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

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.

Obfuscation
If you install

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.

For the author

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.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. 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.
  2. 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 · 8

  • high Obfuscation uni-zero-width docs/agentskills.md:15
    Zero-width / invisible characters (possible hidden text) (32 occurrences)
    ␀
Medium and low: 7
  • medium Dangerous commands cmd-autorun-instruction AGENTS.md:37
    Instructs the agent to auto-run a script on every session
    - Deterministic checks before model judges. Always run `validate_platform_compat.py --require-reference-validator` and `validate_repo.py --strict` before claiming a skill-format or packaging change is
  • low Instruction override en-ignore-previous docs/gemini_research.md:8
    Instruction-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
  • low Secrets in code secret-high-entropy-token examples/long-horizon-prompt-lab/package-lock.json:59
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…bKX+KS9G…yMA/NhKJ…RGz/Q==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/long-horizon-prompt-lab/package-lock.json:181
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha512-Kc+brLq…avx+hJjg…ERQ==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/long-horizon-prompt-lab/package-lock.json:344
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…GLw+xYSd…cqA==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/long-horizon-prompt-lab/package-lock.json:477
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…TIe+vXnW…DL0+idd5…ssn/eusA…vCn/9RBg==",
    detectorfixture
  • low Secrets in code secret-high-entropy-token examples/long-horizon-prompt-lab/package-lock.json:584
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; test fixture / example file)
    "integrity": "sha5…CpK+FtMRQVdIMN6/Df5j…tIC+7KYK…qaA==",
    detectorfixture

Files scanned: 77. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: skills/context-fundamentals/SKILL.md
  • warning missing-ref reference to a missing file: skills/context-degradation/SKILL.md
  • warning missing-ref reference to a missing file: skills/context-compression/SKILL.md
  • warning missing-ref reference to a missing file: skills/multi-agent-patterns/SKILL.md
  • warning missing-ref reference to a missing file: skills/long-horizon-prompting/SKILL.md
  • warning missing-ref reference to a missing file: skills/memory-systems/SKILL.md
  • warning missing-ref reference to a missing file: skills/tool-design/SKILL.md
  • warning missing-ref reference to a missing file: skills/filesystem-context/SKILL.md
  • warning missing-ref reference to a missing file: skills/hosted-agents/SKILL.md
  • warning missing-ref reference to a missing file: skills/context-optimization/SKILL.md
  • warning missing-ref reference to a missing file: skills/self-managed-context/SKILL.md
  • warning missing-ref reference to a missing file: skills/latent-briefing/SKILL.md
  • warning missing-ref reference to a missing file: skills/evaluation/SKILL.md
  • warning missing-ref reference to a missing file: skills/advanced-evaluation/SKILL.md
  • warning missing-ref reference to a missing file: skills/harness-engineering/SKILL.md
  • warning missing-ref reference to a missing file: skills/self-improvement-loops/SKILL.md
  • warning missing-ref reference to a missing file: skills/project-development/SKILL.md
  • warning missing-ref reference to a missing file: skills/bdi-mental-states/SKILL.md

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: skills/context-fundamentals/SKILL.md, skills/context-degradation/SKILL.md, skills/context-compression/SKILL.md
  • 0Tools and files. 18 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
  • 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-for-Context-Engineering)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 28 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Execution cost. Instruction body is 2715 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
  • -49 reference files, but SKILL.md never points to them: the model will not open them
  • +1No license
  • +2Single-language instructions
  • +3Description length 287: enough signal without eating the budget
  • +4Structure: 13 headings
  • +3Step-by-step instructions: 28 items
  • +3Output format is stated explicitly

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.