SKILLEMALL.ai
GitHub ↗ RU Sign in

CC deep-research

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

asgeirtj/system_prompts_leaks Claude Code author: asgeirtj CC0-1.0 2 files · 1 script body ≈ 251 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting

AnalyzerData and analyticstype 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
C
80/100
safety, quality, tests
Safety 60%
95
Quality 40%
58
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation 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 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.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Obfuscation uni-mixed-script-word scripts/workflow-script.js:240
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    // true host: non-ASCII (an IDN homograph like Cyrillic "аmazon.com",

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 251 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Description length 116: 120–800 characters recommended
  • +4Structure: 0 headings, hard to scan
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Step-by-step instructions: 5 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.