SKILLEMALL.ai
GitHub ↗ RU Sign in

CD idea-spark

Generate ONE reviewer-defensible, implementable research idea with a concrete method and falsification plan from a stated research direction. Use when the user asks for a research idea, novelty analysis, bottleneck diagnosis, or paper-shape suggestion. Skip code review, debugging, and unconstrained brainstorming without research context.

microsoft/ResearchStudio Agent Skills author: microsoft 80 files · 4 scripts body ≈ 2 800 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Generate ONE reviewer-defensible, implementable research idea with a concrete method and falsification plan from a stated research direction.

As a process D 39/100 · Unfinished process — References files that are not bundled: references/design-notes.md

AnalyzerSoftware developmenttype 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
89/100
safety, quality, tests
Safety 60%
98
Quality 40%
75
Run on models
none yet
Process rating
D
39/100
Unfinished process
References files that are not bundled: references/design-notes.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Exfiltration read-dotenv references/setup.md:21
    Reads a .env file (quoted — discussed, not commanded)
    3. **Copy** the env template at the project root: `cp .env.template .env`.
    quoted
  • low Exfiltration read-dotenv references/setup.md:33
    Reads a .env file (detector / deny-list definition)
    6. **The orchestrator auto-loads `.env`** at runtime (walks up from skill dir to find `.env`), so you do NOT need to `source .env` in your shell. Shell-set env vars take precedence over `.env` values,
    detector

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/design-notes.md
  • note edit-residue the text marks something as outdated (lines 73): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 39/100

Will not run. References files that are not bundled: references/design-notes.md
  • 0Tools and files. 1 referenced file(s) missing: references/design-notes.md
  • 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
  • 30Running it twice. 7 mutating operations with no state check
  • 40Consistency. Frontmatter name (idea-spark) differs from the folder (idea_spark)
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 10 steps
  • 100Execution cost. Instruction body is 2800 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (7 tags): a typed call is more reliable

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)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -34 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 339: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 10 items
  • +4Reference files are cited in the instructions (4 of 11)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.