SKILLEMALL.ai
GitHub ↗ RU Sign in

CC benchmark-fp-fn-audit

Audit React Doctor against ReactBench or similar diagnostic benchmark corpora for confirmed false positives, false negatives, taxonomy gaps, and verifier artifacts. Use when analyzing rd.log, rd-before.json, rd-after.json, model.patch, result.json, reward/test logs, rule distributions, or when asked to perform a second adversarial pass over React Doctor benchmark findings.

millionco/react-doctor Agent Skills author: millionco NOASSERTION 3 files body ≈ 1 868 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Audit React Doctor against ReactBench or similar diagnostic benchmark corpora for confirmed false positives, false negatives, taxonomy gaps, and verifier…

As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmentData and analyticsWriting and documentstype 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
84/100
safety, quality, tests
Safety 60%
90
Quality 40%
76
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

    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 · 10

    ✓ No critical or high findings

    Medium and low: 10
    • low Secrets in code secret-high-entropy-token references/benchmark-artifacts.md:27
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - `fix-…mgx`: cheap `Map` ref initialization.
      quoted
    • low Secrets in code secret-high-entropy-token references/benchmark-artifacts.md:28
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - `writ…4p2`: cheap `Map` ref initialization.
      quoted
    • low Secrets in code secret-high-entropy-token references/benchmark-artifacts.md:29
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - `fix-…h7Z`: media error state reset keyed by source props.
      quoted
    • low Secrets in code secret-high-entropy-token references/benchmark-artifacts.md:30
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      - `writ…FwQ`: KaTeX HTML passed through a local alias.
      detector
    • low Secrets in code secret-high-entropy-token references/benchmark-artifacts.md:32
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      - `fix-…G4t`: controlled-selection focus handoff.
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:129
      High-entropy token-like string (may be an id, hash or a credential)
      fix-…mgx
    • low Secrets in code secret-high-entropy-token SKILL.md:130
      High-entropy token-like string (may be an id, hash or a credential)
      writ…4p2
    • low Secrets in code secret-high-entropy-token SKILL.md:131
      High-entropy token-like string (may be an id, hash or a credential)
      fix-…h7Z
    • low Secrets in code secret-high-entropy-token SKILL.md:132
      High-entropy token-like string (may be an id, hash or a credential)
      writ…FwQ
    • low Secrets in code secret-high-entropy-token SKILL.md:134
      High-entropy token-like string (may be an id, hash or a credential)
      fix-…G4t

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 60/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 34 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1868 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress

    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
    • -4Absolute local paths (C:\Users, /home/…): not portable
    • -41 reference files, but SKILL.md never points to them: the model will not open them
    • +1No license
    • +2Single-language instructions
    • +3Description length 375: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 34 items
    • +4Has examples (8 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.