SKILLEMALL.ai
GitHub ↗ RU Sign in

BC presubmit

Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 30-plus stages, including Red Team finders, Blue Team defence, verification cascade, legal pass, and copyedit, producing one consolidated report on disk. Verifies installation and API key, chooses the output location and smoke, standard, or custom mode, launches the run, and reports the result path. Use when the user asks to run presubmit, wants a deep unattended pre-submission audit, or needs a math or replication-code audit. Everyday self-audits go to paper-review-lite, and external refereeing to journal-review.

scdenney/open-science-skills Claude Code author: scdenney NOASSERTION 1 file body ≈ 2 956 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 30-plus stages, including Red Team finders, Blue…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions

IntegrationGitHubSoftware developmentAI and agentsData 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
B
90/100
safety, quality, tests
Safety 60%
94
Quality 40%
84
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
50
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 · 6

    ✓ No critical or high findings

    Medium and low: 6
    • low Risky intent intent-offensive-security SKILL.md:4
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      description: Launches and configures the standalone presubmit CLI, an API-driven adversarial peer-review pipeline with 30-plus stages, including Red Team finders, Blue Team defence, verification casca
    • low Dangerous commands cmd-shell-rc SKILL.md:58
      Writes to a shell startup file (documentation of a security skill)
      eval "$(grep -E '^export ANTHROPIC_API_KEY=' ~/.zshrc | head -1)" 2>/dev/null && [ -n "$ANTHROPIC_API_KEY" ] && case "$ANTHROPIC_API_KEY" in sk-ant-*) echo "found in .zshrc";; esac
      security skill
    • low Risky intent intent-offensive-security SKILL.md:102
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **Smoke** — `--stop-stage 2.0`. Metadata extraction + Red Team + numbers auditor. ~15–25 min on a 70-page paper, ~$1–2. Useful for verifying setup or catching show-stoppers fast.
    • low Risky intent intent-offensive-security SKILL.md:133
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - **`FATAL: Claude refused the request (likely safety policy)`** — a Red Team prompt tripped Claude's safety filters. The message does not name the stage; find the last `► Executing <stage>` line abov
    • low Risky intent intent-offensive-security SKILL.md:154
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      `<author_title_uuid>.txt` consolidates all stages into one file: header, disclaimer, overview, Editor's Note, Summary (Is It Credible? + Bottom Line), Potential Issues, Future Research, Copyediting, P
      quoted
    • low Risky intent intent-offensive-security SKILL.md:163
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      | Depth | 30+ stages: Red Team (Breaker, Butcher, Shredder, Collector, Void) + Blue Team defence + verification cascade + legal pass + copyedit + Writer Mode | ~11 sub-agents: content/argument, number

    Files scanned: 1. 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 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 21 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2956 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (5 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
    • +1No license
    • +2Single-language instructions
    • +3Description length 625: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 21 items
    • +4Has examples (8 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.