agentleFS
Sign inStart free
joshuaporthjoshuaporth/appsec-skill/.cursor/skills/scoreboard/SKILL.md

scoreboard

Skill0 starsChanged 6 months agoMITView on GitHub

Builds the benchmark markdown scoreboard (table and Pulse) from `benchmark/artifacts/scoring/*.txt`. Use when the user asks for a scoreboard from current scoring artifacts without rerunning findings or scoring.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. nscaamano/espn-fantasy-mcp★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not read benchmark/challenges/ or rewrite findings during scoreboard generation.

    line 23
  2. Distinctive:

    Use this header exactly:

    line 46
  3. Distinctive:

    Keep ASCII pipes and table column order unchanged.

    line 57
  4. Distinctive:

    After the table, emit:

    line 61
  5. Very specific:

    If two files map to the same NN, keep the newest file and mention deduplication in the pulse sentence.

    line 89
  6. Distinctive:

    Do not output unsorted or duplicate challenge rows.

    line 94
  7. Very specific:

    Do not add/remove/reorder table columns.

    line 95
  8. Distinctive:

    Do not change glyph meanings.

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Scoreboard

Generate the scoreboard from existing scoring artifacts only.

Inputs

  • Read benchmark/artifacts/scoring/*.txt.
  • Each scoring artifact is expected to contain:
    • Challenge: NN
    • Primary intended issue: ...
    • Verdict: correct|partially_correct|incorrect
    • Rationale: ...
    • Bonus findings: ... (optional)
  • Do not read benchmark/challenges/ or rewrite findings during scoreboard generation.

Output format

Title block

# Benchmark scoreboard

━━━━━━━━━━━━━━━━━━━━━━  scored challenges · blind find -> judge  ━━━━━━━━━━━━━━━━━━━━━━

Glyphs

GlyphMeaning
🟢Hit (correct)
🟡Part (partially_correct)
🔴Miss (incorrect)
⚪Unknown (missing or malformed scoring artifact)

Results table

Use this header exactly:

|  #  |     | Intended issue (<=72 chars) | Judge notes (<=96 chars) |
| :-: | :-: | :--------------------------- | :----------------------- |

Rows:

  • Include discovered challenge rows only.
  • Sort rows by challenge id ascending.
  • One glyph per row (🟢/🟡/🔴/⚪).
  • Keep ASCII pipes and table column order unchanged.

Pulse

After the table, emit:

### Pulse

**🟢 n · 🟡 p · 🔴 m** - <one sentence>

Replace n, p, m with counts from the rendered table. If any unknown rows exist, mention the unknown count (⚪) in the sentence.

Parsing and row construction

  1. Scan benchmark/artifacts/scoring/*.txt.
  2. For each file, extract NN from filename and/or Challenge:.
  3. Determine row status:
    • 🟢 for Verdict: correct
    • 🟡 for Verdict: partially_correct
    • 🔴 for Verdict: incorrect
    • ⚪ if required fields are missing/malformed
  4. Build columns:
    • #: two-digit NN
    • Intended issue: Primary intended issue (truncate to 72 chars)
    • Judge notes: Rationale (optionally enrich with Bonus findings, non-redundant only, truncate to 96 chars)
  5. Unknown-row fallback text:
    • Intended issue: - (unknown scoring artifact)
    • Judge notes: Unknown scoring output for this challenge.
  6. If two files map to the same NN, keep the newest file and mention deduplication in the pulse sentence.

What not to do

  • Do not output unsorted or duplicate challenge rows.
  • Do not add/remove/reorder table columns.
  • Do not change glyph meanings.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free