New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Workflow Score To Target

by MengTo in MengTo/Skills

Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6…

MITAuto-check passedEducation

Install Workflow Score To Target

skills CLI
$ npx skills add MengTo/Skills --skill workflow-score-to-target -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MengTo/Skills workflow-score-to-target --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MengTo/Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills/workflow/workflow-score-to-target .claude/skills/workflow-score-to-target && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
workflow-score-to-target
GitHub stars
6.7k
Token cost
~1.3k tokens
SKILL.md length
794 words
Files
3
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6…

  • Works in 5 steps: Pin down the target and the items → Anchor the rubric before scoring → Score honestly from real evidence → …
  • The user asks to score
  • SKILL.md covers 1. Pin down the target and the…, 2. Anchor the rubric before…, 3. Score honestly from real… and 4. Improve in rounds, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Workflow Score To Target is an agent skill from MengTo/Skills. Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6 up to 6+"). Covers anchored rubrics, measurable criteria, independent or blind judging, before/after scorecards, and honest reporting of anything still short. Use whenever the user asks to score, rate, grade or judge something out of 10, names a target score, or asks "what would make this a 9?".

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `templates/critic-prompt.md` and `templates/scorecard.md`).

It sits in Education, covering Quizzes and assessments. The repository describes itself as: Agent skills for designers and builders using Codex, Claude, Cursor, and other AI coding agents. The licence is MIT.

When your agent uses it

  • The user asks to score
  • Judge something out of 10
  • Names a target score
  • Asks what would make this a 9?

Example prompts

  • “get it to 8 out of 10”
  • “bring everything under 6 up to 6+”
  • “what would make this a 9?”
  • “/workflow-score-to-target”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Pin down the target and the items
  2. Anchor the rubric before scoring
  3. Score honestly from real evidence
  4. Improve in rounds
  5. Lock it in

What it can do on your machine

Read from SKILL.md and the folder at commit 83a47fe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Workflow Score To Target loads about 1.3k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 794 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MengTo/Skills at commit 83a47fe, republished under its MIT licence (© MengTo). 794 words, ~1,296 tokens.

Download SKILL.mdSave it as .claude/skills/workflow-score-to-target/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
workflow-score-to-target
description
Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6 up to 6+"). Covers anchored rubrics, measurable criteria, independent or blind judging, before/after scorecards, and honest reporting of anything still short. Use whenever the user asks to score, rate, grade or judge something out of 10, names a target score, or asks "what would make this a 9?".

Workflow: score to a target

The user sets quality bars as numbers:

  • "score them out of 10. let's get them to 8 out of 10"
  • "anything less than 6 out of 10, get them to 6+"
  • "give it a score out of 10. get at least 8"
  • "make it 8 or 9 out of 10"

The job isn't just the score; it's reaching the bar, proving it, and saying plainly where it falls short.

1. Pin down the target and the items

  • Restate the bar: the target (6, 8 or 9), and whether it applies to every item or the average. "Get them to 8" means every item reaches 8.
  • List every item being scored: each skill, each weapon, each screen element, each object. Score them one by one, never as one blob.
  • Name the benchmark the user judges against, such as the games or sites they compare to. A 7 means nothing without one.
  • A bar the user sets once is a standing rule for that kind of work. Record it where future work will see it, such as project instructions, memory, or a test.

2. Anchor the rubric before scoring

Write the scale down so scores mean the same every round. Default anchors:

ScoreMeans
10Best-in-class, something you'd study
9Excellent: a trained eye finds almost nothing
8Polished and intentional, only minor nits
7Good, but a noticeable flaw
6Acceptable: works and reads clearly, with visible rough edges
5Mediocre: the idea is there, the execution distracts
3–4Clearly broken or wrong in places
1–2Barely works, or reads as something else

Then break each item into 3–5 criteria, 0–2 points each, so the total is out of 10 and every point has a reason. For example:

  • Animation: weight and timing, body mechanics, final pose, props, context and variety.
  • A skill or spell: its rules (a clear job of its own), the hover (shows where it lands and the numbers), the cast (its own pose, effect and sound), and what it leaves behind that you can see.
  • An object: silhouette at play distance, material and detail, fitting its setting, readability.

Wherever a criterion can be measured, measure it. Examples:

  • foot slide under 10% of travel speed;
  • weapon clipping in millimetres;
  • a 48% win rate over 40 seeds;
  • a download of 28 MB.

Numbers stop the score drifting with mood.

3. Score honestly from real evidence

  • Score from renders, recordings or measurements of the actual thing, never from the code or from memory. Capture the state first; see the workflow-progress-screenshots skill.
  • Score the baseline before changing anything. The before→after is the proof.
  • Judge independently when it matters. Hand the captures to a fresh subagent that didn't do the work. Give it the rubric and benchmark, but not your hopes or the previous scores. Use two blind judges per item if you can, and take the lower score or reconcile the difference.
  • Never round up to reach the bar. A 7.5 on an 8 bar is below the bar.
Show full SKILL.md (292 more words)Show less

4. Improve in rounds

  1. Fix the lowest items first, and the criterion costing the most points in each.
  2. Re-capture, and re-score only with the same rubric and judge setup.
  3. Send a picture per round (the start and the result), with the score moving: for example, "Hollow Keeper 3 → 6 → 8".
  4. Stop when every item meets the bar, or when an item plateaus because of something outside the task (a model limit, an art asset, a performance budget). Report that item as short, with the reason and what it would take.
  5. Keep guardrails while climbing: don't trade away performance budgets, tests or other items' scores to raise one number. Note any trade-off you made.

5. Lock it in

  • Where the bar can be checked by a machine, add a test so it can't quietly regress. Examples: weapons out of bodies in seven poses, a skill has its own pose and card, win rate at least 90%.
  • Save the scorecard in the project (for example qa/<area>/README.md), with the rubric, every item's before and after, the evidence, and the date. Future rounds start from it.

Report

Lead with the result: "All 49 now score 8 or better; 38 started below 8; the average rose from 6.7 to 8.1."

Then:

  • A table: item, before → after, and the main fault fixed (or the reason it's still short). See templates/scorecard.md.
  • How it was scored: the rubric, the benchmark, who judged (you, an independent subagent, or blind judges), and from what evidence.
  • Where it isn't perfect: items at or just over the bar with known nits, and anything still below.
  • The pictures: before and after per item, or per round.
  • Say that scores are judgements. Say which criteria were measured, and label captures honestly.

© MengTo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in agent-skills/workflow/workflow-score-to-target of MengTo/Skills.

  • SKILL.md
  • templates/critic-prompt.md
  • templates/scorecard.md

Open the folder on GitHubat commit 83a47fe

Compare with similar skills

Workflow Score To Target next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Workflow Score To Target compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Workflow Score To Target this skillMengTo/Skills6.7k—~1.3kAutomated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch66k—~2kAutomated safety check: PassMIT
Codebase to Coursezarazhangrui/codebase-to-course5.7k—~4.4kAutomated safety check: PassNone
AI Engineering Phase Quizrohitg00/ai-engineering-from-scratch66k—~2.1kAutomated safety check: PassMIT
Scholar EvaluationK-Dense-AI/claude-scientific-writer2.4k2 repos~2.9kAutomated safety check: NotesMIT

Similar skills

  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated 2 days ago
    EducationAuto-check passed

  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    66k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed

  • Codebase to Course

    zarazhangrui/codebase-to-course

    Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.

    5.7k GitHub stars~4.4k tokensUpdated 6 mo ago
    EducationAuto-check passed

  • AI Engineering Phase Quiz

    rohitg00/ai-engineering-from-scratch

    Quizzes you on a completed phase of the AI Engineering from Scratch course, taking a phase number or name and mapping it to that phase's directory.

    66k GitHub stars~2.1k tokensUpdated today
    EducationAuto-check passed

  • Scholar Evaluation

    K-Dense-AI/claude-scientific-writer

    Provide qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls.

    2.4k GitHub starsUsed in 2 repos~2.9k tokens
    EducationAuto-check: notes

  • Evaluation

    guanyang/open-agent-hub

    This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and…

    977 GitHub starsUsed in 2 repos~4.2k tokens
    EducationAuto-check passed

More from MengTo/Skills

All 39 skills in this repo

  • Illustration Bold Pop

    MengTo/Skills

    Draws hand-authored SVG spot illustrations in a bold pop-geometric style for design and coding scenes.

    6.7k GitHub stars~5.1k tokensUpdated 3 days ago
    Auto-check passed

  • Flat Vector Illustration Style

    MengTo/Skills

    Draws a slim, long-limbed character acting out one coding or design moment as an outline-free flat SVG card, in a fixed measured palette with confetti and no ground line.

    6.7k GitHub stars~4.9k tokensUpdated 3 days ago
    Auto-check passed

  • Flat Illustration With Black

    MengTo/Skills

    Draws flat vector spot illustrations of lanky people doing design and coding things, with solid black as a main fill, for empty states, onboarding and error pages.

    6.7k GitHub stars~5.2k tokensUpdated 3 days ago
    Auto-check passed

  • Grainy Gouache Illustration

    MengTo/Skills

    Draws cozy animal scenes as hand-authored 480x360 SVG cards in a grainy, risograph-like gouache style on hot pink, for empty states, headers and marketing cards.

    6.7k GitHub stars~5.2k tokensUpdated 3 days ago
    Auto-check passed

  • Illustration Halftone Line

    MengTo/Skills

    Draws hand-authored SVG spot illustrations in a halftone line style for design and coding scenes.

    6.7k GitHub stars~4.7k tokensUpdated 3 days ago
    Auto-check passed

  • Illustration Ink Sketch

    MengTo/Skills

    Draws hand-inked cartoon critters and living objects as SVG cards (480x360), each acting out a coding or design idea.

    6.7k GitHub stars~4.6k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Workflow Score To Target

What does Workflow Score To Target do?

Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6…. Workflow Score To Target is an agent skill from MengTo/Skills. Score work out of 10 against a clear rubric, then improve it round by round until every item reaches the target score the user named (for example "get it to 8 out of 10", "bring everything under 6 up to 6+").

When should I use Workflow Score To Target?

Workflow Score To Target fits situations like: the user asks to score; judge something out of 10; names a target score; asks what would make this a 9?.

How do I install Workflow Score To Target in Claude Code?

Run `npx skills add MengTo/Skills --skill workflow-score-to-target -a claude-code`. Or copy the skill folder (agent-skills/workflow/workflow-score-to-target in MengTo/Skills) into .claude/skills/workflow-score-to-target in your project. Claude Code loads it when a task matches its description.

How do I install Workflow Score To Target in Codex?

Run `npx skills add MengTo/Skills --skill workflow-score-to-target -a codex`. Or copy the skill folder (agent-skills/workflow/workflow-score-to-target in MengTo/Skills) into .agents/skills/workflow-score-to-target in your project. Codex loads it when a task matches its description.

Can I use Workflow Score To Target in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MengTo/Skills --skill workflow-score-to-target -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow-score-to-target, .gemini/skills/workflow-score-to-target, .github/skills/workflow-score-to-target and .opencode/skills/workflow-score-to-target in your project.

What does Workflow Score To Target need to run?

SKILL.md names no scripts, command-line tools or credentials: Workflow Score To Target is instructions for the agent only.

Does Workflow Score To Target access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Workflow Score To Target safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Workflow Score To Target use?

Workflow Score To Target is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Workflow Score To Target use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Workflow Score To Target?

Skills that share tags, products or a category with Workflow Score To Target: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 66k stars), Codebase to Course (zarazhangrui/codebase-to-course, 5.7k stars) and AI Engineering Phase Quiz (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow Score To Target?

MengTo (a GitHub user) maintains it in MengTo/Skills, which has 6,694 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 6, 2026.

Source: MengTo/Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.