Dx Roaster

What it does

When your agent uses it

• User says roast my repo
• Audit my README
• Developer experience review
• Score my GitHub project

Example prompts

• “roast my repo”
• “audit my README”
• “dx audit”
• “/dx-roaster”

Requirements

• A credential in GITHUB_TOKEN
• Compatibility (from SKILL.md): ["claude-code","gemini-cli","github-copilot"]

Workflow steps

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

1. 1Intake
2. 2Discover
3. 3Score 10 dimensions
4. 4Write the roast
5. 5Generate action plan
6. 6Generate ideal README
7. 7Terminal summary

What it can do on your machine

Read from SKILL.md and the folder at commit 62e437a. 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

  Shell commands in SKILL.md call:

  • gh
  • git

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GITHUB_TOKEN

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

• Compatibility

  ["claude-code","gemini-cli","github-copilot"]

  From compatibility in the SKILL.md frontmatter.

Context cost

Dx Roaster loads about 2.5k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 885 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~141

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.1k

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

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 Varnan-Tech/opendirectory at commit 62e437a, republished under its MIT licence (© Varnan-Tech). 885 words, ~2,530 tokens.

name

dx-roaster

description

Brutally honest developer-experience audit for a GitHub repo. Scores 10 DX dimensions (time-to-first-success, README clarity, visual proof, install, quick-start, docs, examples, community, trust, marketing), writes a shareable roast in the requested tone (brutal/honest/kind), produces a prioritized action plan ranked by impact × effort, and sketches an ideal README. Trigger when user says "roast my repo", "audit my README", "dx audit", "developer experience review", "score my GitHub project", "before launch checklist", or "make my repo shareable".

compatibility

["claude-code","gemini-cli","github-copilot"]

author

OpenDirectory

version

1.0.0

gh api repos/<owner>/<repo> --jq '{stars: .stargazers_count, forks: .forks_count, watchers: .subscribers_count, pushed_at, description, homepage, topics, default_branch}'
gh api repos/<owner>/<repo>/commits --jq '.[0].commit.author.date' | head -1
gh api repos/<owner>/<repo>/contributors --paginate --jq '[.[] | .login] | length'

"visual_proof": {
  "score": 4,
  "evidence": [
    "Found 1 screenshot at line 89 (below the fold)",
    "No animated demo / gif",
    "No video"
  ]
}

{
  "repo": "<owner/repo or local path>",
  "scanned_at": "<ISO 8601 timestamp>",
  "dimensions": {
    "time_to_first_success": { "score": 7, "evidence": ["..."] },
    "what_is_this_clarity": { "score": 5, "evidence": ["..."] },
    "visual_proof": { "score": 4, "evidence": ["..."] },
    "install_simplicity": { "score": 9, "evidence": ["..."] },
    "runnable_quick_start": { "score": 8, "evidence": ["..."] },
    "documentation_depth": { "score": 6, "evidence": ["..."] },
    "examples": { "score": 5, "evidence": ["..."] },
    "community_signals": { "score": 3, "evidence": ["..."] },
    "trust_signals": { "score": 7, "evidence": ["..."] },
    "marketing_signals": { "score": 4, "evidence": ["..."] }
  },
  "total": 58,
  "grade": "D",
  "tone": "honest"
}

# DX Roast: <repo name>

**Grade: <letter> (<total>/100)** · Tone: <tone>

<Paragraph 1: the verdict. What works + the big gap.>

<Paragraph 2: cite 2 specific findings with file references.>

<Paragraph 3: cite 2 more findings, tie to dimension scores.>

<Paragraph 4 (optional): a final twist or comparison to a known good repo.>

<Closing paragraph: point to `action-plan.md` for the path forward.>

### N. <Fix in imperative voice, one line>

**Why:** <One-sentence justification. Reference which dimension it improves.>

**Impact:** +<X> points · **Effort:** <5min / 30min / 2h / half-day>

**How:**

1. <Concrete step 1>
2. <Concrete step 2>
3. <Concrete step 3>

<Optional code/markdown snippet showing exact change>

# Action Plan — <repo name>

Current grade: <letter> (<total>/100)
Top fixes ranked by impact × effort. Do these in order.

---

DX Roast complete — Grade: <letter> (<total>/100)

Top 3 fixes (impact-ranked):
  1. <fix 1>                                +<X> pts  · <effort>
  2. <fix 2>                                +<X> pts  · <effort>
  3. <fix 3>                                +<X> pts  · <effort>

Files:
  → dx-roast/roast.md          (shareable verdict)
  → dx-roast/action-plan.md    (prioritized fixes)
  → dx-roast/ideal-readme.md   (target state)
  → dx-roast/score.json        (raw scores)

Benchmark: <other repo> scores <X>/100 (grade <Y>) — gap of <delta> points.

© Varnan-Tech, 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 4 other files (references) in skills/dx-roaster of Varnan-Tech/opendirectory.

• SKILL.md
• README.md
• references/readme-template.md
• references/roast-voice-guide.md
• references/scoring-rubric.md

Open the folder on GitHubat commit 62e437a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Varnan-Tech/opendirectory, which our catalogue first saw on October 7, 2026.

• majiayu000/claude-skill-registryskills/bash/dx-roaster