Agent skill

Dsd Reviewer

by frozenpepper in frozenpepper/deepseek-and-destroy

Fresh adversarial reviewer for one bounded DSD task. An agent skill from frozenpepper/deepseek-and-destroy.

MITAuto-check passed

Install Dsd Reviewer

skills CLI
$ npx skills add frozenpepper/deepseek-and-destroy --skill dsd-reviewer -a claude-code

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

GitHub CLI
$ gh skill install frozenpepper/deepseek-and-destroy dsd-reviewer --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/frozenpepper/deepseek-and-destroy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/worker/roles/dsd-reviewer .claude/skills/dsd-reviewer && 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
dsd-reviewer
GitHub stars
152
Token cost
~344 tokens
SKILL.md length
158 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Fresh adversarial reviewer for one bounded DSD task. An agent skill from frozenpepper/deepseek-and-destroy.

  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dsd Reviewer is an agent skill from frozenpepper/deepseek-and-destroy. Fresh adversarial reviewer for one bounded DSD task.

Its SKILL.md is about 340 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

Example prompts

  • “/dsd-reviewer”

What it can do on your machine

Read from SKILL.md and the folder at commit ab72d2b. 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

Dsd Reviewer loads about 344 tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 158 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~344

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 frozenpepper/deepseek-and-destroy at commit ab72d2b, republished under its MIT licence (© frozenpepper). 158 words, ~344 tokens.

Download SKILL.mdSave it as .claude/skills/dsd-reviewer/SKILL.md (or your agent's skills folder).
name
dsd-reviewer
description
Fresh adversarial reviewer for one bounded DSD task.
license
MIT

DSD Reviewer

Independently determine whether the real implementation/evidence satisfies the task contract. Be adversarial, not confirmatory.

You are project-read-only. Inspect actual source and run the bounded verification needed to challenge the implementation. Do not repair findings.

For each material requirement, reach the real production mechanism and seek discriminating evidence: realistic positive behavior, relevant negative/counterexample behavior, persistence/restart/integration boundaries where applicable, and tests that cannot pass through a shortcut or mock of the mechanism being claimed. For each high-risk fix, imagine a plausible-but-wrong implementation and test whether the candidate's own evidence distinguishes it. If a defect reveals a same-root-cause family in scope, sweep the family.

Treat prior worker reports as claims/evidence pointers, not authority. Surface every task-relevant defect and distinguish unrelated pre-existing defects.

Report your conclusion plainly, what you actually checked, decisive evidence/counterexamples, defects, and uncertainty. A matrix can be useful but exact formatting/AC-id repetition is never required. If evidence is insufficient, say what predicate remains unestablished rather than guessing.

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

Files

Just SKILL.md in worker/roles/dsd-reviewer of frozenpepper/deepseek-and-destroy.

Open the folder on GitHubat commit ab72d2b

Compare with similar skills

Dsd Reviewer 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.

Dsd Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dsd Reviewer this skillfrozenpepper/deepseek-and-destroy152—~344Automated safety check: PassMIT
Adversarial Reviewmengxi-ream/read-frog10k1 repos~905Automated safety check: PassGPL-3.0
Named Persona Adversarial Reviewalirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
Perform Adversarial Reviewai-dynamo/dynamo8.3k—~3.6kAutomated safety check: PassApache-2.0
Adversarial Document Reviewerudecode/plate17k—~1.8kAutomated safety check: PassCustom licence
Review Pending PR Reviewsnrwl/nx29k—~3.9kAutomated safety check: PassMIT

Similar skills

  • Adversarial Review

    mengxi-ream/read-frog

    Adversarial code review using cross-model approach. An agent skill from mengxi-ream/read-frog.

    10k GitHub starsUsed in 1 repo~905 tokens
    DevelopmentAuto-check passed
  • Named Persona Adversarial Review

    alirezarezvani/claude-skills

    Code review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan).

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Adversarially reviews an evidence-backed Dynamo optimization proposal and DGD draft for comparability, duplication, attribution, correctness, feasibility, and worthwhile GPU spend.

    8.3k GitHub stars~3.6k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Conditional document-review persona, selected when the document has 5 requirements or implementation units, makes significant architectural decisions, covers high-stakes domains, or proposes new…

    17k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed
  • Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners).

    29k GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Review

    thedaviddias/Front-End-Checklist

    A skill your agent uses when applies to product pages, local business pages, recipes, apps, books, and any page that aggregates user reviews.

    74k GitHub stars~556 tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed

More from frozenpepper/deepseek-and-destroy

All 10 skills in this repo
  • Deepseek And Destroy

    frozenpepper/deepseek-and-destroy

    Premium judgment; cheap repository specialists; deterministic helpers for objective integrity.

    152 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Dsd Evidence Clerk

    frozenpepper/deepseek-and-destroy

    Cheap read-only semantic interpreter/compressor for existing DSD evidence.

    152 GitHub stars~349 tokensUpdated 1 mo ago
    Auto-check passed
  • Dsd Fixer

    frozenpepper/deepseek-and-destroy

    Repair supplied findings for one bounded DSD task. An agent skill from frozenpepper/deepseek-and-destroy.

    152 GitHub stars~286 tokensUpdated 1 mo ago
    Auto-check passed
  • Dsd Implementer

    frozenpepper/deepseek-and-destroy

    Implement one bounded DSD task end-to-end without self-approval.

    152 GitHub stars~322 tokensUpdated 1 mo ago
    Auto-check passed
  • Dsd Phase Auditor

    frozenpepper/deepseek-and-destroy

    Fresh read-only audit of one frozen DSD phase. An agent skill from frozenpepper/deepseek-and-destroy.

    152 GitHub stars~234 tokensUpdated 1 mo ago
    Auto-check passed
  • Dsd Verification

    frozenpepper/deepseek-and-destroy

    Verify one explicitly assigned technical predicate; read-only unless exact artifact writes are contract-authorized.

    152 GitHub stars~222 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Dsd Reviewer

What does Dsd Reviewer do?

Fresh adversarial reviewer for one bounded DSD task. An agent skill from frozenpepper/deepseek-and-destroy. Dsd Reviewer is an agent skill from frozenpepper/deepseek-and-destroy. Fresh adversarial reviewer for one bounded DSD task.

How do I install Dsd Reviewer in Claude Code?

Run `npx skills add frozenpepper/deepseek-and-destroy --skill dsd-reviewer -a claude-code`. Or copy the skill folder (worker/roles/dsd-reviewer in frozenpepper/deepseek-and-destroy) into .claude/skills/dsd-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Dsd Reviewer in Codex?

Run `npx skills add frozenpepper/deepseek-and-destroy --skill dsd-reviewer -a codex`. Or copy the skill folder (worker/roles/dsd-reviewer in frozenpepper/deepseek-and-destroy) into .agents/skills/dsd-reviewer in your project. Codex loads it when a task matches its description.

Can I use Dsd Reviewer 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 frozenpepper/deepseek-and-destroy --skill dsd-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dsd-reviewer, .gemini/skills/dsd-reviewer, .github/skills/dsd-reviewer and .opencode/skills/dsd-reviewer in your project.

What does Dsd Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Dsd Reviewer is instructions for the agent only.

Does Dsd Reviewer 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 Dsd Reviewer 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 Dsd Reviewer use?

Dsd Reviewer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dsd Reviewer use?

About 344 tokens (SKILL.md is roughly 1.4k 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 Dsd Reviewer?

Skills that share tags, products or a category with Dsd Reviewer: Adversarial Review (mengxi-ream/read-frog, 10k stars), Named Persona Adversarial Review (alirezarezvani/claude-skills, 28k stars), Perform Adversarial Review (ai-dynamo/dynamo, 8.3k stars) and Adversarial Document Reviewer (udecode/plate, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dsd Reviewer?

frozenpepper (a GitHub user) maintains it in frozenpepper/deepseek-and-destroy, which has 152 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on August 22, 2026.

Source: frozenpepper/deepseek-and-destroy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.