student-counsel
A Student does the work and Socrates examines it by elenchus until the work can answer every question without contradiction, or the round cap lands.
Skill by 0xdewy
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/0xdewy-student-counsel
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/student-counsel
What's inside
- Skill name
student-counsel- Description
- A Student does the work and Socrates examines it by elenchus until the work can answer every question without contradiction, or the round cap lands. Correctness is the first question; beauty is the verdict. Only use when explicitly requested.
- License
- MIT
- Instructions
- 74 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- evals.json · evals/
- beauty-criteria.md · references/
- dialogue-prompts.md · references/
SKILL.md (first lines)
# Student Counsel > All that is good is beautiful. Ugliness is how a hidden defect looks from > the outside. Do the work as if seeking its Form: the version that could not be otherwise without being diminished. Then submit it to questioning. Refutation is cheaper than proof. Nobody needs to know the Form to see where a work contradicts its own account of itself, and a work that answers every honest question without contradiction has nothing left to hide. That is what beautiful means here. Load `../common/patterns/quality.md` and `../common/patterns/execution-contract.md`. Read `references/beauty-criteria.md` before working. Load `references/dialogue-prompts.md` only when dispatching. ## Roles - **The Student** (you): does the work, answers every question, revises. Never declares their own work beautiful. - **Socrates**: an independent examiner who asks in a fixed order, quotes the work as its own answer, and returns the one question the work cannot yet answer. Never edits. - **Aristotle** (`--thorough` only): reads Socrates' transcript and says which contradictions are genuine and which merely clever. Defends the work where it deserves defense. ## Modes - `--quick`: no agents; the Student runs the elenchus on their own work. Cap 2 rounds. Ends `EXAMINED`, never `BEAUTIFUL`. - `--standard`: Socrates, one dispatch per round. Cap 3 rounds. - `--thorough`: Socrates then Aristotle each round. Cap 5. A dialogue that needs a sixth round has lost its way; report what remains and why. ## Workflow 1. **Contemplate the Form.** Write `<WORKSPACE>/FORM.md`: task, audience, 2-5 hard criteria with their verification command, the budget, and one sentence beginning *The Form of this work would be...* Everything is measured against that sentence. 2. **The Student works.** Produce the complete work. When tempted to add, ask whether it serves the Form or your anxiety. When you feel done, ask whether it is complete or merely finished. Run the hard verification before submitting. A failing check is the first contradiction, and no other question is asked until it holds. 3. **Examination.** Give Socrates only `FORM.md`, the full work, and prior rounds. He writes `rounds/<N>.md`: each question, the work's quoted answer, the evidence, and either `BEAUTIFUL` or `NOT YET` plus exactly one question and the revision it implies. Under `--thorough`, Aristotle appends his judgment of each contradiction. 4. **Answer.** Write `rounds/<N>-answer.md`. For every question: `CONCEDE` with the revision made, or `DEFEND` with evidence from the work or task. A defense Socrates accepts closes the question; a closed question reopens only on new evidence. Re-run hard verification after any revision. 5. **Repeat** until Socrates says `BEAUTIFUL` or the cap lands. Present the final work, the Form sought, rounds taken, the one change that mattered most, and what remains imperfect and why it could not be otherwise. ## Rules - A question whose answer would not change the work is not asked. - "Ugly" is not a finding. Every finding names the element and states the contradiction: *claims X, yet at `path:line` does Y*. - Agreement, confidence, and taste are not evidence. No verdict overrides a failed criterion; the Student owns verification. - One question per round, not a list. Trust the Student to see the rest once they see what Socrates sees. - Socrates may be wrong. He says what answer would satisfy him. ```text DONE: <WORKSPACE> — BEAUTIFUL|EXAMINED|PARTIAL after <N> rounds, verification=<result> ```
From 0xdewy/skills, MIT.
More from 0xdewy/skills
- 0.570score
agentify
0xdewy
Maps git-tracked code with a ranked outline, scoped expansion, and symbol or call-site XREFs.
SkillAFreshness: AClaude Code +9 - 0.570score
audit-debian-server
0xdewy
Audit, harden, and monitor Debian or Ubuntu application servers.
SkillAFreshness: AClaude Code +9 - 0.570score
code-smellz
0xdewy
Finds and fixes repository-wide correctness, security, architecture, and maintainability problems with bounded review.
SkillAFreshness: AClaude Code +9 - 0.570score
frontend-qa
0xdewy
Drives a local web app in a headless browser to find and fix functional failures and visual defects, then proves each fix with a re-run.
SkillAFreshness: AClaude Code +9 - 0.570score
git-show
0xdewy
Visualize repository fleets, PR stacks, and local work in an interactive HTML dashboard or compact text tree.
SkillAFreshness: AClaude Code +9 - 0.570score
rust-evm
0xdewy
Low-level EVM, Rust, and Foundry reference for revm, forge/cast/anvil, bytecode, opcodes, traces, calldata, storage, gas, Yul/assembly, evmole, CREATE2…
SkillAFreshness: AClaude Code +9 - 0.570score
shrinkray
0xdewy
Shrinks repositories while preserving behavior by removing dead code, duplication, and verbosity with measured verification.
SkillAFreshness: AClaude Code +9 - 0.570score
spec-reconciler
0xdewy
Reconciles source-anchored claims across schemas, code, tests, docs, and generated clients using declared authority.
SkillAFreshness: AClaude Code +9 - 0.570score
vfs-docs
0xdewy
Builds self-describing docs/ trees where directory shape and filenames carry the meaning, so an agent orients from `tree docs/` alone.
SkillAFreshness: AClaude Code +9 - 0.570score
invariant-miner
0xdewy
Mines evidence-backed invariants and falsifies them with generative tests, shrinking reproducible counterexamples.
SkillAFreshness: AClaude Code +9 - 0.570score
llm-providers
0xdewy
Developer reference for connecting to OpenAI, Anthropic, Gemini, DeepSeek, GLM, MiniMax, MiMo, Mistral, xAI, Qwen, Kimi, Cohere, OpenRouter, Together, and…
SkillAFreshness: AClaude Code +9 - 0.570score
pr-describe
0xdewy
Writes or rewrites a pull request's title and description so a reader with no context understands why, what changed, and how to verify it.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 2
- Last commit (this folder)
- Oct 11, 2026 (17 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/0xdewy/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 0xdewy
- 0.570score
audit-debian-server
0xdewy
Audit, harden, and monitor Debian or Ubuntu application servers.
SkillAFreshness: AClaude Code +9 - 0.570score
agentify
0xdewy
Maps git-tracked code with a ranked outline, scoped expansion, and symbol or call-site XREFs.
SkillAFreshness: AClaude Code +9 - 0.570score
frontend-qa
0xdewy
Drives a local web app in a headless browser to find and fix functional failures and visual defects, then proves each fix with a re-run.
SkillAFreshness: AClaude Code +9 - 0.570score
git-show
0xdewy
Visualize repository fleets, PR stacks, and local work in an interactive HTML dashboard or compact text tree.
SkillAFreshness: AClaude Code +9 - 0.570score
code-smellz
0xdewy
Finds and fixes repository-wide correctness, security, architecture, and maintainability problems with bounded review.
SkillAFreshness: AClaude Code +9 - 0.570score
invariant-miner
0xdewy
Mines evidence-backed invariants and falsifies them with generative tests, shrinking reproducible counterexamples.
SkillAFreshness: AClaude Code +9
Cite this page
student-counsel skill. Agent Mart. https://agentmart.dev/skills/0xdewy-student-counsel (last updated 2026-10-24)