no-comments
Kill needless comments plus the dead code they protect, fix root causes in scope, encode real constraints as structure.
Skill by TudeOrangBiasa
Chalk Labs
Need help deploying no-comments?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/tudeorangbiasa-no-comments
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/no-comments
What's inside
- Skill name
no-comments- Description
- Kill needless comments plus the dead code they protect, fix root causes in scope, encode real constraints as structure. Use before review or when comments outnumber reasons.
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (3)
- CREDITS.md
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# No comments Hunt needless comments and the dead code and workarounds they protect, fix the root cause in scope, and encode real constraints as structure. Comments that survive must prove they are about something unchangeable. Companion to `interrogate` (adversarial review of the change) and rule 24 (no phase-narrating comments): this one goes further, treating every comment as guilty until proven load-bearing. ## Scope The caller's files or diff; otherwise the current diff against the base branch, working tree included. ## Steps 1. Spawn one reviewer per available model with the same brief (scope plus this rubric), all in one round; single-model harnesses run two passes (find, then challenge). Models follow the repo model map. Never restate the rubric inside the brief; point at it. 2. Judge every finding skeptically before touching code. Reject application-code edits, scope escapes, exception-protected deletions, misstated kill reasons, and flags treating kept intentional code as guilty. A keep survives only with proof it is about something unchangeable (generated code, external contract, hardware limit); run `how` or `why` on thin keeps before believing them. Ambiguous kill means do not restore; refuted or still-ambiguous keep means delete. A rejected report gets one rerun with the failure named; reject twice and the skill fails open with the report. 3. Fix trivial accepted flags directly: delete the dead path, drop the parameter, use the real API. Fixes needing shape get one `codebase-design` sketch first; the sketch shapes, implementation follows. 4. Implement the smallest root-cause fix in scope (rule 2) and remove every named workaround. Root cause out of scope means landing the smallest in-scope fix and reporting the rest open. Never bolt on symptom guards, never widen the fence. 5. Constraint comments (`do not remove`, `do not change wording`, `talk to X`) become encodings, not keeps: offer the cheapest in-scope type, runtime check, test, or CI lint (rule 13), wait for approval, encode, then delete the comment. Unattended runs need caller pre-approval; without it, delete, report the constraint open, and sketch the out-of-scope work. 6. Report: deletion count, restored comments, reruns, sketch, fixes, encoding offers and landings, unenforced constraints, other open work.
From TudeOrangBiasa/skills-for-agents, MIT.
More from TudeOrangBiasa/skills-for-agents
- 0.592score
diagnose
TudeOrangBiasa
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
show-me-your-work
TudeOrangBiasa
Keep a reviewable decision trail for long or unattended work: TSV log per decision, end audit, cross-model attention flags.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
setup-pre-commit
TudeOrangBiasa
Set up fast hooks with the repo's own toolchain (oxlint/oxfmt, Biome, or Prettier), type checking, tests, and a token-size gate.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
arena
TudeOrangBiasa
Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
break
TudeOrangBiasa
Stress-test one component against worst-case content and states on a throwaway page, then report what visibly broke.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
interrogate
TudeOrangBiasa
Adversarial multi-model review with rubric and bucketed verdict.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
correct
TudeOrangBiasa
Eliminate repeated agent mistakes at the highest level that works: architecture, types, lint, tests, docs last.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
architect
TudeOrangBiasa
Settle types, signatures, and module shape before code: ground, sketch twice, agree, implement, scrap when wrong.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
how
TudeOrangBiasa
Explain how a subsystem works: triage complexity, fan out explorers on 2 to 4 angles for complex scopes, synthesize into fixed sections.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
prototype
TudeOrangBiasa
Build a throwaway prototype to answer a design question.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
codebase-design
TudeOrangBiasa
Shared vocabulary for designing deep modules.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
domain-modeling
TudeOrangBiasa
Build and sharpen a project's domain model.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 17, 2026 (13 days ago)
- Last release
- Oct 23, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TudeOrangBiasa
- 0.592score
diagnose
TudeOrangBiasa
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
show-me-your-work
TudeOrangBiasa
Keep a reviewable decision trail for long or unattended work: TSV log per decision, end audit, cross-model attention flags.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
arena
TudeOrangBiasa
Parallel design bakeoff: N candidates on one brief, cross-judge, pick a base, graft the best parts.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
break
TudeOrangBiasa
Stress-test one component against worst-case content and states on a throwaway page, then report what visibly broke.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
setup-pre-commit
TudeOrangBiasa
Set up fast hooks with the repo's own toolchain (oxlint/oxfmt, Biome, or Prettier), type checking, tests, and a token-size gate.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
interrogate
TudeOrangBiasa
Adversarial multi-model review with rubric and bucketed verdict.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get no-comments running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
no-comments skill. Agent Mart. https://agentmart.dev/skills/tudeorangbiasa-no-comments (last updated 2026-10-24)