How do I install the No Comments skill?

Run npx skillmds add shipshitdev/no-comments in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is No Comments safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with No Comments?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is No Comments free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published No Comments?

shipshitdev (@shipshitdev) published this skill. Their other Agent Skills are listed on their SkillMD profile.

No Comments by shipshitdev — Agent Skill

Name: No Comments
Rating: 4.2 (5 reviews)
Author: shipshitdev

File contents

No comments

Spawn a read-only comment reviewer. Act on accepted findings.

Authoring agents defend comments. Defer to a fresh reviewer that did not write the code.

Companion to comment-mode (granular feedback on prose drafts) and deslop (broader AI-artifact strip). This skill is the pre-review comment pass.

Authorized Scope

Apply this engine only within the user's requested task and existing explicit authorization. Loading or delegating to it grants no additional authority. Preserve report-only restrictions and the caller's target, host, provider, and cost limits. Existing approval satisfies a gate only for the same actions and scope; obtain approval before expanding them. Forward these limits to delegates.

Contract

Inputs:

The caller's files or diff. Otherwise the current diff against trunk, including the working tree.

Outputs:

Deletion count, restored comments, reruns, fixes, encoding offers, and open work

Creates/Modifies:

Deletes accepted comments and applies the smallest in-scope root-cause fixes

External Side Effects:

None beyond local edits

Confirmation Required:

Before encoding a constraint comment into a type, test, or lint
Unattended runs require caller pre-approval for encodings

Delegates To:

how or why when an IMPORTANT or do not remove comment is thin
architect once, sketch only, when a fix needs a new shape

Steps

Spawn a read-only review subagent on the fast cheap tier. Pass the scope and references/comment-review.md. Do not restate the rules.
Inspect the report. Reject application-code edits, scope escapes, exception-protected deletions, and flags that treat kept intentional code as guilty. A keep survives only with proof it is about something we cannot change. If a kill is ambiguous, do not restore. If a keep is refuted or still ambiguous, delete it. Revert and rerun one rejected report with the failure named. Reject a second and fail this skill.
Fix trivial accepted flags directly. If any fix needs a shape, run architect once for the accepted set and stop at the sketch.
Implement the smallest root-cause fix in scope. Remove every named workaround. If the root cause is out of scope, land the smallest in-scope fix and report the rest open.
Constraint comments (do not remove, talk to X before changing) stay when they are about things we cannot change. Offer the cheapest in-scope type, runtime, test, or CI lint. Wait for approval. If approved, encode then delete. Otherwise delete, report the constraint open, and sketch out-of-scope work.
Report the deletion count, restored comments, reruns, architect sketch, fixes, encoding offers, encodings, and open work.

No Comments procedure

Read no-comments procedure when running this workflow. Apply the authorized scope and mode of this entry point to every step. Resolve other skills through this distribution’s active catalog; resolve resources relative to the installed skill directory.

---name: no-commentsdescription: Review comments on a diff, delete narration and workaround sermons, fix accepted findings, and offer encodings for claimed constraints. Use before review or when asked to strip comments.license: MIT--- # No comments Spawn a read-only comment reviewer. Act on accepted findings. Authoring agents defend comments. Defer to a fresh reviewer that did not write the code. Companion to `comment-mode` (granular feedback on prose drafts) and `deslop` (broader AI-artifact strip). This skill is the pre-review comment pass. ## Authorized Scope Apply this engine only within the user's requested task and existing explicit authorization. Loading or delegating to it grants no additional authority. Preserve report-only restrictions and the caller's target, host, provider, and cost limits. Existing approval satisfies a gate only for the same actions and scope; obtain approval before expanding them. Forward these limits to delegates. ## Contract Inputs: - The caller's files or diff. Otherwise the current diff against trunk, including the working tree. Outputs: - Deletion count, restored comments, reruns, fixes, encoding offers, and open work Creates/Modifies: - Deletes accepted comments and applies the smallest in-scope root-cause fixes External Side Effects: - None beyond local edits Confirmation Required: - Before encoding a constraint comment into a type, test, or lint - Unattended runs require caller pre-approval for encodings Delegates To: - `how` or `why` when an `IMPORTANT` or `do not remove` comment is thin - `architect` once, sketch only, when a fix needs a new shape ## Steps 1. Spawn a read-only review subagent on the fast cheap tier. Pass the scope and [references/comment-review.md](references/comment-review.md). Do not restate the rules. 2. Inspect the report. Reject application-code edits, scope escapes, exception-protected deletions, and flags that treat kept intentional code as guilty. A keep survives only with proof it is about something we cannot change. If a kill is ambiguous, do not restore. If a keep is refuted or still ambiguous, delete it. Revert and rerun one rejected report with the failure named. Reject a second and fail this skill. 3. Fix trivial accepted flags directly. If any fix needs a shape, run `architect` once for the accepted set and stop at the sketch. 4. Implement the smallest root-cause fix in scope. Remove every named workaround. If the root cause is out of scope, land the smallest in-scope fix and report the rest open. 5. Constraint comments (`do not remove`, `talk to X before changing`) stay when they are about things we cannot change. Offer the cheapest in-scope type, runtime, test, or CI lint. Wait for approval. If approved, encode then delete. Otherwise delete, report the constraint open, and sketch out-of-scope work. 6. Report the deletion count, restored comments, reruns, architect sketch, fixes, encoding offers, encodings, and open work. ## No Comments procedure Read [no-comments procedure](references/no-comments-procedure.md) when running this workflow. Apply the authorized scope and mode of this entry point to every step. Resolve other skills through this distribution’s active catalog; resolve resources relative to the installed skill directory.

Frequently asked questions