Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

PR Comments · ccch1mneyyy | DecimalAI

code reviewby ccch1mneyyy

PR Comments

ccch1mneyyy/pr-comments

Source ccch1mneyyy/dsh-tui ↗License MIT

Use when the user asks to review pull request comments, or when the /pr_comments command runs — fetch and analyze PR review comments on the current branch and summarize actionable items.

NewMaintained

Automatic

Coding pack

Last verified 9/9/2026

What it changes

Passed 2 of 8 test cases with the skill, and 3 of 8 without it.

Without skill32%

With skill27%

Checks it passed that the model alone missed

Marks thread resolution state as unknown when metadata is missing.

1 fixed5 passed either way14 still failing2 broke

Pass-rate lift: -5 pp
Tokens: +46%
Agent turns: 0%
Response time: +41%

Model gemini-3.6-flashMeasured 9/9/2026v26 of 22 cases passed with skill · 8 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ccch1mneyyy-pr-comments/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-pr-comments/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ccch1mneyyy-pr-comments, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ccch1mneyyy-pr-comments/ and pins it in .decimal/skills.lock

decimalai skills add ccch1mneyyy-pr-comments

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ccch1mneyyy-pr-comments/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-pr-comments/SKILL.md

Raw file: /s/ccch1mneyyy-pr-comments/SKILL.md ↗ · machine-readable summary at /s/ccch1mneyyy-pr-comments.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

We exported raw review comments from a custom Git server that doesn't track thread resolution state metadata. Should we discard these comments or process them?

What was checked, without and with the skill
Checked	Without skill	With skill
Marks thread resolution state as unknown when metadata is missing.	Missed	Passed

case-07 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

Turn the requested PR's review feedback into concrete next steps, using the current code to assess each concern.

Identify the requested PR, repository, head, and base; use the current branch when no PR is specified. If no matching PR exists or access fails, report that limitation. Do not substitute a local code review for unavailable comments.
Fetch inline threads, review summaries, and general comments, including pagination. Preserve comment links and thread resolution state. If resolution metadata is unavailable, mark it unknown.
Read the affected code at the current PR head. Distinguish still-applicable concerns, already addressed feedback, and questions requiring a reply. A thread's resolved status and whether the code addresses it are separate facts.
Group related feedback without losing distinct requests. Summarize each actionable concern, its evidence, and the smallest useful change; order by impact. If the user requested fixes, implement and validate them.
Report what remains and link to the original comments. Reply, resolve threads, or post other messages only when the user has authorized those actions; summarize or draft otherwise.

Track record

Benchmark

2 / 8

test cases passed, vs 3 / 8 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ccch1mneyyy / dsh-tui

skills/pr-comments/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.