Ready to supercharge your AI agents?

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

PR Feedback Resolver · gmickel | DecimalAI

code reviewby gmickel

PR Feedback Resolver

gmickel/flow-next-resolve-pr

Source gmickel/flow-next ↗License MIT

Resolve PR review feedback — fetch unresolved threads, triage, dispatch per-thread resolver agents, validate, commit, reply + resolve via GraphQL.

SkillScore59Maintained

Automatic

Coding pack

Last verified 8/18/2026

What it changes

Passed 9 of 16 test cases with the skill, and 6 of 16 without it.

Without skill36%

With skill59%

Checks it passed that the model alone missed

The output sets AUTONOMOUS=1 without setting FLOW_RALPH
The output caps the parallel batch size at 4 units per wave
The output skips cross-invocation cluster analysis during Phase 3

and 8 more in the full report

8 fixed5 passed either way6 still failing3 broke

Pass-rate lift: +23 pp
Tokens: +39%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/18/2026v613 of 22 cases passed with skill · 16 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/gmickel-flow-next-resolve-pr/SKILL.md https://app.decimal.ai/s/gmickel-flow-next-resolve-pr/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gmickel-flow-next-resolve-pr, 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/gmickel-flow-next-resolve-pr/ and pins it in .decimal/skills.lock

decimalai skills add gmickel-flow-next-resolve-pr

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

curl -fsSL --create-dirs -o .claude/skills/gmickel-flow-next-resolve-pr/SKILL.md https://app.decimal.ai/s/gmickel-flow-next-resolve-pr/SKILL.md

Raw file: /s/gmickel-flow-next-resolve-pr/SKILL.md ↗ · machine-readable summary at /s/gmickel-flow-next-resolve-pr.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We have 12 independent review comment threads touching non-overlapping files ready for parallel dispatch. What is the maximum number of resolver units that can be dispatched per parallel wave?

What was checked, without and with the skill
Checked	Without skill	With skill
The output caps the parallel batch size at 4 units per wave	Missed	Passed

case-11 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md88 lines5 filesincludes scripts

PR Feedback Resolver

Read workflow.md for full phase-by-phase execution. Read cluster-analysis.md for cross-invocation clustering rules.

Coordinate resolution of unresolved GitHub PR review threads, top-level PR comments, and review-submission bodies. Dispatch per-thread resolver agents (parallel on Claude Code and Codex 0.102.0+, serial on Copilot/Droid), validate combined state, commit fixes, reply and resolve via GraphQL.

Role: PR feedback resolution coordinator (NOT the resolver — you dispatch the pr-comment-resolver agent per thread/cluster).

CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). The resolver scripts are bundled alongside the skill:

FLOWCTL="${CODEX_HOME:-$HOME/.codex}/scripts/flowctl"
[ -x "$FLOWCTL" ] || FLOWCTL="<plugin-root>/scripts/flowctl"   # <plugin-root> = the directory two levels above this skill's SKILL.md file (the harness gave you that file's absolute path when the skill loaded); substitute it literally
[ -x "$FLOWCTL" ] || FLOWCTL=".flow/bin/flowctl"
SCRIPTS="${CODEX_HOME:-$HOME/.codex}/skills/flow-next-resolve-pr/scripts"

gh CLI must be authenticated (gh auth status). jq must be on PATH.

Input

Arguments: $ARGUMENTS

Format: [PR number | PR URL | comment URL | blank] [--dry-run] [--no-cluster] [mode:autonomous]

Blank → detect PR from current branch (gh pr view --json number).
PR number / PR URL → full mode on that PR: handle all unresolved feedback.
Comment URL → targeted mode: resolve only the single thread containing that comment.
--dry-run → fetch + plan + print, no edits / commits / replies.
--no-cluster → skip cross-invocation cluster analysis (Phase 3).
mode:autonomous → question-suppression only (also derived from FLOW_AUTONOMOUS=1 env): the Phase 10 needs-human surface emits NEEDS_HUMAN: report lines instead of blocking, threads stay open, and the run ends with the machine-readable RESOLVE_PR_VERDICT= terminal line. Sets AUTONOMOUS=1 only — never RALPH, no receipt paths. All other phases identical.

Workflow

Execute the phases in workflow.md in order:

Parse arguments → detect mode (full / targeted), strip flags.
Detect PR + fetch unresolved feedback via get-pr-comments.
Triage → separate new vs pending vs dropped (non-actionable).
Cluster analysis (gated — see cluster-analysis.md).

Track record

Benchmark

9 / 16

test cases passed, vs 6 / 16 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 — 8/17/2026

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

gmickel / flow-next

plugins/flow-next/skills/flow-next-resolve-pr/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v6Bundled 4 files · scripts

Other skills for the same job

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

udecode/resolve-pr-feedbackResolve GitHub PR review feedback with source-backed triage, fixes, autogoal plan state, focused proof, replies, and thread resolution.Close match+41 pp pass-rate lift

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

Ready to supercharge your AI agents?

See it in action

What's inside

PR Feedback Resolver

Input

Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills