neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/feature-pipeline-preview/18-ci-cycle/02-fix-bot-comments
docs/archive/2026-07-ai-artifacts/claude-skills/feature-pipeline-preview/18-ci-cycle/02-fix-bot-comments/SKILL.md
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: 02-fix-bot-comments description: Reads CodeRabbit and other bot review comments, addresses them, and pushes fix-up commits. kind: leaf executor: sonnet model: claude-sonnet-4-6 --- # Fix Bot Comments Reads CodeRabbit / bot comments on the PR, addresses each, and p
$ install --global
skillsauthnpx skillsauth add neohaskell/neohaskell docs/archive/2026-07-ai-artifacts/claude-skills/feature-pipeline-preview/18-ci-cycle/02-fix-bot-commentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 8, 2026, 7:46 AM179.3s1 file scanned
SKILL.md
ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE. Superseded by
codemap/+ rootAGENTS.md. Scheduled for deletion once the pipeline is verified (Phase 6). Manifest:docs/archive/2026-07-ai-artifacts/MANIFEST.md
name: 02-fix-bot-comments description: Reads CodeRabbit and other bot review comments, addresses them, and pushes fix-up commits. kind: leaf executor: sonnet model: claude-sonnet-4-6
Fix Bot Comments
Reads CodeRabbit / bot comments on the PR, addresses each, and pushes fix-up commits.
Inputs
pipeline.py get pr_number→ PR number.
Plan
- Resolve the PR number → verify: integer captured.
- Fetch both bot-comment surfaces and union them — review-thread comments (
gh api repos/neohaskell/NeoHaskell/pulls/<N>/comments) AND general PR-timeline comments (gh api repos/neohaskell/NeoHaskell/issues/<N>/comments) → verify: both fetches return JSON arrays. - Address each bot comment with a code edit or a thread reply explaining false positive → verify: every bot comment has either a diff or a reply.
- Commit and push fix-ups → verify: branch updated.
Assumptions:
- Both PR comment surfaces are enumerated each cycle (review-thread
pulls/<N>/commentsand generalissues/<N>/comments) and merged into one bot list before filtering — a bot can post to either. - Max 5 cycles of bot-comment fixing. After the 5th cycle, escalate to the maintainer.
- False positives must be explained on the PR thread, never silently dismissed.
- Test files remain immutable unless a bot specifically flags a broken test in spec terms — in that case escalate.
If any assumption fails, refuse — do not guess.
Steps
NUM=$(python3 .claude/skills/feature-pipeline-preview/scripts/pipeline.py get pr_number).- Fetch review-thread comments:
gh api repos/neohaskell/NeoHaskell/pulls/$NUM/comments. - Fetch general PR-timeline comments:
gh api repos/neohaskell/NeoHaskell/issues/$NUM/comments. Merge the two arrays (dedup byid) before the next step — bots can post to either surface. - Filter the merged list to bot authors (CodeRabbit, etc.).
- For each comment, decide: real issue (fix with an edit) or false positive (reply on the thread explaining why).
- After all edits, run
nix develop --command cabal build allandnix develop --command cabal testto confirm nothing regressed. - Stage, commit with a
chore(review): address bot feedbackmessage, and push. - Increment the cycle counter via
pipeline.py iter 17. If > 5, refuse and escalate.
Output
Fix-up commit pushed; bot comments addressed; cycle counter advanced.
Refusals
- Cycle counter > 5 → refuse: "bot-comment cycle exhausted; escalate to maintainer".
ghnot on PATH → refuse: "gh not found".
Related Skills
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-style-guide
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-style-guide description: NeoHaskell coding style reference and enforcement rules. Load when writing, reviewing, or modifying any Haskell code in the NeoHaskell project. Triggers on 'NeoHaskell style', 'NeoHaskell conventions', 'how to write NeoHaskell', '
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-security-review
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-security-review description: Security & Code Quality review for NeoHaskell. Use when reviewing code changes, PRs, or architectural decisions for security implications. Evaluates OWASP, NIST, EU compliance. Handles pipeline phases 2 (ADR review) and 10 (im
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-qa-designer
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-qa-designer description: Testing QA Designer for NeoHaskell. Designs comprehensive test specifications with exhaustive edge cases, boundary conditions, and happy paths BEFORE implementation. Handles pipeline phase 6 (Test Spec Design). Outside-in TDD meth
347SKILL.mdUpdated Jul 9, 2026
neohaskell/docs/archive/2026-07-ai-artifacts/claude-skills/neohaskell-performance-review
development
VerifiedTrustedCommunity
> **ARCHIVAL KNOWLEDGE — DO NOT USE OR REFERENCE.** > Superseded by `codemap/` + root `AGENTS.md`. Scheduled for deletion once the pipeline is verified (Phase 6). > Manifest: `docs/archive/2026-07-ai-artifacts/MANIFEST.md` --- name: neohaskell-performance-review description: Performance review for NeoHaskell targeting 50k req/s throughput. Use when reviewing code for performance implications, INLINE pragmas, strictness, and allocation patterns. Handles pipeline phases 3 (ADR review) and 11 (imp
347SKILL.mdUpdated Jul 9, 2026