agentsclimarketplace

Review & quality

19,016 rows, by stacks then stars

1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid

  • Auto review loop minimax

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/auto-review-loop-minimax Skill

    no license0★ repo

    Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".

    The same file is in 1 other repository

  • Auto review loop

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/auto-review-loop Skill

    no license0★ repo

    Autonomous multi-round research review loop. Repeatedly reviews using a secondary Codex agent, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

    The same file is in 1 other repository

  • Citation audit

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/citation-audit Skill

    no license0★ repo

    Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations (cite present but the cited paper does not establish the claim). Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.

  • Comm lit review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/comm-lit-review Skill

    no license0★ repo

    Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.

    The same file is in 1 other repository

  • Novelty check

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/novelty-check Skill

    no license0★ repo

    Verify research idea novelty against recent literature. Use when user says "\u67e5\u65b0", "novelty check", "\u6709\u6ca1\u6709\u4eba\u505a\u8fc7", "check novelty", or wants to verify a research idea is novel before implementing.

    The same file is in 1 other repository

  • Paper claim audit

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/paper-claim-audit Skill

    no license0★ repo

    Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

    The same file is in 1 other repository

  • Patent novelty check

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/patent-novelty-check Skill

    no license0★ repo

    Assess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.

    The same file is in 1 other repository

  • Patent review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/patent-review Skill

    no license0★ repo

    Get an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.

    The same file is in 1 other repository

  • Proof checker

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/proof-checker Skill

    no license0★ repo

    Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

    The same file is in 1 other repository

  • Research review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/research-review Skill

    no license0★ repo

    Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

    The same file is in 1 other repository

  • Training check

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/skills-codex/training-check Skill

    no license0★ repo

    Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

    The same file is in 1 other repository

  • Training check

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/wanshuiyin__Auto-claude-code-research-in-sleep/skills/training-check Skill

    no license0★ repo

    Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.

    The same file is in 2 other repositories

  • Research novelty review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-novelty-review Skill

    no license0★ repo

    Run a stringent, adversarial novelty review over a concrete research idea, method, protocol, artifact, or claimed finding. Use when asked to assess novelty, position a paper or project, build a prior-art matrix, decide whether something is incremental, or pressure-test whether the right move is to proceed, reframe, or abandon. Prefer `research-paper-review` for first-pass technical critique of a single paper artifact and `research-rebuttal` when the task is to answer concrete reviewer comments rather than establish novelty positioning from scratch.

  • Research paper review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-paper-review Skill

    no license0★ repo

    Run academic paper review with OCR extraction, multi-method CLI review, local visualization, and deep section-level critique workflows integrated into the research skill suite. Use when Codex needs an initial or first-pass review of one paper artifact or arXiv URL, including OCR, extraction, section-level critique, or viz JSON generation. Prefer `research-review-loop` once a tracked review state or revised artifact already exists, `research-novelty-review` for prior-art and positioning questions, `research-rebuttal` when concrete reviewer comments already exist, and `adversarial-doc-review` for non-paper documents.

  • Research rebuttal

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-rebuttal Skill

    no license0★ repo

    Draft venue-aware academic rebuttals and author responses from reviewer comments, scores, and paper artifacts. Use when concrete reviewer comments already exist and Codex needs to analyze reviews, build a reviewer issue board, plan evidence or manuscript fixes, draft a rebuttal, respond to AC or meta-review feedback, manage multi-round author-reviewer discussion, or prepare a paste-ready response for conference or journal review systems. Prefer `research-paper-review` for initial manuscript diagnosis before reviews arrive, `research-review-loop` for internal tracked review without external reviewer comments, and `research-novelty-review` for prior-art positioning disputes.

  • Research results auditor

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-results-auditor Skill

    no license0★ repo

    Audit ML/statistics experiment outputs for validity, confounds, statistical support, calibration, and mismatch between measured results and claimed conclusions. Use when asked to interpret results, sanity-check benchmarks, review ablations, assess robustness claims, or decide whether an experiment actually supports a paper or project claim.

  • Research review loop

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-review-loop Skill

    no license0★ repo

    Run iterative adversarial review over research plans, experiment outputs, and drafts with claim ledgers, issue tracking, evidence checks, and explicit closure criteria. Use when asked to red-team a research artifact across multiple rounds, maintain issue state across revisions, or pressure-test whether revised results and prose actually support a claim. Prefer `research-paper-review` for an initial single-paper critique or OCR/extraction workflow, and prefer `research-rebuttal` when concrete external reviewer comments already exist and the task is to draft a venue response.

  • Research systematic literature review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/yananlong__codex-skills/research/research-systematic-literature-review Skill

    no license0★ repo

    Full systematic literature review (PRISMA 2020 core) with discovery, screening, evidence extraction, synthesis, confidence grading, and adversarial stress-testing across papers. Prefer peer-reviewed published versions over preprints and use this skill either directly or as the coordinated literature stage inside a larger research workflow. Use when asked to run or audit a literature review, evidence synthesis, state-of-the-art survey with explicit methods, citation integrity checks, or confidence-rated conclusions from research publications.

  • Literature review

    kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/ymx10086__ResearchClaw/src/researchclaw/agents/skills/literature_review Skill

    no license0★ repo

    Generate a structured literature review outline from a topic and optional paper set. Use when the user wants a review plan or survey structure.

  • Grill me

    theomonfort/skills/skills/grill-me Skill

    no license0★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

  • Git conflict

    bluefeet/skills/git-conflict Skill

    no license0★ repo

    Helps resolve or recover from Git conflicts or interrupted operations, including merge, rebase, cherry-pick, revert, stash apply/pop, autostash, marker-only cleanup, or safe branch rebase/update previews. Does not apply to generic Git advice, ordinary commits, commit-message drafting, or history organization.

  • Skill review

    bluefeet/skills/skill-review Skill

    no license0★ repo

    Review an existing skill directory, SKILL.md file, or pasted skill text for skill-authoring quality. Use when the user asks to review, audit, critique, evaluate, improve, harden, or quality-check a skill's metadata, trigger behavior, progressive disclosure, instruction design, examples, bundled assets, dependencies, validation loops, or evaluation quality.

  • Code review

    MarchRory/liushi_agent_settings/packages/harness/src/.agents/skills/code-review Skill

    no license0★ repo

    Use when code, configuration, documentation, policies, or public interfaces changed and the result needs risk-focused review before delivery.

  • Lean startup validation

    walterkken/popular-process-skills/lean-startup-validation Skill

    no license0★ repo

    Run a Lean Startup validation loop with assumptions, MVP, build-measure-learn, validated learning, and pivot/persevere decisions. Use when Codex is asked to test a startup, product, feature, market, or business model under uncertainty.

  • Ss agile implementing an issue

    Emrebener/Sublime-Skills/skills/agile-ralph-loop/ss-agile-implementing-an-issue Skill

    no license0★ repo

    Use when dispatched as a subagent to implement a single GitHub issue on an already-checked-out feature branch. The coordinator (`ss-agile-advancing-milestones`) briefs you with the issue body and acceptance criteria; you implement, commit locally, and report back. Not for picking issues, opening PRs, or merging — that's the coordinator's job.

  • Ss agile polishing an issue

    Emrebener/Sublime-Skills/skills/agile-ralph-loop/ss-agile-polishing-an-issue Skill

    no license0★ repo

    Use when dispatched as a subagent to polish an implementer's work on a GitHub issue — improving naming, comments, structure, error messages, and removing dead code within the scope of the existing diff. Also does a lightweight acceptance-criteria sanity check and flags possibly-unmet items as info. Has NO veto power, NEVER blocks the merge, and "no changes" is a valid outcome.

  • Architecture review

    Emrebener/Sublime-Skills/skills/engineering/architecture-review Skill

    no license0★ repo

    A structured architecture-review process — finds shallow, leaky, tightly-coupled modules with the deletion test, proposes concrete deepening refactors, and grills the chosen design (with parallel exploration of alternative interfaces). Design-only; stops at an agreed design and does not implement it. Prefer this over reviewing code ad hoc whenever the user wants an architecture review, asks where or how to refactor or reorganize a codebase, says code feels tangled, hard to test, or hard to navigate, wants to consolidate tightly-coupled modules, or asks whether a module structure makes sense — even if they never say the word "architecture".

  • Ss sdd choosing feature branch

    Emrebener/Sublime-Skills/skills/spec-driven-development/ss-sdd-choosing-feature-branch Skill

    no license0★ repo

    Use after the plan is written (Stage 6) and before implementation (Stage 8). Auto-decides where the SDD planning commits land — silent when on `main` (creates and switches to the derived feature branch) or when already on the derived branch (build-on-top of a partial implementation). Falls back to an inline prompt only when the current branch is neither. Then batch-commits the planning artifacts in two thematic, path-scoped commits and persists the chosen branch into state for Stage 11 to merge.

  • Ss sdd preflight

    Emrebener/Sublime-Skills/skills/spec-driven-development/ss-sdd-preflight Skill

    no license0★ repo

    Use at the very start of a spec-driven-development pipeline run, before any spec drafting, planning, or implementation work begins. A permissive validation gate — confirms config is valid, the repo is a git repo, the user is on a named branch, warns (does not abort) on a dirty working tree, and creates the SDD state file shell once everything checks out.

  • Ss sdd receiving review findings

    Emrebener/Sublime-Skills/skills/spec-driven-development/ss-sdd-receiving-review-findings Skill

    no license0★ repo

    Use inline by the SDD coordinator when the spec-review subagent returns its findings (Stage 3). Guides how to evaluate findings, decide what to fix vs push back on, and avoid performative agreement.

  • Ss workflow restrict git commands

    Emrebener/Sublime-Skills/skills/workflow/ss-workflow-restrict-git-commands Skill

    no license0★ repo

    Establishes a policy that destructive git operations (push, reset --hard, clean -f, branch -D, checkout . / restore .) require explicit user authorization before execution. Use at session start to commit to the policy, or whenever about to run a git command. Tool-agnostic via instruction; a Claude Code `PreToolUse` hook script is bundled at $SUBLIME_SKILLS_HOME/skills/workflow/ss-workflow-restrict-git-commands/scripts/block-dangerous-git.sh as an optional drop-in for users who want deterministic harness-level enforcement.

  • Commit message gate

    iiwish/skillrun/examples/commit_message_gate Skill

    0★ repo

    Local-first Agent Skill Runtime for packaging SOPs, schemas, preflight checks, run records, and MCP tools as executable skill capsules.

  • Paper review

    dengzhe-hou/best-skills-research-writing/skills/review/paper-review Skill

    0★ repo

    Research review pipeline. Get critical feedback on research ideas from cross-model review. Use when user says 'review my idea', 'critique this', 'feedback on research'.

  • Full quality scan

    silvio-l/skills/skills/full-quality-scan Skill

    18 days old0★ repo

    Runs all configured linters and security scanners (cppcheck, ESLint, Semgrep, osv-scanner, dart analyze) repo-wide, then fixes every finding. Use for a repo-wide quality or security scan, e.g. "scan everything" or "fix all lint issues".

  • Screenshot review

    silvio-l/skills/skills/screenshot-review Skill

    18 days old0★ repo

    Uncompromising UI/UX audit of a folder of app screenshots: pulls app context from the repo, reviews each screen via a subagent against a 13-point rubric, writes actionable findings. Use when auditing screenshots, UI review, 'Screens prüfen'.

  • Source quality check

    stoicpickle/skillseeking/skills/source-quality-check Skill

    0★ repo

    Score source quality, credibility, reliability, and relevance for research tasks.

  • Source quality check

    stoicpickle/skillseeking/tests/fixtures/gauntlet-skills/source-quality-check Skill

    0★ repo

    Score source quality, credibility, reliability, and relevance for research tasks.

  • Quality assurance and observability validation

    meyverick/agy-skills/skills/quality-assurance-and-observability-validation Skill

    0★ repo

    Validates testing, logging, and observability standards. Use when writing tests, setting up logging systems, reviewing API schemas, or compiling system documentation.

  • Acuris eudi

    Acuris-GmbH/acuris-agent-context/claude-code-plugin/skills/acuris-eudi Skill

    0★ repo

    Acuris EUDI Wallet Verifier — a hosted OID4VP relying-party service at https://eudi.acuris-geo.com that accepts EU Digital Identity Wallet presentations (SD-JWT VC PID), validates the credential against EU 27 member-state trust lists (LOTL → TSL → x5c → CRL), and cross-checks the disclosed residence address against Acuris's address-validation pipeline. Use when the user is integrating EUDI Wallet verification into a bank KYC / branch onboarding flow, building a relying-party backend that initiates verification sessions and polls for results, generating OID4VP presentation_definitions, handling SD-JWT VC responses, or interpreting verification_status, accuracy_type, and credential_validity in poll responses.

  • Acuris eudi

    Acuris-GmbH/acuris-agent-context/skills/acuris-eudi Skill

    0★ repo

    Acuris EUDI Wallet Verifier — a hosted OID4VP relying-party service at https://eudi.acuris-geo.com that accepts EU Digital Identity Wallet presentations (SD-JWT VC PID), validates the credential against EU 27 member-state trust lists (LOTL → TSL → x5c → CRL), and cross-checks the disclosed residence address against Acuris's address-validation pipeline. Use when the user is integrating EUDI Wallet verification into a bank KYC / branch onboarding flow, building a relying-party backend that initiates verification sessions and polls for results, generating OID4VP presentation_definitions, handling SD-JWT VC responses, or interpreting verification_status, accuracy_type, and credential_validity in poll responses.

  • Skill eudi

    Acuris-GmbH/acuris-agent-context/src/skill-eudi Skill

    0★ repo

    Acuris EUDI Wallet Verifier — a hosted OID4VP relying-party service at https://eudi.acuris-geo.com that accepts EU Digital Identity Wallet presentations (SD-JWT VC PID), validates the credential against EU 27 member-state trust lists (LOTL → TSL → x5c → CRL), and cross-checks the disclosed residence address against Acuris's address-validation pipeline. Use when the user is integrating EUDI Wallet verification into a bank KYC / branch onboarding flow, building a relying-party backend that initiates verification sessions and polls for results, generating OID4VP presentation_definitions, handling SD-JWT VC responses, or interpreting verification_status, accuracy_type, and credential_validity in poll responses.

  • Python rust package methods check

    maxwellkonnaris/agents_skills/.agents/skills/python-rust-package-methods-check Skill

    0★ repo

    Review Python packages, Rust crates, and mixed scientific software for correctness, numerical robustness, APIs, tests, performance, and docs.

  • R package methods check

    maxwellkonnaris/agents_skills/.agents/skills/r-package-methods-check Skill

    0★ repo

    Review R package method changes for statistical correctness, numerical robustness, API stability, tests, and docs.

  • Duplicate bug checker

    vikenpatel14/cursor-qa-skills/duplicate-bug-checker Skill

    no license0★ repo

    Search JIRA for duplicate bugs and stories before filing a new issue. Searches across all projects, not just EXAMPLE-PROJ. Use when the user describes a bug they found, asks if a bug already exists, mentions duplicate check, or wants to check before filing a bug.

  • Openspec verify change

    knvpk/Agentic/.claude/skills/openspec-verify-change Skill

    no license0★ repo

    Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

  • Backend scaffold

    knvpk/Agentic/skills/backend-scaffold Skill

    no license0★ repo

    Bootstrap files every new backend project needs — flake.nix dev shell, Taskfile environment loading, pre-commit linters, ruff config for Python, and OpenAPI spec init. Use when starting a new backend service or repo from scratch, or when any of these foundational files are missing.

  • Project management

    knvpk/Agentic/skills/project-management Skill

    no license0★ repo

    Provider-agnostic project management skill. Manages local project docs (docs/prd.md, docs/architecture.md, docs/database.md, docs/tools.md) and connects to any supported issue tracker (GitHub, GitLab, Jira, Plane) via MCP. Ten modes: init (configure provider, probe plan capabilities), docs (scaffold and edit project docs; suggests docker-modular-stack for Docker dependencies), bulk (generate a full backlog from docs/ — reads all docs files, produces typed dependency-ordered ticket manifest, deduplicates against existing tickets, human review then creates in one pass), ticket (create rich opsx-ready ticket briefs with requirements, BDD scenarios, use cases; CRUD; all relationship types; canonical lifecycle; intelligent scope-width detection proposes breakdown into multiple tickets when input covers broad scope), sprint (manage sprints/milestones/cycles and labels; agile ceremonies: plan, review, retro, close), next (algorithmic daily ticket recommendation from dependency graph and priority), start (fetch a specific ticket by ID, enrich with project doc context, transition state with WIP limit check, create branch, invoke opsx:explore), status (sprint board with health signal and burndown grouped by canonical state), standup (daily standup: what I did / what's next / blockers), backlog (refine unestimated tickets with DoR check and story-point prompts). Quality gates: Definition of Done enforcement on ticket close, WIP limit enforcement on in-progress transitions. Context for tickets is relevance-filtered from docs and falls back to local repo files or configured sibling repos.

  • Review pr

    rfl-designer/rfl-laravel-skills/skills/laravel/review-pr Skill

    no license0★ repo

    Review the current branch's pull request in a single consolidated pass without spawning review sub-agents. Checks Laravel idioms, Livewire/Flux/a11y, Pest test quality, and spec compliance against originating issue acceptance criteria. Use before merging, when user says "review the PR", "review my changes", "/review-pr [number]", or after /simplify.

  • Grill with docs

    rfl-designer/rfl-laravel-skills/skills/process/grill-with-docs Skill

    no license0★ repo

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

  • Open pr

    rfl-designer/rfl-laravel-skills/skills/process/open-pr Skill

    no license0★ repo

    Open a GitHub pull request for the current branch with title derived from Conventional Commits, body referencing closed issues, and gated by Pest + Pint. Use when the user finishes a slice and wants to open a PR, says "abrir PR", "open pr", or "ship this".

  • Sql query review

    openagentskills/betterskills/skills/data/sql-query-review Skill

    0★ repo

    Reviews and improves SQL queries for readability and performance using a structured checklist. Use when users ask to optimize a query, review query performance, explain a slow query, or interpret an execution plan.

  • Code review

    openagentskills/betterskills/skills/engineering/code-review Skill

    0★ repo

    Reviews code changes for correctness, security, maintainability, and test coverage using a severity-tagged checklist. Use when reviewing pull requests, diffs, patches, or when the user asks for a code review.

  • Conventional commits

    openagentskills/betterskills/skills/engineering/conventional-commits Skill

    0★ repo

    Drafts Conventional Commits messages from staged or unstaged diffs. Use when the user asks for a commit message, conventional commit, or help summarizing git changes before commit.

  • Pull request description

    openagentskills/betterskills/skills/engineering/pull-request-description Skill

    0★ repo

    Generates clear, structured pull request descriptions from branch diffs or commit lists. Creates summaries, change logs, test plans, breaking change notes, and related issue references. Use when the user asks for a PR description, needs to summarize changes for reviewers, or wants a test plan section for their PR. Turns a branch diff or commit list into a clear pull request description with summary, motivation, test plan, and breaking changes. Use when the user says "write a PR description", "summarize this diff for reviewers", or "generate a PR body".

  • Security review

    openagentskills/betterskills/skills/engineering/security-review Skill

    0★ repo

    Performs a lightweight security review using OWASP-oriented checks for auth, input validation, secrets, and dependencies. Use for security review, threat check, or before merging sensitive changes.

  • Drive pr

    0xdeafcafe/skills/skills/drive-pr Skill

    0★ repo

    Use when the user says "drive this PR", "/drive-pr", asks to resolve all PR comments, get a PR green, address review feedback, or otherwise wants Claude to iterate on an open pull request until every trusted comment is resolved, CI is passing, and the PR description matches the code. Runs /review-pr upfront for a baseline audit (informational by default; pass --audit-blocks to make P0s gate the exit). Code-change comments are batched into synthetic findings and dispatched via the agent pipeline (orchestrate-merge + fix-applier under sensitivity gating) so edits across files apply in parallel. Reply-only comments stay on the existing inline path. GH-specific ops (post replies, resolve threads, monitor CI) remain in the skill. Operates only on the current branch's PR or an explicitly passed PR number/URL.

  • Open pr

    0xdeafcafe/skills/skills/open-pr Skill

    0★ repo

    Use when the user says "open a PR", "/open-pr", "make the PR", "ship this", "draft a PR", "create the PR", or wants Claude to turn the current branch's work into an open pull request. Runs final sanity checks (lint, format, type-check, tslsp diagnostics if installed), drafts a title and body that actually describe what's in the diff and commits + any linked ADR / spec / ticket, confirms with the user, then pushes and opens via `gh pr create`. Closes by asking whether to drive the PR now (`/drive-pr`) or wait for review. Bookend to `/drive-pr` - open-pr opens, drive-pr iterates.

  • Review change

    0xdeafcafe/skills/skills/review-change Skill

    0★ repo

    Use when the user says "review the change", "/review-change", "audit my working tree", "what's wrong with what I've got staged", "review without fixing", or asks Claude to audit the working tree's diff read-only without modifying files, committing, or pushing. Read-only mirror of /drive-change — same slice/fan-out/merge/verify pipeline, same finding-format output, never edits or commits. Always runs /review-code + /review-test + /review-feature + /review-security; adds /review-ux when UI extensions are touched. Produces a single terminal report grouped by severity. Use /drive-change when you want Claude to apply the fixes; use /review-change when you want the verdict and intend to act on it yourself.

  • Review code

    0xdeafcafe/skills/skills/review-code Skill

    0★ repo

    Use when the user wants Claude's judgment on the design and shape of code in touched files — single-responsibility, modularity, layering, naming, length, structural smells, dead code, stale comments — without running linters or formatters and without applying any fixes. Triggers on "/review-code", "review the code", "what's wrong with this code's design", "is this file too long", "code-quality findings on design", "structural review", "the design pass". Read-only audit specialist that emits findings in the finding-format.md schema. Does NOT run linters / formatters / LSP diagnostics — that's /review-hygiene's job; this skill focuses on judgment a tool can't make. Mechanical findings get concrete fix: lines; structural changes (extract, split, rename module) get decide: prefixes for the orchestrator to escalate. Use /review-code when you want the design verdict; use /review-hygiene for tool-driven lint/format findings; use /drive-change to have the orchestrator dispatch the fixes.

  • Review feature

    0xdeafcafe/skills/skills/review-feature Skill

    0★ repo

    Use when the user says "review the feature", "/review-feature", "audit the feature logic", "is the feature complete", "check edge cases", or asks Claude to evaluate whether a feature (typically the one in the current PR) is well built end-to-end against its spec without modifying any code. Read-only audit specialist — reads any ADRs and specs that exist for the feature, traces the data flow from entry to exit, and emits findings for each gap, edge case, error-handling miss, or spec mismatch in finding-format.md schema. Does NOT pass judgment on code style (use /review-code) or click through the UX (use /review-ux). Use /review-feature when you want the feature-logic verdict in finding form; use /drive-change to have the orchestrator dispatch the fixes those findings describe.