Review & quality
19,000 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
SamyakJhaveri/loam/cultivation/marketplace/business-process/skills/weekly-review Skill
0★ repoInteractive weekly review assistant that helps business owners reflect on their week, measure progress against stated goals, and plan the next week with clarity. Use when user says "weekly review", "review my week", "what did I accomplish", "plan next week", "week in review", "how did my week go", or asks to reflect on recent work.
SamyakJhaveri/loam/cultivation/marketplace/code-review-graph/skills/code-review-graph Skill
0★ repoGraphRAG-powered code review with blast-radius analysis via Tree-sitter AST. MCP server. Recommended for 500+ file codebases.
SamyakJhaveri/loam/cultivation/marketplace/helpers/skills/grill-research Skill
0★ repoAdversarial research interrogation before launching an eval or making a published claim. Use before /overnight-eval, before adding a claim to the paper, or when a reviewer-style stress test is needed. 4 waves — basics, clarifications, deep probes, assessment. Stops you from running expensive batches on shaky premises. NOT for implementation plan review (use plan-reviewer agent) or general topic research (use /researcher).
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/grill-with-docs Skill
0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (DOMAIN.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/prototype Skill
0★ repoBuild a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
SamyakJhaveri/loam/cultivation/marketplace/team-deliberation/skills/session-critique Skill
0★ repoUse when a session's implementation work is complete and needs adversarial critique and code quality review before committing. Triggers — after multi-file changes, after feature implementation, before final commit on significant work, when independent review of own work is needed. NOT for single-file trivial edits (use /validate directly) or standard code review without fixes (use /multi-review).
SamyakJhaveri/loam/seed/.claude/skills/commit Skill
0★ repoCreate a conventional commit. Use when user says "commit", "make a commit", or "save changes". NOT for: drafting code, running tests, or anything that changes files — this skill only stages and commits already-finished work.
SamyakJhaveri/loam/seed/.claude/skills/critique-swarm Skill
0★ repoParallel adversarial critique with 4 specialized agents plus synthesis. Use before merging a feature branch, before committing a complex plan, or when you want independent multi-angle review of a plan or implementation. Complements /multi-review (which reviews code quality) by reviewing plan/scope quality. NOT for single-file trivial changes (use /validate), standard code review (use /multi-review), or post-implementation shipping (use /ship).
SamyakJhaveri/loam/seed/.claude/skills/grill-with-docs Skill
0★ repoGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (DOMAIN.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions. NOT for implementation review (use /multi-review) or architecture analysis (use /improve-codebase-architecture).
SamyakJhaveri/loam/seed/.claude/skills/impeccable Skill
0★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
SamyakJhaveri/loam/seed/.claude/skills/multi-review Skill
0★ repoMulti-agent parallel code review with 4 reviewers (style, correctness, security, performance). Use before merging a feature branch, before committing a non-trivial change, or when a second pair of eyes is needed. Complements /validate (which checks pipeline correctness); review checks code quality. NOT for: single-line trivial changes, commit-message review, or replacing /validate — use both, not either.
SamyakJhaveri/loam/seed/.claude/skills/plan-review-invoke Skill
0★ repoInvoke the plan-reviewer agent using the canonical reference prompt from seed/plan-reviewer-design.md. Use when reviewing a plan in a fresh Claude Code session (after the plan was created in a prior session) and you want adversarial review (checklist + Elegance Gate + handoff plan) without manually copy-pasting the reference prompt. Accepts the plan path as an argument. NOT for: same-session plan reviews (just invoke the agent directly with the plan in context), reviewing implementations that already shipped (use /multi-review or /session-critique), or spec audits (the agent has a separate Spec Audit mode invoked differently).
SamyakJhaveri/loam/seed/.claude/skills/pr Skill
0★ repoPush and open a GitHub PR. Use when user says "open a PR", "create a pull request", or "push and PR". NOT for: committing changes (use /commit), running validation (use /validate), or reviewing code (use /multi-review) — only the push-and-PR step.
SamyakJhaveri/loam/seed/.claude/skills/session-critique Skill
0★ repoUse when you explicitly want adversarial, decision-aware critique of a session's completed work before committing — invoke it manually with /session-critique. Reviews every changed artifact (code, data, report) as a senior software engineer and AI researcher, asking: did the work follow the decisions you made this session, follow repo rules, stay un-over-engineered, and leave the codebase maintainable and extensible? Stops at each HIGH/MEDIUM finding to discuss the fix with you before applying it, batches LOW nits, and applies only the fixes you authorize. NOT for single-file trivial edits (use /validate directly) or standard code review without fixes (use /multi-review).
SamyakJhaveri/loam/seed/.claude/skills/ship Skill
0★ repoOrchestrates the full shipping pipeline in strict order. Runs session-critique, then validate (both waves), then commit, then PR. Use when work is complete and ready to ship. Enforces ordering to prevent premature commits and skipped critiques. Accepts optional argument 'critique-only' to run just the critique step. NOT for mid-implementation checks (use /validate), code review without shipping (use /multi-review), or committing without the full pipeline (use /commit directly only if critique + validate already passed).
SamyakJhaveri/loam/seed/.claude/skills/validate Skill
0★ repoPost-session validation loop — two-wave checks (Deterministic / Rule-based) before commit. Use before every git commit. Writes .validation_passed sentinel with waves_passed field on success. NOT for: ad-hoc test runs, code review, or implementation work — only the Pipeline Gate between implement and commit.
SamyakJhaveri/loam/seed/_research/skills/auto-paper-improvement-loop Skill
0★ repoAutonomously improve a generated paper via REVIEWER_MODEL (default o3) xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
SamyakJhaveri/loam/seed/_research/skills/citation-audit Skill
0★ repoZero-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.
SamyakJhaveri/loam/seed/_research/skills/cite-check Skill
0★ repoPaper citation and claims verifier. Use before submitting a paper, after major eval runs that change numbers, or when reviewing a paper draft. Traces every numeric claim in the paper to a result JSON on disk; flags UNTRACED, MISMATCH, STALE_REF, MISSING_CITE, PHANTOM categories.
SamyakJhaveri/loam/seed/_research/skills/grill-research Skill
0★ repoAdversarial research interrogation before launching an eval or making a published claim. Use before /overnight-eval, before adding a claim to a paper, or when a reviewer-style stress test is needed. 4 waves: basics, clarifications, deep probes, assessment. Stops you from running expensive batches on shaky premises.
SamyakJhaveri/loam/seed/_research/skills/hpc-code-reviewer Skill
0★ repoCode review checklist for parallel code correctness in CUDA, OpenMP, and OpenCL. Use when reviewing LLM-generated parallel code translations, when auditing benchmark source code for correctness issues, when writing the paper's 'common failure modes' section, or when a translated kernel has a subtle VERIFY_FAIL that needs root cause analysis. Covers data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.
SamyakJhaveri/loam/seed/_research/skills/paper-claim-audit Skill
0★ repoZero-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.
SamyakJhaveri/loam/seed/_research/skills/paper-review-sim Skill
0★ repoSimulate a NeurIPS/SC/ICSE-style peer review with 5 reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate). Use before paper submission, after major methodology changes, or when stress-testing a draft against expected objections. Each reviewer verifies claims against actual result data.
ats4321/claude-engineering-skills/skills/change-control Skill
0★ repoSafe-change discipline for editing ANY repository. Auto-load before editing files, fixing bugs, refactoring, committing, pushing, publishing, deleting, uploading, or running any irreversible command. Covers read-before-edit, smallest-correct-diff at the root cause (not the symptom), checking every caller before changing a shared function, verifying flag/command behavior (e.g. DRY_RUN) before destructive actions, commit hygiene, when to branch, and never presenting unverified work as done. Trigger keywords: edit, fix, refactor, commit, push, publish, release, delete, migrate, rename, deploy, "make a change", "apply the fix".
ats4321/claude-engineering-skills/skills/code-review-playbook Skill
0★ repoReview other people's (or other agents') changes with rigor and proportion. Auto-load when asked to "review this PR / diff / change / patch", when acting as a reviewer on someone else's work, when reviewing AI-generated code, or when writing/receiving review comments. Covers intent-before-diff reading, review order (tests → contracts → logic → style), severity taxonomy (blocking/important/nit), per-change-type checks, actionable comment craft, and the silence rule (no genuine issues → approve, never invent nits). NOT for making the change yourself (change-control) and NOT for security-focused audits (security-review-playbook).
ats4321/claude-engineering-skills/skills/failure-archaeology Skill
0★ repoMine git history for engineering lessons. Auto-load when asked "what went wrong here", "why is this pinned", "find past incidents", "check the git history", "why does this workaround exist", or before touching code whose shape seems inexplicable. Finds reverts, fix-after-fix chains, security hardening arcs, and dependency-pinning incidents; reconstructs incidents from diffs and commit messages; converts history into concrete guardrails (tests, pins, comments, checklists) so the same failure cannot recur silently.
ats4321/claude-engineering-skills/skills/research-methodology Skill
0★ repoDisciplined investigation of unknowns in any context — codebases, tools, APIs, incidents, claims. Auto-load when the task is to investigate, research, verify, audit, or answer "why/how/whether" questions; when uncertainty exists about how a system behaves; or when findings will feed a decision. Enforces explicit hypotheses, disconfirming evidence, primary-source verification (code > docs > memory), explicit epistemic status labels (verified / inferred / hypothesis / requires verification), date-stamping of volatile findings, digest-form output, and explicit stopping criteria so research converges into action.
ats4321/claude-engineering-skills/skills/security-review-playbook Skill
0★ repoProportional security review for any codebase. Load when reviewing or hardening code that crosses a trust boundary — webhooks, HTTP handlers, deserialization, SQL, shell execution, outbound requests (SSRF), file paths — or when asked "is this secure?". Method: write the threat model FIRST, then harden proportionally. Covers trust-boundary inventory, concrete checks (constant-time compares, size limits before parsing, parameterized queries, allow_pickle=False, fixed-host outbound calls), guardrail-vs-boundary honesty, and locking hardening in with tests.
ats4321/claude-engineering-skills/skills/validation-and-testing Skill
0★ repoRisk-first test strategy for ANY codebase. Auto-load when writing tests, adding a runnable check to a change, deciding what to test first, bootstrapping tests into an untested project, or choosing between mocks/fakes/monkeypatch. Covers testing the highest-risk surface first (security boundaries, parsers, money paths), preferring monkeypatch and hand-rolled fakes over mocking libraries, leaving at least one runnable check per non-trivial change, adding a first test to an untested codebase, and knowing when NOT to write a test (trivial one-liners). Trigger keywords: test, testing, pytest, unit test, coverage, mock, monkeypatch, fake, fixture, "add a test", "how do I test", "is this tested".
yousefkadah/laravel-ai-kit/skills/release-check Skill
0★ repoUse right before opening a pull request or shipping a change. A final gate covering tests, formatting, secrets, tenant-safety, and post-deploy steps.
dungsil/skills/skills/requirement-quality-gate Skill
0★ repoVerifies whether source code, diffs, tests, runtime evidence, or implementation artifacts satisfy stated product or engineering requirements. Separates implementation gates from operation, deployment, data, and manual gates. Use for requirement quality gates, acceptance-criteria checks, implementation verification reports, change-to-requirement mapping, or user-requested adversarial verification of an existing gate report.
kulapoo/opencode-agent-harness/.opencode/skills/code-review-and-quality Skill
0★ repoConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
kulapoo/opencode-agent-harness/.opencode/skills/git-workflow-and-versioning Skill
0★ repoStructures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
srfinch17/peckworks-skills-laboratory/skills/nemesis-review Skill
0★ repoA workshop where skills for LLM agents are engineered, not just written: developed test-first against baseline agent behavior, hardened by adversarial review, and required to earn their keep with a logged field-win record.
srfinch17/peckworks-skills-laboratory/skills/paladin-review Skill
0★ repoA workshop where skills for LLM agents are engineered, not just written: developed test-first against baseline agent behavior, hardened by adversarial review, and required to earn their keep with a logged field-win record.
srfinch17/peckworks-skills-laboratory/skills/review-court Skill
0★ repoA workshop where skills for LLM agents are engineered, not just written: developed test-first against baseline agent behavior, hardened by adversarial review, and required to earn their keep with a logged field-win record.
DevOtts/review-it/plugins/review-it/skills/pr-review Skill
0★ repoSECONDARY review-it mode \u2014 the PR-review PROCESS wrapper. Produces severity-tiered (BLOCKER/MAJOR/MINOR/NIT), evidence-cited (file:line) findings with a blocking-vs-advisory split, loading the consumer project's checklist from .claude/review-config.md (works with zero config via a generic checklist). It does not duplicate /code-review \u2014 it may invoke code-review-style passes as executors and wraps them in process: scope, checklist, severity, evidence, verdict. Invoked by /review-it when the target is a PR ref/branch/diff, or standalone when the user says "review this PR", "review the diff", "pre-merge review".
DevOtts/review-it/plugins/review-it/skills/review-it Skill
0★ repoThe QA front door of the DevOtts lifecycle family \u2014 plan-it plans, build-it builds, /review-it verifies. PRIMARY mission: run the unit tests, e2e tests and test-cases generated at plan phase to prove the build obeys the plan \u2014 the independent verification leg of the plan\u2192build\u2192review triangle. Also verifies third-party side-effects (the Airtable class), staging/prod deploys (deployed-code ladder + [REAL] re-runs), and runs a severity-tiered PR review. Routes execution to full-qa, iterate, chrome-cdp-control, make-eval and parallel-lifecycle \u2014 never re-implements them \u2014 and enforces an 11-rule gate catalog that makes false-VERIFIED claims un-shippable. Invoked with no Test Contract it never refuses and never self-grades \u2014 it runs the no-contract ladder and tags every verdict AUTHORED or DERIVED. Use when the user says "/review-it", "review it", "verify the build", "run the test contract", "QA this feature", "verify this deploy", "review this PR", or when build-it reaches its QA phase.
DevOtts/review-it/plugins/review-it/skills/side-effects Skill
0★ repoThird-party side-effect verification \u2014 the Airtable failure class, first-class. Verifies that writes to external systems (Airtable, Slack, Shopify, CRMs, payment providers) actually landed, by reading the record back from the target system's OWN surfaces \u2014 API GET for field values AND the UI render for display semantics \u2014 with read-back stability (2\u20133 reads) and real-target coverage. Invoked by /review-it when a DoD includes third-party writes, or standalone when the user says "verify the write landed", "check the Airtable/Slack/Shopify record", "did the integration actually save it". A write verified only by sender-side success is not verified.
ChrisLamDev/cocos-creator-debug-skills/skills/cocos-ts-compile-check-sop Skill
0★ repoUse when running TypeScript compile check on Cocos Creator 3.x project.
Syo-M/codex-frontend-skills/.agents/skills/pre-ship Skill
0★ repoPre-merge verification covering scope, typecheck, lint, affected tests, security, accessibility, and a single pass or fail report. 日本語の依頼例:「出荷前チェック」「マージ前確認」「完成か確認」「PR前チェック」。
Syo-M/codex-frontend-skills/.agents/skills/tooling Skill
0★ repoESLint, Stylelint, TypeScript config, environment validation, dead-code checks, and automated convention enforcement. 日本語の依頼例:「Lint設定」「tsconfig」「Stylelint」「ルールをCIで強制」。
Syo-M/codex-frontend-skills/plugins/codex-frontend-skills/skills/pre-ship Skill
0★ repoPre-merge verification covering scope, typecheck, lint, affected tests, security, accessibility, and a single pass or fail report. 日本語の依頼例:「出荷前チェック」「マージ前確認」「完成か確認」「PR前チェック」。
Syo-M/codex-frontend-skills/plugins/codex-frontend-skills/skills/tooling Skill
0★ repoESLint, Stylelint, TypeScript config, environment validation, dead-code checks, and automated convention enforcement. 日本語の依頼例:「Lint設定」「tsconfig」「Stylelint」「ルールをCIで強制」。
adeilsonrbrito/cross-model-consult/consult-opencode Skill
0★ repoConsult the OpenCode CLI for an independent, cross-model second opinion on a decision, design, interpretation, diagnosis, or piece of work. OpenCode runs a different model and provider (default: deepseek/deepseek-v4-flash), so its take is genuine divergence — not an echo of your own reasoning, which is what makes it useful. Reach for it on a genuinely hard or high-stakes call: a decision that is costly or hard to reverse, a design or plan worth pressure-testing before committing to it, a risky diff worth an outside review, or a tie between two interpretations you cannot break from the evidence alone. The user may run it explicitly (/consult-opencode), but also self-invoke it — without being asked — when an outside perspective would actually change the risk on a hard call. Skip it for trivial lookups, routine edits, and decisions you are already confident in: each consult spends real tokens and a few seconds, so spend it only where cross-model divergence would genuinely change the outcome.
finnfotschki/mindful-agent-collaboration/skills/premise-review Skill
0★ repoPeriodically review the premises steering recurring human-agent work—goals, criteria, thresholds, readiness evidence, reliability assumptions, standing rules, memory, routing, delegation modes, gates, and resilience—on an output-independent trigger. Use at calendar or milestone boundaries, after long-running automation, before scaling a workflow, or when rules and memory have accumulated. Propose changes for human decision; never treat successful output as proof that the frame remains appropriate.
finnfotschki/mindful-agent-collaboration/skills/review-gate Skill
0★ repoReview agent-produced work before it is accepted, released, merged, sent, or acted upon. Use evidence-first criterion checks for verifiable autonomous or controlled output, and use hypothesis-first review only at consequential judgment nodes where an assistive recommendation or human-final decision could anchor the reviewer. Supports full, lite, and off: full waits for approve/revise/reject; lite is only for already-autonomous low-reach work; off cannot disable any required review or permission.
IcodeNet/agent-skills/skills/code-review Skill
0★ repoMulti-axis review of diffs before merge. Use when reviewing a PR, branch, or local changes; when asking if a change is safe; or before marking code tasks complete. Do not use for CI babysitting loops or live incidents.
IcodeNet/agent-skills/skills/contract-guard Skill
0★ repoGuard external contracts before changing them. Use BEFORE modifying anything consumed outside the current codebase or by clients you do not control: public/exported APIs, REST/GraphQL endpoints and their request/response shapes, published package entry points, database schemas read by other services, event/message payloads, webhooks, or generated client types. Also use when reviewing a diff that touches such surfaces. Prevents silently shipping breaking changes to external consumers.
IcodeNet/agent-skills/skills/grill-me Skill
0★ repoInterview 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".
The same file is in 23 other repositories
IcodeNet/agent-skills/skills/grill-with-docs Skill
0★ repoGrilling 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.
The same file is in 11 other repositories
IcodeNet/agent-skills/skills/plan-critic Skill
0★ repoChallenge a proposed implementation plan before execution: scope, dependency order, PR slicing, risk, test adequacy, operational readiness. Use when the user asks to review, critique, or stress-test a plan, or after plan-from-rfc when a second pass is wanted.
IcodeNet/agent-skills/skills/pr-babysitter Skill
0★ repoKeep a PR merge-ready after push: monitor CI until green, poll for new review comments (human, Copilot, security scanners, bots), alert the user, validate and auto-fix legitimate feedback, auto-commit and auto-push, reply and resolve threads. Use after pushing to a PR branch or when asked to babysit a PR.
IcodeNet/agent-skills/skills/prototype Skill
0★ repoBuild a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
The same file is in 11 other repositories
IcodeNet/agent-skills/skills/queue-check Skill
0★ repoReconcile the task queue against everything the user has asked in this session. Use when the user says "queue check", "you missed my prompt", "you didn't track that", "find missing todos", "what's outstanding", or when resuming after a context reset and the queue may have drifted.
IcodeNet/agent-skills/skills/rebase-onto-main Skill
0★ repoRebase the current branch onto main with guardrails. Manual command — run with /rebase-onto-main when the user asks to rebase the current branch on main.
IcodeNet/agent-skills/skills/security-review Skill
0★ repoDedicated security pass over a change or feature: trust boundaries, authn/z, input handling, secrets, injection, and dependency risk. Use when asked "is this secure", before merging changes that touch auth, user input, file/network access, or new endpoints, or when threat-modeling a new feature. Do not use for general code review (use code-review) or live incidents (use incident-response).
IcodeNet/agent-skills/skills/squash-and-push Skill
0★ repoSquash the current branch's full history since its base into one commit and force-push with lease. Manual command — run with /squash-and-push when the user asks to squash and push the current branch as a single commit.
Verification before completion
IcodeNet/agent-skills/skills/verification-before-completion Skill
0★ repoGate every completion claim behind executed evidence. Use before saying "done", "fixed", "works", "passing", "delivered", or "merge-ready" — for any code change, bug fix, refactor, or configuration change. Requires running the relevant command and observing the output in this session; code inspection alone never counts as verification.
shinzoxD/knackbox/skills/coding/code-review Skill
0★ repoReview code changes for bugs, security issues, and maintainability with severity-tagged, actionable findings. Use whenever the user shares a diff, pull request, or code snippet and asks for review, feedback, "does this look right", "find issues", or "check my code" — even for small snippets or partial files.