Comments
Code comments and annotations
parley
by osdlc
Check, serve and render a parley document as one review page, then read the reviewer's comments and answers back and reply to each one. A document is JSON: a list of typed blocks and the questions the agent needs answered. The peer parley.mjs is one bundled file that runs under bun, node 22+ and deno with no dependencies and no build step.
deslop
by strikersam
Remove AI code slop before committing. Review AI-generated code for unnecessary verbosity, redundant comments, over-engineering, and low-signal patterns that degrade codebase quality over time.
cron-scheduler
by AIDotNet
解析、验证和解释cron表达式，计算下次运行时间。
documentation-writer
by AIDotNet
生成全面的文档，包括README文件、API文档、代码注释（JSDoc、docstrings、XML）和架构文档。
council-review
by strikersam
Multi-perspective code review before merging. Simulates a council of reviewers (security, correctness, performance, maintainability) independently evaluating a change. Use before any PR merge or for significant changes.
pr-review
by milistu
Analyze and explain a pull request to help review it effectively
Digest
by ohdearquant
Ingest research material into the knowledge graph — papers, concepts, implementations. Extract entities, link them, verify density.
docs-sweep
by osdlc
Sweep a codebase's comments and prose for ACCURACY first and length second. Nominates comment blocks deterministically, shards them one owner per file so agents edit concurrently without racing, applies a keep/delete rubric, then runs three verification passes: a comment-only gate over the diff, a review of removals that lost a constraint, and a check that what the sweep WROTE is true. Use for stale comments, dead path citations, doc drift, verbose module headers, duplicated prose, or a "clean up the docs" request at a scale one context cannot hold. Not a formatter and not a linter.
reviewdog
by AgentSecOps
Automated code review and security linting integration for CI/CD pipelines using reviewdog. Aggregates findings from multiple security and quality tools (SAST, linters, formatters) into unified code review comments on pull requests. Use when: (1) Integrating security scanning into code review workflows, (2) Automating security feedback on pull requests, (3) Consolidating multiple tool outputs into actionable review comments, (4) Enforcing secure coding standards in CI/CD pipelines, (5) Providing inline security annotations during development.
pr-stats
by osdlc
Summarize a pull request or branch diff beyond GitHub's +/-: lines added and removed by code, comments, blank and prose; a change-category breakdown (added, deleted, renamed, tests, docs, generated, formatting-only, comment-only, logic); dependency and exported-API changes; and the cyclomatic-complexity movers. Use before or after opening a PR, in review, or when asked to "summarize this change", "how big is this PR", "what did this branch actually change", or "add stats to the PR". Optionally writes the table into the PR body. Runs from a bundled script with plain Node, git and gh; needs no other plugin.
discuss
by osdlc
Propose one solution as a parley document that ends in a decision: the problem, the solution as typed blocks, and a question with a recommendation for every trade-off the reviewer must ratify, so the page can be approved or sent back. Domains are notes beside this skill (sql and ui). Then hand it to parley. Use it when the reader must decide.
consolidate-task-prs
by osdlc
Collapse every open single-task-file PR — each carrying one new draft task file under docs/planning/tasks/ — into a single consolidation PR, deduping the folded tasks against the present task list, then close the superseded PRs and delete their branches. Explicit cleanup only, never auto-invoked: run it to fold an accumulation of one-task-each PRs back into one reviewable PR.
explain
by osdlc
Explain one thing as a parley document with no questions: the subject as typed blocks with numbered nodes anchored to the exact text, a walkthrough the reader comments on. Domains are notes beside this skill (sql today). Then hand it to parley. Use it when the reader needs to understand something, not decide something.
pr-mermaid-comment
by osdlc
Post or update a GitHub pull request comment (or PR body) that carries Mermaid diagrams, and prove the diagrams render before it goes up. Drafts the Markdown in a scratch file, renders every fenced mermaid block through the same pipeline GitHub's viewer uses (GitHub's Markdown API, then Mermaid in headless Chromium at the default security level), screenshots the result, then posts with gh. Use when asked to add diagrams, an architecture summary, or a flow to a PR, or to check whether a Mermaid block on GitHub will render.
pr-respond
by osdlc
Respond to review feedback on an open task PR with lease coordination. Given a PR number, parses the lease-binding footer from the PR body, cd's into the task's worktree, fences the discovered lease against the footer's lease_id, re-acquires the lease into the responding phase, dispatches a sub-agent to address review comments, pushes the response commits, and transitions the lease back to awaiting-review. Each re-acquisition is a CAS-REPLACE with steal-on-expired semantics: two operators racing the same PR resolve to a single owner.
pr-check
by osdlc
Classify the state of a single open or closed pull request into one of a fixed verdict enum — CLEAN, BEHIND, NEEDS-RESPONSE, CONFLICTS, CI-FAILED, CI-BLOCKED, MERGED, CLOSED, or ERROR — plus a one-line reason. Non-interactive and read-only on both the repo and GitHub; the only file it writes is a per-PR cursor under .sdlc/pr-cursors/ (gitignored) used to detect new review comments between calls. Designed to be called per open PR from /sdlc:orchestrate; the parent dispatches on the verdict and never has to parse free-form PR state itself. Supports a --mock-state flag that swaps the live gh payload for a JSON fixture so the classifier and cursor-update path can be exercised deterministically under the eval harness.
tavern2agent
by Xerxes-2
用户提供 SillyTavern 角色卡（PNG/JSON）并要求转换、迁移、移植到 agent 平台（pi coding agent / Claude Code）时使用；覆盖纯角色卡、世界书、以及带骰子/战斗/好感度/经济等游戏系统的复杂卡。
check-pr
by osdlc
"Tend one or more pull requests in a single pass: report their state, rebase them onto their base branch when they are behind or conflicting, and assess and answer new review comments. Fixes worthwhile comments straight away with --fix auto, or proposes the fix and waits for a thumbs-up with --fix ask (the default). Keeps no files of its own and records its answers to review-pr findings on a state ref beside the PR, so it suits a loop such as /loop /check-pr."
review-todos
by osdlc
Scan the codebase for TODO / FIXME / HACK comments, judge each one's worth in context, and ask the user what to do per item: promote to a task (immediate work), capture as a backlog item (defer triage), edit the comment in place, or skip. Promotion to a task calls sdlc task create and commits on main; promotion to a backlog item calls sdlc backlog create, which lands it on the rolling backlog-capture PR.
pr-review
by osdlc
Run an adversarial code review of an open pull request's diff and post the findings as a PR comment. Given a PR number, fetches the diff via gh, judges it against the project's configured rubric (orchestrator.review.rubric_path in sdlc.yaml; falls back to a generic inlined rubric when unset), and posts a summary comment through the same self-posted-comment wrapper /sdlc:pr-respond uses, so the orchestrator's own comment cursor filters it out on the next /sdlc:pr-check tick. Read-only on the repo (no commits, no code changes, no worktree needed) — the posted comment is its only write. This is the sdlc chain's review-stage workflow ([[D-0019-sdlc-chain-stages-and-labels]]); the prs orchestrator tick dispatches it for a PR it has never classified before (merges never dispatches pr-review — only pr-respond, for a merge conflict), under the model workflows.pr-review.profile or .model names.
project-cleanup
by osdlc
Sweep local branches, worktrees, remote branches, and SDLC task linkage to identify what can safely be cleaned up. The deterministic sdlc project cleanup scanner gathers facts and pre-classifies each item; this skill dispatches sub-agents in parallel to investigate ambiguous cases, then presents a single batched plan for one-shot approval, then hands the approved rows to sdlc project apply-cleanup.
github-pr-review
by aidankinzett
Use when reviewing GitHub pull requests with gh CLI - creates pending reviews with code suggestions, batches comments, and chooses appropriate event types (COMMENT/APPROVE/REQUEST_CHANGES)
deft-directive-gh-slice
by deftai
Break a SPECIFICATION.md, PRD, or plan into independently-grabbable GitHub Issues using tracer-bullet vertical slices. Use after spec generation, when the user wants to create implementation tickets, or when breaking work into parallel-assignable issues. Requires the GitHub CLI (gh).
deft-directive-refinement
by deftai
Conversational refinement session. Ingests external work items into xBRIEF proposed/ scope, deduplicates via origin references, evaluates proposals with the user, reconciles stale origins, and promotes/demotes scopes through the lifecycle using deterministic task commands.