Skip to content

compound-engineering-plugin

by EveryInc

Office Compound Engineering plugin for Claude Code, Codex, and more

About

Office Compound Engineering plugin for Claude Code, Codex, and more

23,277
Stars
45
Skill Files
1,801
Forks
713
PRs Merged
81
Contributors
53
Issues Open
243
Issues Closed
2026-07-21
Last Activity

Skill Analysis

168
Avg Lines / Skill
2,397
Avg Words / Skill
144
Code Blocks
729
Total Files
10.34 MB
Repo Size
119
Reference Files
Skill lines6 min / 103 median / 817 max
Code languagesbash, json, markdown, mermaid, text, yaml
Frontmatter keysallowed-tools, argument-hint, capabilities, ce_platforms, description, disable-model-invocation, model, name, user-invocable
Has CLAUDE.mdYes
Has LicenseYes
File typesmd (476), ts (151), json (31), py (25), sh (15), yaml (8), jsonl (4), yml (3), png (2), js (2)

Skills (51)

  • triage-prs
    194 lines955 words7 blocks

    Triage all open PRs with parallel agents, label, group, and review one-by-one

    bash
  • ce-polish
    112 lines656 words5 blocks

    "Start the dev server, inspect the feature in browser, and iterate on polish."

    bash
  • ce-optimize
    668 lines5540 words18 blocks

    "Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt ...

    bashyaml
  • ce-dogfood
    199 lines2930 words6 blocks

    "Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression te...

    bashmermaid
  • ce-resolve-pr-feedback
    68 lines1242 words

    Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.

  • ce-test-browser
    242 lines1534 words10 blocks

    Run browser tests for pages affected by the current branch or PR.

    bashmarkdown
  • ce-babysit-pr
    241 lines10468 words5 blocks

    "Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement throughout ...

    bash
  • ce-riffrec-feedback-analysis
    38 lines471 words1 blocks

    Analyze Riffrec feedback captures from bundles or standalone recordings. Always load for `riffrec-*.zip`, `session.json` + `events.json` + `recording....

    bash
  • ce-brainstorm
    341 lines7079 words1 blocks

    'Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decid...

    bash
  • ce-test-xcode
    209 lines994 words5 blocks

    "Build and test iOS apps on simulator with XcodeBuildMCP."

    bashmarkdown
  • ce-product-pulse
    177 lines2043 words

    "Generate time-windowed product pulse reports from configured signals."

  • ce-proof
    347 lines2351 words11 blocks

    Publish, read, comment on, or edit markdown in Proof. Use for Proof links, sharing specs/plans/drafts, or publish handoffs from planning workflows; av...

    bashjson
  • ce-debug
    313 lines5166 words2 blocks

    'Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after...

  • ce-promote
    140 lines1572 words3 blocks

    "Draft launch or promotion copy for a shipped feature."

    bash
  • ce-handoff
    135 lines1704 words3 blocks

    Create a session handoff for another agent, or resume, find, and read any user-selected continuity source. Use when work or conversation must continue...

    bashtextyaml
  • ce-sweep
    165 lines2039 words2 blocks

    "Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes m...

    bash
  • ce-compound-refresh
    680 lines8429 words7 blocks

    Refresh docs/solutions learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general r...

    text
  • lfg
    115 lines3014 words1 blocks

    "Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR,...

    bash
  • ce-compound
    756 lines9656 words18 blocks

    Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.

    bash
  • ce-explain
    103 lines2268 words1 blocks

    "Create a durable, visual teaching artifact — plus an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick — for...

    bash

Recent Commits

-356 contributions across all repos
JulAugSepOctNovDecJanFebMarAprMayJunJul
Less
More
  • 11e3d462026-07-21
    fix(kiro): don't rewrite absolute paths as slash command skill refs (#1171)
    Luke Johnson
  • f0e188c2026-07-21
    fix(cross-model): scope peer auth failures to execution context (#1211)
    Trevin Chow
  • 6493b8d2026-07-21
    fix(ce-code-review): tool-adaptive evidence ladder for callsite recall (#1191)
    EthycalOne
  • 880231f2026-07-21
    fix(ce-code-review): make codex stdout-recovery JSON extractor string-aware (#1207)
    dev_Hakaze
  • e5ed7e62026-07-21
    fix(ce-code-review): skip cross-model adversarial peer when the diff is empty (#1205)
    dev_Hakaze
  • 7d61a8a2026-07-21
    fix(ce-brainstorm): preserve multi-area project continuity (#1210)
    Trevin Chow
  • 5f48fb52026-07-21
    feat(ce-plan,ce-brainstorm): elevate reasoning to a chosen model on any harness (#1206)
    Trevin Chow
  • 80550a82026-07-21
    feat(ce-ideate): generalize issue-tracker ideation to any tracker (#1209)
    Trevin Chow
  • 10bdacd2026-07-21
    fix(ce-code-review): move codex adversarial peer to gpt-5.6-luna at xhigh (#1208)
    Trevin Chow
  • b3c38a22026-07-21
    fix(ce-code-review): recover oversized adversarial reviews (#1200)
    Trevin Chow