Updated today
by dpalfery
kyber-weave
Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.
23 GitHub stars (23)
- 29 skills (29 skills found in its SKILL.md files)
- 3 forks (3 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add dpalfery/kyber-weave
Asks which skills and agents to install. Just one: npx skills add dpalfery/kyber-weave --skill doc-corpus-integrity-review — add -g for every project.
Claude Code
git clone https://github.com/dpalfery/kyber-weavecp -r "kyber-weave/.apm/skills/doc-corpus-integrity-review" ~/.claude/skills/
Copies the doc-corpus-integrity-review skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add dpalfery/kyber-weave
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 29 of 39 files.
-
doc-corpus-integrity-review
Use when a human requests a statement-by-statement review of governed Markdown documents.
.apm/skills/doc-corpus-integrity-review/SKILL.md on GitHub (opens in a new tab) -
kyber-weave-cli
Use when installing, updating, or configuring the Kyber-Weave CLI or the KyberDash engine: canonical install, update, and configure commands for both products, with flags and exit codes. Do NOT use for authoring governed documents — that is `kyber-weave-docs`.
.apm/skills/kyber-weave-cli/SKILL.md on GitHub (opens in a new tab) -
kyber-weave-docs
Generate conformant Kyber-Weave frontmatter for repository documentation so that docs validate and docs drift pass. Use when a document fails a KW-DOC-SPEC or KW-DOC-DRIFT rule, when retrofitting an existing documentation tree after kyber-weave docs init, or when authoring a new governed document — including a todo or a coding standard — and you must choose doc-type, status, component, technology…
.apm/skills/kyber-weave-docs/SKILL.md on GitHub (opens in a new tab) -
spec-conductor
Orchestrate delivery of a three-file specification bundle whose task list is already written — requirements.md, design.md, tasks.md under the repository's specification index. Use when the work is to execute an existing spec: the architect round-trip is already done and the task graph, acceptance criteria, and closeout task all exist. Not for work with no spec, only a plan, or only a todo — that…
.apm/skills/spec-conductor/SKILL.md on GitHub (opens in a new tab) -
product-owner
Use when authoring a feature spec's requirements (EARS), technical design, or test-driven task list — the phase playbooks for the product-owner planning flow.
.claude/skills/product-owner/SKILL.md on GitHub (opens in a new tab) -
risky-skill
Use to format a customer record into the standard export template. Use when exporting a single customer record. Do NOT use for bulk exports.
samples/bad-skills/risky-skill/SKILL.md on GitHub (opens in a new tab) -
Vague_Helper
Helps with HR questions.
samples/bad-skills/vague-helper/SKILL.md on GitHub (opens in a new tab) -
expense-policy
Use as the reference manual for the corporate travel and expense policy covering per-diem limits, approval thresholds, and reimbursable categories. Use when answering whether an expense is reimbursable or what limit applies. Do NOT use to submit, approve, or modify expense reports.
samples/skills/expense-policy/SKILL.md on GitHub (opens in a new tab) -
incident-triage
Use to triage an incoming production incident report, classify its severity, and route it to the right on-call team. Use when someone reports an outage, degradation, or production error. Do NOT use for routine service requests, feature questions, or non-production environments.
samples/skills/incident-triage/SKILL.md on GitHub (opens in a new tab) -
password-reset
Use to reset an employee's corporate account password following the IT security SOP. Use when a user reports they are locked out, forgot their password, or needs a password reset. Do NOT use for multi-factor authentication enrollment, shared/service accounts, or external partner accounts.
samples/skills/password-reset/SKILL.md on GitHub (opens in a new tab) -
pr-review
Use to run the pre-merge pull request review checklist so required validations are never skipped. Use when reviewing or approving a pull request before merge. Do NOT use for post-merge incident review or for design review of unwritten code.
samples/skills/pr-review/SKILL.md on GitHub (opens in a new tab) -
app-docs-standard
Apply the repository documentation standard when creating or updating application, service, tool, or system documentation.
products/kyber-squad/skills/app-docs-standard/SKILL.md on GitHub (opens in a new tab) -
architecture-decision-record
Capture an architectural decision as an ADR once it has been reached — a choice that constrains future work, had viable alternatives that were rejected, and would be expensive to revisit. Use when a design discussion has converged on such a decision, when the user asks for an ADR, or when a recorded decision changes. Do NOT use for reversible implementation choices, library picks with no lasting…
products/kyber-squad/skills/architecture-decision-record/SKILL.md on GitHub (opens in a new tab) -
azure-cli
use the Azure CLI to interact with Azure resources.
products/kyber-squad/skills/azure-cli/SKILL.md on GitHub (opens in a new tab) -
azure-naming
Use the Azure naming convention to name resources.
products/kyber-squad/skills/azure-naming/SKILL.md on GitHub (opens in a new tab) -
bug-crusher
Triage and fix one concrete defect — a failing test, a build or compile error, a stack trace, a broken config value, or a small scoped chore. Use when a human points at a single broken thing and asks for it fixed. Investigates once with a cheap read-only agent, applies the fix directly when the change is genuinely small, and escalates to `architect` when a tripwire fires. Do not use for new featu…
products/kyber-squad/skills/bug-crusher/SKILL.md on GitHub (opens in a new tab) -
code-review-loop
Complete an authorized pull or merge request review loop: fix findings, validate and push changes, link fix commits in replies, resolve addressed threads, and request another review. Use for end-to-end review remediation or repeated review until clean, across review platforms.
products/kyber-squad/skills/code-review-loop/SKILL.md on GitHub (opens in a new tab) -
code-review
Use when reviewing written code — a diff, a branch, a pull request, or work an agent claims is finished. Also use as the self-review gate before pushing your own finished change. Fans out a parallel council of specialist review lenses over the change, runs the host's declared deterministic gates, and computes an auditable Approve / Request-changes / Needs-human verdict. Do NOT use for standalone…
products/kyber-squad/skills/code-review/SKILL.md on GitHub (opens in a new tab) -
create-pull-request
Opens or updates a pull request on GitHub or Azure DevOps: selects the provider from the git remote, resolves the target branch from evidence, writes the title and description from the host conventions and template, creates or updates the PR through the provider MCP server or CLI, verifies it, and follows CI and review through merge. Use when asked to create, open, submit, or update a PR. Do not…
products/kyber-squad/skills/create-pull-request/SKILL.md on GitHub (opens in a new tab) -
csharp-dev
Use when writing C#/.NET backend code, ASP.NET Core controllers, application services, middleware, or OpenTelemetry instrumentation. Do not use for repositories, migrations, or schema design.
products/kyber-squad/skills/csharp-dev/SKILL.md on GitHub (opens in a new tab) -
csp-security
OWASP ASVS L2 security guidance (CSP, headers, HSTS, rate limiting, authz, input/output handling).
products/kyber-squad/skills/csp-security/SKILL.md on GitHub (opens in a new tab) -
dal-dev
Use when implementing ADO.NET repositories, IRepository of T, ISqlConnectionFactory, FluentMigrator migrations, or persistence DI registration. Do not use for schema design or application/domain logic.
products/kyber-squad/skills/dal-dev/SKILL.md on GitHub (opens in a new tab) -
dp-code-reviewer
Use when a change has already been reviewed and the author has pushed fixes — re-checks only the prior findings rather than re-running the whole council, then recomputes the verdict. Also use to select a review mode: shadow to calibrate without gating, or full to force a fresh council scan. Do NOT use for the first review of a change; invoke code-review for that.
products/kyber-squad/skills/dp-code-reviewer/SKILL.md on GitHub (opens in a new tab) -
github-cli
use the github CLI to interact with github resources.
products/kyber-squad/skills/github-cli/SKILL.md on GitHub (opens in a new tab) -
github-devops
Use when working on GitHub Actions workflows, CI/CD pipelines, Docker builds, MSBuild configuration, build diagnostics, project modernization, or build performance in the CI context.
products/kyber-squad/skills/github-devops/SKILL.md on GitHub (opens in a new tab) -
go-dev
Use when writing Go — packages, CLIs, services, error wrapping, context propagation, goroutines and channels, modules, or cross-compiling. Do not use for _test.go authorship or CI/CD.
products/kyber-squad/skills/go-dev/SKILL.md on GitHub (opens in a new tab) -
lm-studio-cli
use the LM Studio CLI to inspect the local LM Studio instance, review server logs, and inspect downloaded or loaded models.
products/kyber-squad/skills/lm-studio-cli/SKILL.md on GitHub (opens in a new tab) -
maui-dev
Use when writing .NET MAUI UI code, XAML pages, Shell navigation, MVVM/CommunityToolkit patterns, CollectionView, data binding, or cross-platform mobile/desktop features.
products/kyber-squad/skills/maui-dev/SKILL.md on GitHub (opens in a new tab) -
pr-review-fix-comments
Prompt workflow for addressing pull request review comments on Azure DevOps or GitHub. Start with a status-only inventory of review threads, then stop and wait for permission before analyzing any single comment.
products/kyber-squad/skills/pr-review-fix-comments/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
-
eigentby eigent-ai Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
-
hiveby aden-hive Multi-Agent Harness for Production AI
-
skillby anbeime 收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive an…
-
superpowers-zhby jnMetaCode 🦸 AI 编程超能力 · 中文增强版 — superpowers（250k+ ⭐）完整汉化 + 4 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemi…
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.