mattpocock-skills
claudeMatt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Use GLM-5.3 (z.ai) from inside Claude Code for code reviews or to delegate tasks.
Plugin glm from marketplace radityasurya-glm in radityasurya/glm-plugin-cc. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
glm-5-2-promptingGuidance for prompting GLM-5.3 effectively when delegating review, rescue, or adversarial-review work via the glm plugin. Use when constructing prompts sent to GLM through glm-broker.mjs.
/glm:adversarial-reviewRun a skeptical design review with GLM-5.3 that challenges the approach, tradeoffs, auth, and reliability of local changes. Append focus text to steer it.
/glm:cancelAbort a running GLM job by id (or the most recent job if no id is given). Stops the worker, its claude process, and everything claude started, then marks the job cancelled.
/glm:rescueHand a task to GLM-5.3 via z.ai to investigate or fix
/glm:resultFetch the result (and metadata) of a GLM job. Pass a job id, or omit for the most recent job.
/glm:reviewRun a GLM-5.3 code review against local git state (read-only)
/glm:setupCheck GLM plugin readiness and toggle the stop-time review gate. Run after install to confirm the z.ai key and claude binary are available.
/glm:statusCheck the status of GLM jobs. Pass a job id for one job, or omit to list recent jobs.
/glm:transferHand the current Claude Code session off to a resumable GLM-5.3 thread. Renders a prior Claude transcript and starts a GLM session continuing that work.
glm-rescueSubagent that delegates active debugging, multi-file refactors, or implementation loops to GLM-5.3 via the glm plugin's broker. Use for tasks you want to run against GLM rather than the primary model.
node ${CLAUDE_PLUGIN_ROOT}/scripts/session-lifecycle-hook.mjs
node ${CLAUDE_PLUGIN_ROOT}/scripts/stop-review-gate-hook.mjs
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
6 skills · 7 commands · 4 agents
Use Codex from Claude Code to review code or delegate tasks.
3 skills · 8 commands · 1 agent · hooks
Write, review, debug, and document LanceDB pipelines in Python and TypeScript that work with both LanceDB Embedded and LanceDB Enterprise.
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.