tomzx/agents

A library of composable skills, agents, and conventions that teach agents how to perform repeatable software-engineering and knowledge-work tasks

This repository also configures its own agents. See what agents tells them →

6Stars on the repository
200Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

review-project

169

tomzx/agents

Skill Claude CodeCodex

Review the project context files (.sdlc/context/) for completeness, consistency, clarity, and actionability. Use when the user says /review-project, after /create-project, or before relying on project context to drive feature work.

not rated 6 yesterday A 50 tokens original MIT

review-question

170

tomzx/agents

Skill Claude Code

Review a question record for specificity, answerability, impact, and resolution quality, then record the answer and set the lifecycle status.

not rated 6 yesterday A 29 tokens original MIT

review-requested-prs

171

tomzx/agents

Skill Claude Code

Orchestrate full PR reviews (validate-pr, verify-pr, review-pr) across all PRs where you are a requested reviewer, or on a specific PR by URL. Skips steps already completed for the current commit. Never posts anything to GitHub; all reports are written locally.

not rated 6 yesterday A SkillSpector: warn 64 tokens original MIT

review-requirements

172

tomzx/agents

Skill Claude CodeCodex

Review a requirements document for clarity, completeness, testability, and feasibility.

not rated 6 yesterday A 20 tokens original MIT

review-roadmap

173

tomzx/agents

Skill Claude CodeCodex

Review a roadmap for alignment, sequencing, focus, horizon discipline, and currency before it drives prioritization.

not rated 6 yesterday A 25 tokens original MIT

review-service-levels

174

tomzx/agents

Skill Claude CodeCodex

Review SLOs, SLIs, SLAs, and error budgets for measurability, coverage, and policy soundness.

not rated 6 yesterday A 31 tokens original MIT

review-skills

175

tomzx/agents

Skill Claude Code

Audit a skill directory for duplicates, broken references, circular dependencies, orphaned skills, composability issues, and skill gaps. Use when the user says /review-skills or wants to audit their skill library.

not rated 6 yesterday A SkillSpector: warn 46 tokens original MIT

review-specifications

176

tomzx/agents

Skill Claude CodeCodex

Review a technical specification for ambiguities, inconsistencies, incoherences, missing information, and implementability concerns.

not rated 6 yesterday A 27 tokens original MIT

tomzx/agents

Skill Claude CodeCodex

Review a task decomposition for granularity, completeness, dependency clarity, and estimability.

not rated 6 yesterday A 23 tokens original MIT

review-telemetry

178

tomzx/agents

Skill Claude CodeCodex

Review a telemetry plan for completeness, actionability, measurability, and consistency with the specification.

not rated 6 yesterday A 25 tokens original MIT

review-tests

179

tomzx/agents

Skill Claude CodeCodex

Review a test suite or test plan for coverage, quality, correctness, and maintainability.

not rated 6 yesterday A 21 tokens original MIT

sdlc-status

180

tomzx/agents

Skill Claude Code

Display a progress dashboard for SDLC features from .sdlc/ directory data, without modifying any artifacts. Use when the user says /sdlc-status, wants a status report, wants to see feature progress, or asks "where am I" in the SDLC pipeline.

not rated 6 yesterday A SkillSpector: pass 62 tokens original MIT

sdlc

181

tomzx/agents

Skill Claude Code

Run the full software development lifecycle pipeline, from issue creation through implementation, documentation, and learnings capture.

not rated 6 yesterday A SkillSpector: warn 25 tokens original MIT

session-review

182

tomzx/agents

Skill Claude CodeCodex

End-of-session checklist covering code quality (tests, docs, specs, simplicity, observability) and higher-level concerns (architectural fit, breaking changes, rollback, technical debt, communication).

not rated 6 yesterday A SkillSpector: pass 41 tokens original MIT

setup-docs-site

183

tomzx/agents

Skill Claude Code

Scaffold a MkDocs documentation site with Material theme, initial content structure, and a GitHub Actions workflow to publish to GitHub Pages. Use when the user says /setup-docs-site, "set up docs", "create docs site", "mkdocs setup", or wants to bootstrap a documentation website.

not rated 6 yesterday A SkillSpector: warn 67 tokens original MIT

slack-kb-channel

184

tomzx/agents

Skill Claude CodeCodex

Build or update a Slack channel knowledge base for a given month. Works for any accessible channel given its Slack channel id. Ingests threads via the Slack API and produces temporal monthly memory files.

not rated 6 yesterday A 45 tokens original MIT

slack-kb-individual

185

tomzx/agents

Skill Claude CodeCodex

Collect all Slack conversations a specific person participated in during a date range. Useful for performance reviews, 1:1 prep, or building a picture of someone's contributions. Outputs JSONL via the Slack API.

not rated 6 yesterday A 48 tokens original MIT

slackx

186

tomzx/agents

Skill Claude CodeCodex

Use the slack-cached CLI to cache and read Slack threads, channel history, users, and channels from a local SQLite database. It fetches threads via conversations.replies, channel history via conversations.history, and workspace users/channels, storing everything locally so subsequent reads are instant and incremental.…

not rated 6 yesterday A SkillSpector: warn 150 tokens original MIT

sprint-retro

187

tomzx/agents

Skill Claude CodeCodex

Generate a sprint retrospective covering kudos, what went well, what could have gone better, blockers to speed, and action items. Use when the user asks for a sprint retro, retrospective, or sprint review.

not rated 6 yesterday A 47 tokens original MIT

tomzx/agents

Skill Claude Code

Draft and post a structured infrastructure progress announcement to relevant stakeholder Slack channels. Use when the user says /stakeholder-announcement, "announce to stakeholders", "post progress update", or wants to share infrastructure changes (GSAs, WIF, cluster provisioning, batch inference milestones) with…

not rated 6 yesterday A 64 tokens original MIT

start-day

189

tomzx/agents

Skill Claude CodeCodex

Opens the workday by grounding priorities in yesterday's plan and goals, and optionally writes a short start-of-day note. Use when the user says /start-day, start of day, morning planning, or daily kickoff.

not rated 6 yesterday A 48 tokens original MIT

start-month

190

tomzx/agents

Skill Claude CodeCodex

Opens the calendar month with a theme, monthly outcomes, and carryover from the prior month review. Use when the user says /start-month, start of month, monthly planning, or new month kickoff.

not rated 6 yesterday A 45 tokens original MIT

start-week

191

tomzx/agents

Skill Claude CodeCodex

Opens the calendar week with themes, outcomes, and carryover from last week. Use when the user says /start-week, start of week, weekly planning, or Monday kickoff.

not rated 6 yesterday A 40 tokens original MIT

summarize-meeting

192

tomzx/agents

Skill Claude Code

Produces a structured meeting summary document from a transcript file. Use when the user says "summarize meeting", "meeting summary", "summarize transcript", or provides a meeting transcript file to process.

not rated 6 yesterday A 47 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: