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 →

13Stars on the repository
231Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

supersede-decision

193

tomzx/agents

Skill Claude Code

Mark an existing decision as superseded by a newer one, updating status in both records and validating the relationship.

not rated 13 +1 yesterday A 28 tokens original MIT

sync-articles

194

tomzx/agents

Skill Claude Code

Bring a batch of blog articles into conformance with the repository writing rules by dispatching one create-article job per article via opencode run, in parallel, then verifying links, front matter, style, and AI disclosure tags. Use when the user says /sync-articles, "sync articles", "update articles according to the…

not rated 13 +1 yesterday A SkillSpector: warn 91 tokens original MIT

sync-documentation

195

tomzx/agents

Skill Claude Code

Reconcile the docs/ directory with the codebase so documentation stays current. Detects and fixes drift between code and docs (stale references, missing docs, broken links, nav drift, outdated examples). Use when the user says /sync-documentation, "sync docs", "update docs", "docs are stale", or wants to ensure docs…

not rated 13 +1 yesterday A SkillSpector: pass 78 tokens original MIT

tomzx/agents

Skill Claude Code

Create any Mermaid diagram (flowchart, sequence, class, state, ER, C4, architecture, gantt, mindmap, timeline, pie, sankey, and 20+ more) from a description or source material. Use when the user says "diagram", "visualize", "mermaid", "draw a flowchart", "sequence diagram", "ER diagram", "mindmap", "gantt chart", or…

not rated 13 +1 changed 7d ago A 129 tokens original MIT

create-svg-image

197

tomzx/agents

Skill Claude Code

Create great looking SVG diagrams, images, and visualizations as hand-authored SVG following a bundled style guide. Use when the user says "svg", "create an svg image", "svg diagram", "draw this as svg", "architecture diagram in svg", or asks for a figure that needs pixel-level control over layout, color, or branding…

not rated 13 +1 changed 22d ago A 92 tokens original MIT

select-issue

198

tomzx/agents

Skill Claude Code

Select the next issue to work on from a GitHub project's priority view, constrained to work also planned in the roadmap view. Use when the user says /select-issue, "what should I work on", "pick the next issue", or wants the next planned high-priority issue.

not rated 13 +1 yesterday A 62 tokens original MIT

handle-failing-pr-ci

199

tomzx/agents

Skill Claude Code

List your open pull requests and their CI status, then fix failing CI across all of them in parallel by fanning out one handle-pr-ci session per failing PR. Use when the user says /handle-failing-pr-ci, "fix my failing CI", "my PRs have failing checks", "get my PRs green", "check my PRs CI", or wants to bulk-fix CI on…

not rated 13 +1 changed 22d ago A 92 tokens original MIT

tomzx/agents

Skill Claude Code

Search Slack for messages a set of colleagues authored on a given day, read the full threads behind them, and extract the decisions each of them made plus who supported them, filtering out the chatter and citing permalinks. Use this to catch up on what changed across a team without reading every thread, or when asked…

not rated 13 +1 changed 22d ago A 120 tokens original MIT

assess-pr-risk

201

tomzx/agents

Skill Claude Code

Estimate how risky a GitHub pull request is and how confident that estimate is, then recommend the next action for a human reviewer. Self-contained: it gathers its evidence from the diff, the codebase, and churn of the touched files, so it can run in parallel with the other review skills. Use when the user asks "how…

not rated 13 +1 changed today A 0 tokens original MIT

propagate-changes

202

tomzx/agents

Skill Claude Code

Run a bidirectional propagation pass over the SDLC artifact chain after a change, updating the artifacts that depend on the change (downward) and re-checking the premises the change depends on (upward). Use when the user says /propagate-changes, "propagate changes", "propagate this change", "bring the artifacts back…

not rated 13 +1 changed 22d ago A 105 tokens original MIT

tomzx/agents

Skill Claude Code

Remove local git worktrees (and their branches) whose associated pull request was merged, verifying merge state against GitHub instead of git ancestry. Use when the user says /prune-merged-worktrees, "prune worktrees", "clean up merged worktrees", "remove worktrees for merged PRs", or wants stale worktree cleanup…

not rated 13 +1 changed 22d ago A 79 tokens original MIT

tomzx/agents

Skill Claude Code

Refactor the code just produced by create-implementation, introducing only the abstractions and seams it needs to stay small, cohesive, and testable, using the dependency-breaking and behavior-preservation techniques from Michael Feathers' Working Effectively with Legacy Code. Use after implementation and before…

not rated 13 +1 changed 22d ago A 121 tokens original MIT

slack-resolve-threads

205

tomzx/agents

Skill Claude CodeCodex

Go through the Slack threads you participated in, read each one with slackx, judge whether the discussion reached a satisfactory conclusion, and mark resolved threads with a checkmark reaction so future runs skip them. Use this whenever the user wants to triage, review, clean up, or "close out" their open Slack…

not rated 13 +1 yesterday A 107 tokens original MIT

attach-assets

206

tomzx/agents

Skill Claude Code

Upload files (images, logs, screenshots) to a dedicated orphan branch in the repository and embed them in a GitHub issue or PR comment or description, so sensitive content stays out of the main branch and out of inline user-attachments. Use when the user says /attach-assets, "attach image to issue", "attach screenshot…

not rated 13 +1 changed 22d ago A 117 tokens original MIT

tomzx/agents

Skill Claude CodeCodex

Shared guidelines for writing concise, high-signal outbound communication the agent posts or drafts on the user's behalf, covering GitHub PR and issue comments, inline review comments, review reports, thread replies, PR and issue descriptions, Slack messages and announcements, and email. Other skills reference this…

not rated 13 +1 changed 22d ago A 70 tokens original MIT

create-discussion

208

tomzx/agents

Skill Claude Code

Create a GitHub Discussion (for example a feature request in a repository that routes them to Discussions instead of issues) with background, prioritized acceptance criteria (Must/Should), and a justified time budget.

not rated 13 +1 changed 22d ago A 44 tokens original MIT

create-skill

209

tomzx/agents

Skill Claude Code needs its repo

Author a new skill by discovering similar skills, studying their strengths and weaknesses, and synthesizing the best single skill from them. Use when the user says /create-skill, "create a skill", "build a skill", "make a skill for X", or wants a new skill grounded in the best existing examples rather than written…

not rated 13 +1 changed 22d ago A 73 tokens original MIT

improve-sessions

210

tomzx/agents

Skill Claude Code needs its repo

Mine past AI coding sessions from the agentsview SQLite archive and produce prioritized recommendations for improving future sessions (recurring friction, corrections, repeated questions, manual loops, missing skills). Use when the user says /improve-sessions, "improve future sessions", "what should I learn from my…

not rated 13 +1 changed 22d ago A 98 tokens original MIT

review-cli-design

211

tomzx/agents

Skill Claude CodeCodex

Review a CLI design for command-surface completeness, cross-command consistency, usability, error handling, output behavior, and convention fit.

not rated 13 +1 changed 18d ago A 30 tokens original MIT

review-readme

212

tomzx/agents

Skill Claude CodeCodex

Review a README for template conformance, accuracy, completeness, clarity, and getting-started usability.

not rated 13 +1 changed 22d ago A 24 tokens original MIT

review-team-api

213

tomzx/agents

Skill Claude CodeCodex

Review a Team API for completeness, ownership clarity, dependency accuracy, interaction-mode soundness, and contract quality.

not rated 13 +1 changed 22d ago A 26 tokens original MIT

review-team-charter

214

tomzx/agents

Skill Claude CodeCodex

Review a team charter for completeness, clarity, boundary soundness, decision-making, metric quality, and ratifiability.

not rated 13 +1 changed 22d ago A 29 tokens original MIT

identify-bugs

215

tomzx/agents

Skill Claude Code

Proactively discover latent bugs in an existing codebase (correctness, error handling, null and boundary handling, async, concurrency, state, resource management), keep only high-confidence ones, verify each where a seam exists, and use ghx to discard anything already tracked by a GitHub issue, searching for another…

not rated 13 +1 changed 16d ago A 140 tokens original MIT

tomzx/agents

Skill Claude Code

Discover concrete gaps and improvements in an existing codebase, keep only the high-confidence ones, and use ghx to discard anything already tracked by a GitHub issue, searching for another candidate until nothing useful remains. Works bottom-up from the code (correctness, tests, maintainability, performance…

not rated 13 +1 changed 22d ago A 134 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: