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
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

create-question

49

tomzx/agents

Skill Claude Code

Record an open question with its context, who can answer it, what it blocks, and when the answer is needed.

not rated 6 +1 4d ago A 27 tokens original MIT

create-readme

50

tomzx/agents

Skill Claude Code

Generate a README.md for a project using a structured template with badges, feature lists, roadmap, and setup instructions.

not rated 6 +1 4d ago A 27 tokens original MIT

create-requirements

51

tomzx/agents

Skill Claude Code

Draft a requirements document with functional and non-functional requirements from a feature brief or issue.

not rated 6 +1 4d ago A 22 tokens original MIT

create-roadmap

52

tomzx/agents

Skill Claude CodeCodex

Sequence initiatives across Now/Next/Later horizons, aligned to goals, so prioritization and needs-assessment have a strategic plan to follow.

not rated 6 +1 4d ago A 32 tokens original MIT

tomzx/agents

Skill Claude CodeCodex

Define SLOs, SLIs, SLAs, and error budgets for a service so reliability targets are explicit and measurable.

not rated 6 +1 4d ago A 30 tokens original MIT

tomzx/agents

Skill Claude Code

Create a technical specification from a requirements document, covering architecture, data models, API contracts, and sequences.

not rated 6 +1 4d ago A SkillSpector: warn 25 tokens original MIT

tomzx/agents

Skill Claude Code

Decompose a feature or plan into discrete, actionable tasks with effort estimates and dependencies.

not rated 6 +1 4d ago A SkillSpector: pass 23 tokens original MIT

create-team-api

56

tomzx/agents

Skill Claude Code

Define a team's Team API (Team Topologies), covering team type, ownership boundaries, services, inputs, outputs, dependencies, and interaction modes with other teams.

not rated 6 +1 4d ago A SkillSpector: pass 36 tokens original MIT

create-team-charter

57

tomzx/agents

Skill Claude Code

Author a team charter defining the team's purpose, vision, stakeholders, responsibilities, roles, operating norms, decision-making, and success metrics as a single artifact.

not rated 6 +1 4d ago A SkillSpector: pass 36 tokens original MIT

create-telemetry

58

tomzx/agents

Skill Claude Code

Define analytics events, success metrics, and telemetry for a feature so usage can be measured from day one.

not rated 6 +1 4d ago A 26 tokens original MIT

create-tests

59

tomzx/agents

Skill Claude Code

Create a test plan and test cases covering acceptance criteria, edge cases, and failure scenarios.

not rated 6 +1 4d ago A 21 tokens original MIT

deploy-pr

60

tomzx/agents

Skill Claude Code

Deploy merged changes to the target environment, run smoke tests, and verify the rollback plan.

not rated 6 +1 4d ago A 21 tokens original MIT

describe-colleague

61

tomzx/agents

Skill Claude Code

Generate a profile for a colleague based on their Slack and GitHub activity, covering strengths, weaknesses, interests, avoids, and other relevant information.

not rated 6 +1 4d ago A 33 tokens original MIT

tomzx/agents

Skill Claude Code

Create, view, or update a developer trust profile for a GitHub user. Tracks trust level, strengths, weaknesses, PR patterns, and review history.

not rated 6 +1 4d ago A 36 tokens original MIT

devils-advocate

63

tomzx/agents

Skill Claude Code

Challenge an idea, plan, decision, or argument by constructing the strongest case against it. Use when the user says /devils-advocate, "challenge me", "play devil's advocate", "what am I missing", "steelman the other side", "poke holes in this", or wants stress-testing before committing.

not rated 6 +1 4d ago A 72 tokens original MIT

directory-to-spec

64

tomzx/agents

Skill Claude CodeCodex

Create a spec directory with specification files per major feature for code in the current directory and its subdirectories.

not rated 6 +1 4d ago A 25 tokens original MIT

divio-documentation

65

tomzx/agents

Skill Claude CodeCodex

Write or review documentation following the Divio/Diataxis system, which defines four types: tutorials, how-to guides, reference, and explanation. This is the comprehensive reference skill; create-documentation delegates to this for detailed guidance.

not rated 6 +1 4d ago A 52 tokens original MIT

end-day

66

tomzx/agents

Skill Claude CodeCodex

Closes the workday with GitHub and Slack summaries, overall notes, timeline, and next-day standup. Use when the user says /end-day, end of day, EOD, or daily wrap-up.

not rated 6 +1 4d ago A 47 tokens original MIT

end-month

67

tomzx/agents

Skill Claude CodeCodex

Closes the month with GitHub and Slack summaries, colleague activity, action items, and thanks. Use when the user says /end-month, end of month, monthly summary, or month wrap-up.

not rated 6 +1 4d ago A 44 tokens original MIT

end-of-day-review

68

tomzx/agents

Skill Claude CodeCodex

Reflective end-of-day review that forces alignment between your work, your goals, and your team's goals.

not rated 6 +1 4d ago A 26 tokens original MIT

end-of-day-summary

69

tomzx/agents

Skill Claude CodeCodex needs its repo

Summarize GitHub activity, Slack activity, and overall activity for the day, then generate a standup for the next day.

not rated 6 +1 4d ago A 32 tokens original MIT

end-of-month-review

70

tomzx/agents

Skill Claude CodeCodex

Reflective end-of-month review covering OKR/goal progress, time allocation trends, team trajectory, and strategic focus adjustments for the next month.

not rated 6 +1 4d ago A SkillSpector: pass 34 tokens original MIT

tomzx/agents

Skill Claude CodeCodex needs its repo

Summarize monthly GitHub activity, Slack activity, colleague activity, and generate a monthly highlights report.

not rated 6 +1 4d ago A 26 tokens original MIT

end-of-week-review

72

tomzx/agents

Skill Claude CodeCodex

Reflective end-of-week review covering goal progress, time and attention patterns, team health, and what to change next week. Runs the audit-attention skill to classify the week's activities as compounding or depreciating.

not rated 6 +1 4d ago A 48 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: