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
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

pdlc-status

121

tomzx/agents

Skill Claude CodeCodex

Display a progress dashboard for product initiatives from .pdlc/ directory data, without modifying any artifacts.

not rated 6 +1 today A 26 tokens original MIT

plan-launch

122

tomzx/agents

Skill Claude Code

Plan a product launch — readiness checklist, timeline, channels, and success criteria. Start of the PDLC Launch phase.

not rated 6 +1 today A 27 tokens original MIT

prioritize

123

tomzx/agents

Skill Claude Code

Rank a backlog of initiatives or features using a transparent scoring framework (RICE / WSJF). End of the PDLC Strategy phase.

not rated 6 +1 today A 30 tokens original MIT

prototype-ux

124

tomzx/agents

Skill Claude Code

Create wireframes or a clickable prototype and run a lightweight usability test, recording findings. Part of the PDLC Define phase.

not rated 6 +1 today A 29 tokens original MIT

research-market

125

tomzx/agents

Skill Claude Code

Size the market, map trends and segments, and assess timing for a candidate problem space. Part of the PDLC Discover phase.

not rated 6 +1 today A 29 tokens original MIT

review-metrics

126

tomzx/agents

Skill Claude Code

Read the dashboards, compare actuals against goals, surface anomalies, and produce a health report. Part of the PDLC Measure phase.

not rated 6 +1 today A 31 tokens original MIT

run-experiment

127

tomzx/agents

Skill Claude Code

Execute an experiment plan, collect data, and record a proceed/kill verdict against the pre-set threshold. End of the PDLC Validate phase.

not rated 6 +1 today A 33 tokens original MIT

run-retrospective

128

tomzx/agents

Skill Claude Code

Capture what to keep, stop, and start after an initiative, sprint, or kill. Closes the PDLC cycle by turning experience into durable knowledge.

not rated 6 +1 today A 36 tokens original MIT

set-goals

129

tomzx/agents

Skill Claude Code

Define OKRs, success metrics, and guardrail metrics for a product or initiative. Part of the PDLC Strategy phase.

not rated 6 +1 today A 29 tokens original MIT

set-pricing

130

tomzx/agents

Skill Claude Code

Define the pricing model, packaging, and tiers for an initiative. A consumer of the validated value and willingness-to-pay evidence. Part of the PDLC Launch phase.

not rated 6 +1 today A 37 tokens original MIT

spec-analytics

131

tomzx/agents

Skill Claude Code

Specify the events, funnels, dashboards, and guardrails needed to measure an initiative. Guardrail-first by design. Start of the PDLC Measure phase.

not rated 6 +1 today A 35 tokens original MIT

sunset-product

132

tomzx/agents

Skill Claude Code

Plan the end-of-life for a product or feature — migration, communications, and timeline. A first-class PDLC phase, triggered when an initiative is net-negative.

not rated 6 +1 today A 37 tokens original MIT

sync-pdlc

133

tomzx/agents

Skill Claude Code

Reconcile the .pdlc/ directory with current product reality — create the structure if absent, detect drift, and ensure the anchor exists. The PDLC counterpart of sync-sdlc.

not rated 6 +1 today A 44 tokens original MIT

synthesize-feedback

134

tomzx/agents

Skill Claude Code

Aggregate qualitative signal — support, sales, NPS, reviews — and combine it with the metrics read. Produces the artifact the iterate/sunset gate evaluates. Part of the PDLC Measure phase.

not rated 6 +1 today A 44 tokens original MIT

write-prd

135

tomzx/agents

Skill Claude Code

Write a product requirements document — problem, outcomes, success criteria, and non-goals. Start of the PDLC Define phase.

not rated 6 +1 today A 30 tokens original MIT

post-slack-message

136

tomzx/agents

Skill Claude Code

Post a message to a Slack channel or as a thread reply. By default writes the message to a temp file and asks the user to confirm before sending; pass --yes to send immediately without prompting. Use when the user says /post-slack-message, "post to Slack", "send a Slack message", "reply in a Slack thread", or another…

not rated 6 +1 today A SkillSpector: pass 83 tokens original MIT

pr-review-send

137

tomzx/agents

Skill Claude Code

Send PR review comments to GitHub by file and line number using the pr-comment script.

not rated 6 +1 today A 22 tokens original MIT

prioritize-issues

138

tomzx/agents

Skill Claude Code

Score and rank a backlog of GitHub issues by reach, impact, confidence, and effort (RICE).

not rated 6 +1 today A 27 tokens original MIT

publish-plan

139

tomzx/agents

Skill Claude Code

Commit an implementation plan to a branch, open a draft PR linked to the originating issue, and post a comment on the issue pointing to the PR.

not rated 6 +1 today A 33 tokens original MIT

qualify-issue

140

tomzx/agents

Skill Claude Code

Drive a multi-round Q&A loop with an external reporter to gather enough information to proceed to requirements.

not rated 6 +1 today A 25 tokens original MIT

quick-pr-review

141

tomzx/agents

Skill Claude Code

Rapidly review and approve a GitHub pull request to unblock others. Approves unless there are significant risks or significant public interface changes.

not rated 6 +1 today A SkillSpector: warn 31 tokens original MIT

quick-pr-reviews

142

tomzx/agents

Skill Claude Code

Check all PRs where you are a requested reviewer for new commits and run quick-pr-review on each one that has changed since last reviewed. Optionally filter to specific organizations or repositories (owner/repo).

not rated 6 +1 today A 46 tokens original MIT

record-asciinema

143

tomzx/agents

Skill Claude Code

Record a terminal/CLI demonstration with asciinema, render it to an embeddable GIF (or SVG), and return the asset path. Reusable recording primitive used by verify-pr and validate-implementation.

not rated 6 +1 today A 46 tokens original MIT

record-playwright

144

tomzx/agents

Skill Claude Code

Record a web UI demonstration with Playwright, capturing screenshots at one or more viewports and optionally a video clip, then return the asset paths. Reusable recording primitive used by verify-pr and validate-implementation.

not rated 6 +1 today A SkillSpector: warn 46 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: