gh-autopilot
No SKILL.md available for this skill.
View on GitHubMore from henryqw/skills
codex-subagent
Dispatch one or more tasks to Codex CLI subagents to save Claude Code tokens. Accepts explicit task descriptions, auto-selects sandbox (read-only vs workspace-write) and reasoning effort (high vs xhigh) based on task type, and collects structured results with durable artifacts.
2trueflow
Run the full generic trueflow pipeline by invoking `trueflow_initializer`, `trueflow_adversary`, and `trueflow_referee` in sequence, persisting stage outputs under `.context/trueflow/`, and returning a consolidated `findings.md` table. Use this skill whenever the user asks to "use trueflow" or wants multiple agents to review artifacts, solution proposals, coding implementation plans, documents, prompts, or other material and return adjudicated findings rather than a single opinion.
1issue_referee
Make the final ruling on candidate issues by comparing original artifacts against issue_finder and issue_adversary outputs. Use this skill whenever the main agent needs a definitive upheld/unclear/rejected decision for issue claims, even if the user only asks to arbitrate, referee, adjudicate, validate, or make the final call.
1issue_finder
Find plausible issues in any artifact with high recall. Use this skill whenever the user asks to review, audit, critique, inspect, red-team, sanity-check, or look for problems in code, specifications, documents, plans, datasets, prompts, transcripts, logs, reports, or similar material, even if they do not explicitly ask for an "issue finder.
1issue_adversary
Attack issue_finder claims using the original artifacts. Use this skill whenever the main agent has both the original artifacts and the output of issue_finder and needs to challenge, rebut, pressure-test, or adversarially review each candidate issue before a final ruling, even if the user does not explicitly ask for an "adversary.
1trueflow_adversary
Attack `trueflow_initializer` findings using the original artifacts and persist the review to `.context/trueflow/adversary.md`. Use this skill whenever the main agent has both the original artifacts and the output table from `trueflow_initializer` and needs to challenge, rebut, or pressure-test candidate findings in any generic evaluation workflow, even when the task is not issue-focused.
1