Click AI for Codex

Plugin clickai-codex in timharris707/skills. Commands read from the repo's manifest — 10 days ago.

Skills (24)

• huh

  When a message did not land or pasted agent output needs translation, restate it plainly, expand shorthand, separate results from requests, and flag unsupported claims.

• plainspoken

  For chat replies, status updates, review comments, and commit messages, write plainly without AI tells. Also use to revise generated-sounding drafts or review another agent's prose.

• writing-for-agents

  For skills, standing agent instructions, recorded rules, or documents agents skip, write and prune reliable triggers and checkable steps. Use to author or revise SKILL.md, AGENTS.md, CLAUDE.md, rules and references, or diagnose unreliable invocation and skimming.

• writing-for-humans

  For public-facing drafts, pages that read like agent documentation, or a final AI-tell scrub, write clear human copy in the selected project voice. Covers landing pages, README introductions, launch posts, and profile pages.

• advisory-board

  For an explicitly requested advisory board, roundtable, panel, idea tournament, multi-model review or debate, red-team by several models, or consensus handoff, run an authorized multi-provider process with recorded seats, usage, and evidence.

• decision-map

  When asked to chart a decision map, work a map ticket, or plan work whose open decisions gate each other, map the unresolved choices before build slices. Use for a new primitive, milestone charter, or integration that cannot yet be specified in one sitting.

• grilling

  When asked to grill, stress-test, or pressure-test an idea, or before a decision map or spec rests on an untested conversation, interview the decision maker in small rounds to expose assumptions and settle material choices.

• codebase-review

  Before an upcoming feature, when merged work crosses the recorded review threshold, or when implementation exposes structural friction, review the codebase state with independent skepticism. Deliver the report while keeping unresolved adoption decisions tracked.

• ingest

  For a media file or URL shared with a goal, transcription requests, or takeaways from a call, demo, playtest, or video, build a transcript and timestamped visual evidence packet with a manifest and recommended next workflow.

• prototype

  When discussion or static mockups cannot settle how something should look, behave, or feel, build a disposable interactive experiment: UI variants, a terminal UI, or shareable HTML over a small logic module.

• research

  For factual investigations of vendor materials, regulations, upstream repositories, recorded calls, or other evidence, investigate primary sources and return cited findings. Ask targeted questions when missing facts are held by people; match the requested scope.

• domain-memory

  When design decisions close, review findings are declined, the decider corrects a session's assumption, a new task starts in a repo with a bound memory home, work resumes in a bound repo, or memory exceeds its size bound, record or retrieve project terms and decisions, and propose consolidation when

• router

  When unsure which TeamWorkflow skill applies, or orienting a new task or repository, find the right planning, research, building, review, or recovery workflow. Reuse recorded project bindings and working mode.

• setup

  For a new TeamWorkflow installation, binding refresh, or drift audit after a pack release, inspect and bind the project workflow. Reuse explicit recorded decisions with their sources; ask about missing, conflicting, or changed authority and bindings.

• adversarial-review

  Before committing substantial work, at worker completion, before external review, or on an explicit adversarial/red-team request for a diff, branch, or PR, use independent finders and a skeptic to verify defects, disposition findings, and enforce the blocker gate.

• blast-radius

  When asked for a change's blast radius, assessing whether it is safe to merge, or reviewing a small diff you distrust, trace effects beyond the diff and execute the checks that prove its safety assumptions.

• diagnose

  For a bug-fix brief, a bug resisting its first fix, or a fix about to ship without a proven cause, reproduce the failure, state its cause with evidence, and keep a regression check before shipping.

• handoff

  For checkpoint, save-state, wrap-up, or handoff requests, meaningful milestones, impending compaction, or recovery, save or recover the current Codex task with authorization and ownership intact. Continue in the same task unless a transfer is requested.

• implement

  For a build brief, implementing a spec or tracked item, or mid-build discoveries tempting scope expansion, build thin verified slices with test-first checks at named boundaries, proportional validation elsewhere, and respect for scope and commit instructions.

• orchestrate

  For orchestration mode, coordinating several workers or tasks, or an assigned lead-developer role, direct an agent team: route tracked work, monitor workers, independently verify results, and own integration while the human makes decisions.

• pr-writing

  When filing a PR, updating a PR description, responding to PR review feedback, or writing a PR or review-thread comment on someone's behalf, lead with the problem, show before-and-after evidence that ran, and say whether a revert undoes the change.

• show-me-your-work

  For autonomous multi-phase or unattended work, a reviewer needing an evidence trail, or an explicit decision-log/show-your-work request, keep an append-only decision log with why, evidence, and result. Record decisions and corrections, not hidden reasoning transcripts.

• to-tickets

  When asked to file tickets, break down approved work, or move a settled plan onto the board, turn the spec, closed decision map, or pressure-tested conversation into verifiable work items with real dependencies and non-ticket blockers.

• wizard

  When work stalls on steps only a human can perform, or manual setup is tedious to repeat, create a guided script for dashboards, credentials, DNS, CI secrets, or cutovers. Check available tools first; perform agent-capable steps directly.

Similar plugins