tony
- 237 skills
- 0 followers
- 3 days ago last updated
- ▌ Weave Refine · tony bundleUse when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.
- ▌ Weave Review · tony bundleWeave code review — run independent adversarial reviews in parallel, then synthesize findings
- ▌ Reclaim · tonyReclaim disk space through a proof-gated plan — clears regenerable caches, merges proved-redundant copies, and protects agent history
- ▌ Tighten · tonyUse when tightening named files or pasted text in place by removing verbose prose, brittle references, and low-value noise.
- ▌
- ▌ Goal · tonyUse when the review-and-CI loop should continue through bounded rounds until no new actionable feedback remains.
- ▌ What · tonyUse when the user asks what is going on and needs a five-line summary of the session, branch, pull request, and ticket.
- ▌ Draft · tonyUse when asked to file a Linear issue or regression, draft a Jira epic, open a GitLab issue, or create a Shortcut story or tracker document.
- ▌ Prompt · tonyWeave prompt — compare independent adversarial implementations, then pick the best approach
- ▌ Refine · tonyUse when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.
- ▌ Review · tonyWeave code review — run independent adversarial reviews in parallel, then synthesize findings
- ▌ Merge Pr This · tony bundleMerge one PR via gh with a merge commit matching the repo's git history — readiness-gated, CI-watched, trunk synced after
- ▌ Model CLI Agy · tonyUse when delegating to Google Gemini or Antigravity for a second opinion from Google's model; falls back through Gemini and agent CLIs.
- ▌ Model CLI Gpt · tonyUse when invoking OpenAI GPT directly through the same Codex CLI or agent fallback used by the codex skill.
- ▌ Respond Check · tony bundleUse when screening or replying to pull-request review comments and bot findings; decide if each comment is real, worth fixing, deferred, or declined.
- ▌ Situate Brief · tony bundleUse when confusion is only “huh,” “wait, what,” “sorry, you lost me,” or “slow down; explain simply and keep it short.”
- ▌ Spike Bakeoff · tony bundleUse when building two to four competing strategies in isolated git worktrees to compare them without landing commits.
- ▌ Spike Ratchet · tony bundleUse when asked to spike, bake off, then spike again; rinse and repeat, keep spiking, converge on a design, and stop when nothing new fights back.
- ▌ Weave Execute · tony bundleWeave execute — compare independent adversarial implementations, then synthesize their best parts
- ▌ This · tonyMerge one PR via gh with a merge commit matching the repo's git history — readiness-gated, CI-watched, trunk synced after
- ▌ Agy · tonyUse when delegating to Google Gemini or Antigravity for a second opinion from Google's model; falls back through Gemini and agent CLIs.
- ▌ Gpt · tonyUse when invoking OpenAI GPT directly through the same Codex CLI or agent fallback used by the codex skill.
- ▌ Study Deps · tonyUse when pulling upstream source or cloning a dependency at its installed version to study internals, read code, or create pinned worktrees.
- ▌ Check · tonyUse when screening or replying to pull-request review comments and bot findings; decide if each comment is real, worth fixing, deferred, or declined.
- ▌ Brief · tonyUse when confusion is only “huh,” “wait, what,” “sorry, you lost me,” or “slow down; explain simply and keep it short.”
- ▌ Bakeoff · tonyUse when building two to four competing strategies in isolated git worktrees to compare them without landing commits.
- ▌ Ratchet · tonyUse when asked to spike, bake off, then spike again; rinse and repeat, keep spiking, converge on a design, and stop when nothing new fights back.
- ▌ Execute · tonyWeave execute — compare independent adversarial implementations, then synthesize their best parts
- ▌ Respond Action · tony bundleUse when screened review findings should be fixed on the current branch, usually as one verified commit per finding.
- ▌ Scholar Gather · tony bundleResolve and pin a corpus, inventory it, and record what was read and what was deliberately skipped, into sources.jsonl
- ▌ Scholar Render · tony bundleWrite a study's brief and evidence documents, then enforce the brief's citation prohibition with the analyzer
- ▌ Scholar Revise · tonyRecord a correction to a standing claim — what was believed, what it rested on, and why it failed — rather than editing it away
- ▌ Scholar Verify · tony bundleRe-check a finished study against the corpus it cites — refs that moved, files that vanished, quotations that no longer match, numbers that changed
- ▌ Ticket Rebuild · tony bundleUse when rebuilding a bloated tracker item whose epic or Jira ticket hard-codes implementation, restates a spec, or cites counts and line numbers.
- ▌ Action · tonyUse when screened review findings should be fixed on the current branch, usually as one verified commit per finding.
- ▌ Gather · tonyResolve and pin a corpus, inventory it, and record what was read and what was deliberately skipped, into sources.jsonl
- ▌ Render · tonyWrite a study's brief and evidence documents, then enforce the brief's citation prohibition with the analyzer
- ▌ Revise · tonyRecord a correction to a standing claim — what was believed, what it rested on, and why it failed — rather than editing it away
- ▌ Verify · tonyRe-check a finished study against the corpus it cites — refs that moved, files that vanished, quotations that no longer match, numbers that changed
- ▌ Rebuild · tonyUse when rebuilding a bloated tracker item whose epic or Jira ticket hard-codes implementation, restates a spec, or cites counts and line numbers.
- ▌ Action Worktree · tony bundleUse when taking one ticket or a related ticket group into its own branch and git worktree for implementation.
- ▌ Gh Create Issue · tony bundleUse when filing a GitHub issue for a bug, feature, audit, review finding, or investigated piece of work.
- ▌ Model CLI Codex · tonyUse when asked to use Codex, GPT, OpenAI's model, or the Codex CLI to delegate a task; falls back to the GPT agent when needed.
- ▌
- ▌ Scholar Compare · tony bundleSet two term tables against each other — same concept different term, same term different concept, and what each covers that the other lacks
- ▌ Scholar Contest · tony bundleAdversarially judge a distilled ontology one candidate at a time — synonymy, polysemy, orphans, circular evidence, and coverage
- ▌ Scholar Distill · tony bundleBuild the three ontology layers from a term table — types, members with discriminators, and the controlled vocabulary
- ▌ Scholar Extract · tony bundleHarvest terms and their definitions from a gathered corpus into terms.jsonl, each with the citation that supports it
- ▌ Situate Refocus · tony bundleUse when a branch may have drifted from its ticket or pull-request goal and needs its work and gaps reclassified.
- ▌ Worktree · tonyUse when taking one ticket or a related ticket group into its own branch and git worktree for implementation.
- ▌ Create Issue · tonyUse when filing a GitHub issue for a bug, feature, audit, review finding, or investigated piece of work.
- ▌ Codex · tonyUse when asked to use Codex, GPT, OpenAI's model, or the Codex CLI to delegate a task; falls back to the GPT agent when needed.
- ▌
- ▌ Compare · tonySet two term tables against each other — same concept different term, same term different concept, and what each covers that the other lacks
- ▌ Contest · tonyAdversarially judge a distilled ontology one candidate at a time — synonymy, polysemy, orphans, circular evidence, and coverage
- ▌ Distill · tonyBuild the three ontology layers from a term table — types, members with discriminators, and the controlled vocabulary
- ▌ Extract · tonyHarvest terms and their definitions from a gathered corpus into terms.jsonl, each with the citation that supports it
- ▌ Refocus · tonyUse when a branch may have drifted from its ticket or pull-request goal and needs its work and gaps reclassified.
- ▌ Action Worktrees · tony bundleUse when fanning several tickets into parallel branches and git worktrees, with related tickets grouped together.
- ▌ Model CLI Cursor · tonyUse when asked to use Cursor, Cursor's CLI, or the agent binary to delegate a prompt or task; no fallback is available.
- ▌ Model CLI Gemini · tonyUse when invoking Google's Gemini directly through the shared Antigravity, Gemini CLI, or agent fallback chain.
- ▌ Pytest Optimizer · tony bundleUse when a pytest suite or its fixtures are slow and need measured, safety-gated optimization across the full pipeline.
- ▌ Scholar Annotate · tony bundleTake reading notes on a prose corpus — quotations with stable locators and margin notes, as a term source for extract
- ▌ Scholar Ontology · tony bundleUse when distilling an ontology, controlled vocabulary, or glossary of what a codebase, a repository set, or a written corpus calls things.
- ▌ Weave Brainstorm · tony bundleUse when a creative prompt, design question, or open-ended problem needs multiple independent adversarial ideas.
- ▌ Weave Fix Review · tony bundleFix weave review findings — validate, add test coverage, fix, and commit each as atomic changes
- ▌ Worktrees · tonyUse when fanning several tickets into parallel branches and git worktrees, with related tickets grouped together.
- ▌ Cursor · tonyUse when asked to use Cursor, Cursor's CLI, or the agent binary to delegate a prompt or task; no fallback is available.
- ▌ Gemini · tonyUse when invoking Google's Gemini directly through the shared Antigravity, Gemini CLI, or agent fallback chain.
- ▌ Annotate · tonyTake reading notes on a prose corpus — quotations with stable locators and margin notes, as a term source for extract
- ▌ Ontology · tonyUse when distilling an ontology, controlled vocabulary, or glossary of what a codebase, a repository set, or a written corpus calls things.
- ▌ Brainstorm · tonyUse when a creative prompt, design question, or open-ended problem needs multiple independent adversarial ideas.
- ▌ Fix Review · tonyFix weave review findings — validate, add test coverage, fix, and commit each as atomic changes
- ▌ Business Research · tony bundleUse when collecting evidence for the business value of an AI skill or workflow into a provenance-tagged research package.
- ▌ Changelog Refresh · tonyUpdate the branch's own changelog entries to match its current net change; commits only with --commit
- ▌ Merge Pr Multiple · tony bundleMerge a set of PRs one at a time — detect stack vs independent set, rebase and resolve conflicts between merges, watch CI, merge each via gh
- ▌ Research · tonyUse when collecting evidence for the business value of an AI skill or workflow into a provenance-tagged research package.
- ▌ Multiple · tonyMerge a set of PRs one at a time — detect stack vs independent set, rebase and resolve conflicts between merges, watch CI, merge each via gh
- ▌ Double Check Align · tony bundleUse when prior verification was framed as a revision log and the user wants a clean, standalone restatement.
- ▌ Lean Trim Comments · tony bundleUse when existing source comments or docstrings are bloated, dense, repetitive, AI slop, or should be trimmed, debloated, and kept light.
- ▌ Weave Architecture · tony bundleWeave architecture — compare independent adversarial workers, then synthesize the best project architecture
- ▌ Weave Serene Bliss · tony bundleUse when brainstorming and refining developer-experience, documentation, or tooling UX through the Serene DX lenses.
- ▌ Align · tonyUse when prior verification was framed as a revision log and the user wants a clean, standalone restatement.
- ▌ Trim Comments · tonyUse when existing source comments or docstrings are bloated, dense, repetitive, AI slop, or should be trimmed, debloated, and kept light.
- ▌ Architecture · tonyWeave architecture — compare independent adversarial workers, then synthesize the best project architecture
- ▌ Serene Bliss · tonyUse when brainstorming and refining developer-experience, documentation, or tooling UX through the Serene DX lenses.
- ▌ Business Pr Release · tony bundleWrite the tier-3 one-page announcement — figures drawn only from the public case study, denominators attached, limitations one-liner included
- ▌ Research Study Deps · tonyUse when pulling upstream source or cloning a dependency at its installed version to study internals, read code, or create pinned worktrees.
- ▌ Pr Release · tonyWrite the tier-3 one-page announcement — figures drawn only from the public case study, denominators attached, limitations one-liner included
- ▌ Gh Rendered Markdown · tony bundleUse when Markdown must render: never hard-wrap issue-body paragraphs; fix GitHub code fences, fold logs into details, and pin source links to tags.
- ▌ Rendered Markdown · tonyUse when Markdown must render: never hard-wrap issue-body paragraphs; fix GitHub code fences, fold logs into details, and pin source links to tags.
- ▌ Package Updater Update · tony bundleUse when bringing every outdated dependency and toolchain pin current across one repository or a fleet.
- ▌ Self Improvement Apply · tonyUse when applying accepted self-improvement sweep findings to skills as individually gated edits and commits.
- ▌ Self Improvement Sweep · tony bundleUse when mining prompt history to rank skill usage, count invocations, find never-invoked skills, sweep the corpus, or improve repeated instructions.
- ▌ Tailwind Spacing Audit · tony bundleUse when Tailwind UI spacing, alignment, gaps, margins, padding, or toolbar and navbar rhythm looks inconsistent.
- ▌ Terraform Refresh Lock · tony bundleUse when refreshing Terraform or OpenTofu root lockfiles within existing constraints while preserving platform coverage.
- ▌ Update · tonyUse when bringing every outdated dependency and toolchain pin current across one repository or a fleet.
- ▌ Apply · tonyUse when applying accepted self-improvement sweep findings to skills as individually gated edits and commits.
- ▌ Sweep · tonyUse when mining prompt history to rank skill usage, count invocations, find never-invoked skills, sweep the corpus, or improve repeated instructions.
- ▌ Refresh Lock · tonyUse when refreshing Terraform or OpenTofu root lockfiles within existing constraints while preserving platform coverage.