terryyin
@terryyin
Public Skills
dough-land
by terryyin
Dough Land lands everything in one reviewed checkout on the authorized remote trunk: commits all of its changes, reconciles and publishes them without force, and refreshes a supplied default checkout when safe. An owned worktree is retired with its branch once trunk contains its work; the default checkout stays in place. Use only on explicit invocation, such as "/dough-land", "use Dough Land", "land this worktree", or "land" for changes made on the default checkout, or when another skill's validated keep instruction links here. A casual "keep", "looks good", or approval does not invoke it. Hosted merges and pull requests are out of scope. With --process-retrospective, it also reviews the landing's own process and records supported findings in DearDough.md.
dough-bug-fixing
by terryyin
Resolves a reported discrepancy, defect, or regression by gathering expected versus actual behavior and passing the report into bounded shared execution, or by placing known larger or inconclusive work first in this project's product backlog. Use for a bug report, defect, regression, broken or unexpected behavior, a mismatch between intended and actual results, or a larger or inconclusive bug that needs a first-priority story. Do not use for the word "fix" alone, a reporting-only request, or refinement-only work.
dough-story-wrap-up
by terryyin
Closes one completed feature story, bounded retrospective correction, or context-only planless execution using available execution context. Assimilates lasting product knowledge, handles existing follow-ups and authorized product decisions, removes that work's spent plan and history so Git can recover it, and reports truthfully when required inputs are missing or unfinished. Use to wrap up a story, correction, or completed contextual instruction, close completed work, or delete spent plan and execution history. With --process-retrospective, it also reviews the wrap-up's own process and records supported findings in DearDough.md.
dough-execute-plan
by terryyin
Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with independent refactoring, delivery, and asynchronous CI repair. Use to execute a plan, run slices, execute a canonical story when the caller explicitly skips slice planning, or execute a small instruction from context without a story or plan. Also admits an accepted mission that no backlog list holds, such as a standalone review, investigation, or maintenance request, into Taken before its work starts. Does not decide story scope or quick-path eligibility. --trunk selects Trunk Mode; omitted mode keeps Story Branch Mode. --one-shot keeps selected trivial work's result for review; --auto-land lands it. --skip-retro skips the automatic planned-execution retrospective. --replan and --no-replan choose whether an oversized attempt may continue through planning.
dough-execute-plan
by terryyin
Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with independent refactoring, delivery, and asynchronous CI repair. Use to execute a plan, run slices, execute a canonical story when the caller explicitly skips slice planning, or execute a small instruction from context without a story or plan. Also admits an accepted mission that no backlog list holds, such as a standalone review, investigation, or maintenance request, into Taken before its work starts. Does not decide story scope or quick-path eligibility. --trunk selects Trunk Mode; omitted mode keeps Story Branch Mode. --one-shot keeps selected trivial work's result for review; --auto-land lands it. --skip-retro skips the automatic planned-execution retrospective. --replan and --no-replan choose whether an oversized attempt may continue through planning.
dough-land
by terryyin
Dough Land lands everything in one reviewed checkout on the authorized remote trunk: commits all of its changes, reconciles and publishes them without force, and refreshes a supplied default checkout when safe. An owned worktree is retired with its branch once trunk contains its work; the default checkout stays in place. Use only on explicit invocation, such as "/dough-land", "use Dough Land", "land this worktree", or "land" for changes made on the default checkout, or when another skill's validated keep instruction links here. A casual "keep", "looks good", or approval does not invoke it. Hosted merges and pull requests are out of scope. With --process-retrospective, it also reviews the landing's own process and records supported findings in DearDough.md.
dough-bug-fixing
by terryyin
Resolves a reported discrepancy, defect, or regression by gathering expected versus actual behavior and passing the report into bounded shared execution, or by placing known larger or inconclusive work first in this project's product backlog. Use for a bug report, defect, regression, broken or unexpected behavior, a mismatch between intended and actual results, or a larger or inconclusive bug that needs a first-priority story. Do not use for the word "fix" alone, a reporting-only request, or refinement-only work.
dough-story-wrap-up
by terryyin
Closes one completed feature story, bounded retrospective correction, or context-only planless execution using available execution context. Assimilates lasting product knowledge, handles existing follow-ups and authorized product decisions, removes that work's spent plan and history so Git can recover it, and reports truthfully when required inputs are missing or unfinished. Use to wrap up a story, correction, or completed contextual instruction, close completed work, or delete spent plan and execution history. With --process-retrospective, it also reviews the wrap-up's own process and records supported findings in DearDough.md.
dough-story-refinement
by terryyin
Clarifies selected stories before execution planning by establishing goal, scope, and key examples in each story's seed, distinguishing promises from rejection constraints. Adds UI or architectural detail only when needed. Continues a ready story into slice planning in the same workspace; --refine-only stops at the refined story. --one-shot refines a queued story without publishing an assignment and keeps the result for review, or lands it with --auto-land. Use for selected-story refinement, not broad problem decomposition, candidate selection, or slice sizing.
dough-story-refinement
by terryyin
Clarifies selected stories before execution planning by establishing goal, scope, and key examples in each story's seed, distinguishing promises from rejection constraints. Adds UI or architectural detail only when needed. Continues a ready story into slice planning in the same workspace; --refine-only stops at the refined story. --one-shot refines a queued story without publishing an assignment and keeps the result for review, or lands it with --auto-land. Use for selected-story refinement, not broad problem decomposition, candidate selection, or slice sizing.
dough-slice-planning
by terryyin
Plans one understood, bounded story, retrospective correction, or remaining work from an understood instruction as an executable sequence of Behavior/Structure slices with outside-in proof and safe stopping points. Use when a selected story is ready for implementation planning, an execution retrospective has one bounded correction to plan, or authorized remaining work from a sufficient instruction needs an ordinary plan. Stays within the triggering instruction's execution authority: finish after writing and reporting the plan unless that instruction explicitly also requests execution. Invokes slice-plan refinement when remaining plan concerns can be resolved within the understood outcome, then reports remaining concerns or a limited no-concerns finding and records readiness through the shared preparation procedure without granting Take or execution.
dough-slice-plan-refinement
by terryyin
Refines an executable plan in place into proportionate, proof-owned Behavior/Structure slices. Use during or after dough-slice-planning when boundaries fragment cohesive work, combine independent concerns, accumulate special cases, or overrun. Creates no new plan and preserves the selected story or bounded correction outcome. After rewriting the plan, reassess readiness through the shared preparation procedure without granting Take or execution.
dough-product-backlog
by terryyin
Maintains and reprioritizes a product backlog list of canonical story or bounded-correction references, and records necessary blocking story dependencies in canonical homes. Use to add, take, reorder, or complete backlog items, adopt or repair the done catalog beside them, record or inspect a justified prerequisite, or resolve product backlog merge conflicts. Excludes classroom and workshop exercise backlogs.
dough-execution-retrospective
by terryyin
Reviews planned, completed planless quick, or quick-to-planned execution against original intent, aggregate commits, current whole-product architecture, and tests, including after cleanup. Process review is opt-in: it runs only when the project sets skipProcessRetrospective: false or the request asks to include it, and needs available agent history. Use for execution retrospective, product review, or backlog recommendations from current/supplied history. Supports --skip-process and --skip-product. May plan corrections, record process findings in DearDough.md (500-line warning, 1,000-line ceiling, recoverable lower-priority replacement on overflow), and recommend product work; never implements findings.
dough-update
by terryyin
Apply the latest released Open Dough guidance from this project's recorded source, or from a supplied repository URL on first install. Use when the user asks to update Open Dough or invokes dough-update.
dough-update
by terryyin
Apply the latest released Open Dough guidance from this project's recorded source, or from a supplied repository URL on first install. Use when the user asks to update Open Dough or invokes dough-update.
dough-manual-testing
by terryyin
Plans bounded manual or exploratory observation of requested product behavior when the developer explicitly requests manual testing, exploratory testing, or an active plan slice requires it. Covers web, CLI, API, desktop, or combined surfaces. Does not run proactively or replace required automated tests.
dough-manual-testing
by terryyin
Plans bounded manual or exploratory observation of requested product behavior when the developer explicitly requests manual testing, exploratory testing, or an active plan slice requires it. Covers web, CLI, API, desktop, or combined surfaces. Does not run proactively or replace required automated tests.
dough-test-optimization
by terryyin
Speeds up local test feedback through profiling and measured experiments across related tests. Use to optimize slow tests or test-suite performance. Preserves behavioral coverage and confidence while pursuing fewer redundant cases, less code, and cleaner design. With --resolve, triages recorded candidates without profiling or optimizing.
release-version
by terryyin
Prepare or finalize an Open Dough source release with VERSION, CHANGELOG.md, and a matching Git tag. Use when the user asks to release-version, prepare or finalize a release, write VERSION or CHANGELOG, or create a version tag.
dough-story-decomposition
by terryyin
Challenges and decomposes a broad product problem into ordered Valuable/Visible/Vertical stories with rough effort hypotheses. Use when the parent problem, candidate stories, or learning priority are unresolved. Writes one non-executable seed.
triage-retrospective-findings
by terryyin
Ranks reconciled Open Dough process findings with evidence-linked follow-up proposals. After explicit developer selection, records and queues one evaluable story with reciprocal finding links, or records defer, evidence-request, or no-change disposition. On rereview, surfaces existing queued or Taken work instead of duplicating it. Use to triage or prioritize findings, recommend follow-up, rereview linked findings, queue a selected response, defer, request evidence, or record no-change.
dough-post-change-refactor
by terryyin
Refactors concepts implicated by the current uncommitted change before commit. Includes untouched representations and orchestration needed for coherence, stops before unapproved cross-subsystem refactoring or disputed plan behavior, and tests only after edits. Use after a slice, for post-change refactoring, or to clean up the current change.
reconcile-retrospective-findings
by terryyin
Reconciles supplied retrospective findings under stable internal Open Dough codes (ODF-NNN) and retains their evidence for later triage. Use when a maintainer asks to reconcile findings, retain supplied DearDough feedback, recommend a rename, assign an ODF code, or match source and internal finding names.