#SkillRepo stars
- 21793Planner Consolidate WpsTalonT-Org/AutoSkillitAnalyze WP complexity per phase and emit consolidation group manifests for trivial WP merging (L1+L0 pattern)5
- 21794Planner Elaborate AssignmentsTalonT-Org/AutoSkillitElaborate all assignments for a target phase via parallel L0 subagents. One invocation per phase; spawns one L0 per assignment concurrently. (Pass 2 loop body)5
- 21795Planner Elaborate PhaseTalonT-Org/AutoSkillitElaborate a single phase into a full result, parallel-safe — receives plan snapshot + target phase ID5
- 21796Planner Elaborate WpsTalonT-Org/AutoSkillitElaborate all work packages for a target phase via parallel L0 subagents. One invocation per phase; spawns one L0 per WP concurrently. (Pass 3 loop body)5
- 21797Planner Extract DomainTalonT-Org/AutoSkillitExtract domain knowledge and naming conventions for planning context5
- 21798Planner Generate PhasesTalonT-Org/AutoSkillitGenerate high-level phases from project analysis (Pass 1 entry point)5
- 21799Planner Reconcile DepsTalonT-Org/AutoSkillitPost-Pass-3 global dependency DAG construction — detects implicit dependencies individual WP sessions could not see5
- 21800Planner RefineTalonT-Org/AutoSkillitTargeted fix of validate_plan findings — re-elaboration, duplicate resolution, dependency corrections5
- 21801Planner Refine AssignmentsTalonT-Org/AutoSkillitRefine elaborated assignments for a single phase via parallel L0 subagents (L1+L0 pattern), using per-phase context file with peer_summaries for cross-phase visibility5
- 21802Planner Refine PhasesTalonT-Org/AutoSkillitRefine elaborated phases with cross-phase visibility via parallel L0 subagents (L1+L0 pattern)5
- 21803Planner Refine WpsTalonT-Org/AutoSkillitRefine elaborated work packages with cross-phase visibility via per-phase L0 subagents (L1+L0 pattern)5
- 21804Planner Validate Task AlignmentTalonT-Org/AutoSkillitValidate that plan phases and WPs align with the stated task5
- 21805Prepare IssueTalonT-Org/AutoSkillitCreate a single GitHub issue and immediately triage it — dedup check, classification (recipe:implementation or recipe:remediation), mixed-concern detection, and label application. Use when user says "open an issue", "create an issue", "file an issue", or "file a bug". The user-facing counterpart to report_bug.5
- 21806Prepare PRTalonT-Org/AutoSkillitPreparation executor for pull-request metadata. ALWAYS invoke this skill when instructed to prepare PR metadata. Do not read plans or classify files directly — use this skill first to load the preparation workflow.5
- 21807Prepare Research PRTalonT-Org/AutoSkillitReads a research report and experiment plan, synthesizes a recommendation, selects 1-2 exp-lens lenses, writes a context file per lens, and writes a PR prep file. Does NOT open a PR. Part 1 of 3 in the decomposed research-PR flow.5
- 21808Process IssuesTalonT-Org/AutoSkillitExecute recipe sessions batch-by-batch for triaged GitHub issues. Reads the triage-issues output manifest, processes each batch sequentially, and launches the appropriate recipe for each issue. Use when user says "process issues", "run issues", or "execute pipeline for issues".5
- 21809Promote to MainTalonT-Org/AutoSkillitPromote integration to main with comprehensive changelog and PR creation. Use when user says "promote to main", "open promotion PR", "integration to main", or "create release PR to main". Runs pre-flight checks, change inventory, architecture diagrams, and creates a rich PR with release notes and traceability.5
- 21810RectifyTalonT-Org/AutoSkillitDeep investigation of test gaps and architectural weaknesses following an investigation, then devise a plan for architectural immunity rather than direct fixes. Use when user says "rectify", "rectify this", or wants to address root architectural causes after an investigation.5
- 21811Reload SessionTalonT-Org/AutoSkillitReload the current AutoSkillit session — signals the parent process to re-launch with the full wrapper environment and resume the conversation.5
- 21812Render RecipeTalonT-Org/AutoSkillitRender a recipe YAML as a compact visual overview with ASCII flow diagram and input table. Only invoke when the user explicitly says "render recipe" or "/render-recipe".5
- 21813Report BugTalonT-Org/AutoSkillitInvestigate a bug from provided error context, write a structured markdown report to the given path, and output a deduplication fingerprint. Lightweight — no parallel subagents.5
- 21814Resolve Claims ReviewTalonT-Org/AutoSkillitFetch claim findings from audit-claims, run citation-aware intent validation (ACCEPT/REJECT/DISCUSS), apply targeted citation fixes, escalate findings requiring experiment reruns, and post inline replies.5
- 21815Resolve Design ReviewTalonT-Org/AutoSkillitTriage STOP verdict findings from review-design, classifying each as ADDRESSABLE/STRUCTURAL/DISCUSS using parallel subagents. If any are ADDRESSABLE or DISCUSS, generate revision_guidance and emit resolution=revised. If all are STRUCTURAL, emit resolution=failed for terminal stop.5
- 21816Resolve FailuresTalonT-Org/AutoSkillitFailure resolution executor. ALWAYS invoke this skill when instructed to fix test failures in a worktree. Do not read test output or edit code directly — use this skill first to load the failure resolution workflow.5
- 21817Resolve Merge ConflictsTalonT-Org/AutoSkillitGoal-aware resolution of rebase conflicts when merging a conflict-resolution worktree back into the integration branch. Analyzes the intent of each side of a conflict, resolves it in-place when confidence is HIGH or MEDIUM, and escalates when LOW.5
- 21818Resolve Research ReviewTalonT-Org/AutoSkillitFetch PR review comments from review-research-pr, run research-aware intent validation (ACCEPT/REJECT/DISCUSS), apply targeted fixes, escalate unrerunnable findings, and post inline replies. Exit 0 drives recipe re_push_research; exit non-zero halts the cycle.5
- 21819Resolve ReviewTalonT-Org/AutoSkillitFetch PR review comments, run intent validation (ACCEPT/REJECT/DISCUSS) before applying fixes, and post inline replies. MCP-only — used exclusively by recipe orchestration via run_skill after review_pr reports changes_requested or needs_human verdict.5
- 21820Retry WorktreeTalonT-Org/AutoSkillitWorktree retry executor. ALWAYS invoke this skill when instructed to continue or retry an implementation in an existing worktree. Do not resume editing files directly — use this skill first to load the retry workflow.5
- 21821Review ApproachTalonT-Org/AutoSkillitResearch modern solutions and approaches for issues or features proposed in a report or plan. Use when user says "review approach", "review approaches", "research solutions", or wants external validation of a proposed direction.5
- 21822Review DesignTalonT-Org/AutoSkillitValidate an experiment plan before execution using triage-first, fail-fast dimensional analysis with an adversarial red-team. Emits verdict (GO/REVISE/STOP), experiment_type, evaluation_dashboard, and revision_guidance.5
- 21823Review PRTalonT-Org/AutoSkillitAutomated diff-scoped PR code review using parallel audit subagents. Posts inline GitHub review comments and submits a summary verdict. Use after a PR is opened to gate CI on review approval.5
- 21824Review PromotionTalonT-Org/AutoSkillitReviewer-facing deep analysis of an integration-to-main promotion. Performs domain risk scoring, breaking change audit, regression risk assessment, test coverage delta, and cross-domain dependency analysis. Use when you want a reviewer's guide before approving a promotion PR.5
- 21825Review Research PRTalonT-Org/AutoSkillitAutomated diff-scoped research PR review using parallel audit subagents aligned to research quality dimensions. Posts inline GitHub review comments and submits a summary verdict. Use after a research PR is opened to gate on review approval.5
- 21826Run ExperimentTalonT-Org/AutoSkillitExecute a designed experiment in a worktree and collect structured results. Supports --adjust retry mode.5
- 21827ScopeTalonT-Org/AutoSkillitSurvey codebase and web sources to build a known/unknown matrix for a research question. Phase 1 of the research recipe.5
- 21828Setup EnvironmentTalonT-Org/AutoSkillitPre-flight environment gate for the research recipe. Reads the experiment plan, detects the required environment type, builds a Docker image or creates a host micromamba environment, and emits an env_mode verdict consumed by downstream steps.5
- 21829Setup ProjectTalonT-Org/AutoSkillitExplore a target project and generate tailored recipes and config through an interactive workflow. Use when user wants to onboard a new project to AutoSkillit, says "setup project", or wants a starting point config.5
- 21830Smoke TaskTalonT-Org/AutoSkillitExecute an arbitrary prose task as a headless Claude session. For smoke-test pipeline use only.5
- 21831Stage DataTalonT-Org/AutoSkillitPre-flight resource gate for the research recipe. Reads the experiment plan's data_manifest, checks disk space and network connectivity for external/gitignored entries, creates data directory structure, and emits a PASS/WARN/FAIL feasibility verdict.5
- 21832Triage IssuesTalonT-Org/AutoSkillitAnalyze open GitHub issues and produce a sequenced implementation plan — grouping issues into parallel batches, ordering those batches, and tagging each issue with its recipe route. Use when user says "triage issues", "prioritize issues", or "plan issue order".5
- 21833Update ArchitectureTalonT-Org/AutoSkillitUpdate architecture markdown files. Use when user says "update architecture", "update arch docs", "sync architecture", or mentions updating architecture documentation.5
- 21834Update ReqsTalonT-Org/AutoSkillitAdd or update functional requirement documents in docs/requirements/5
- 21835Update SpecsTalonT-Org/AutoSkillitAdd or update functional specification documents. Use when user says "update specs", "update specifications", "sync specs", or wants to maintain specification documents that describe what the software must do.5
- 21836Validate AuditTalonT-Org/AutoSkillitValidate audit findings from audit-arch, audit-tests, or audit-cohesion against actual code, git history, and design intent using 9–10 parallel subagents. Removes contested findings, documents exceptions, adjusts severities. Use when user says "validate audit", "validate findings", "validate report", or "check audit results".5
- 21837Validate AuditTalonT-Org/AutoSkillitValidate audit findings from audit-arch, audit-tests, audit-cohesion, audit-feature-gates, audit-docs, or audit-review-decisions against actual code, git history, and design intent using 9–10 parallel subagents. Removes contested findings, documents exceptions, adjusts severities. Use when user says "validate audit", "validate findings", "validate report", or "check audit results".5
- 21838Validate Review DecisionsTalonT-Org/AutoSkillitValidate review-decisions audit findings with mandatory intent analysis and seven evidence-gathering rules. Adds docstring-as-contract recognition, deliberate-change detection, test-as-intent-signal, consumer-impact verification, architectural feasibility checks, behavioral simulation, and symmetry-as-design recognition to the standard validation workflow. Use when validating reports from audit-review-decisions specifically.5
- 21839Validate Test AuditTalonT-Org/AutoSkillitValidate test audit findings with test-domain semantic rules and intent analysis. Adds import-path-as-contract recognition, precondition-as-assertion detection, provenance verification, split-era lifecycle awareness, and deletion-vs-improvement distinction to the standard validation workflow. Use when validating reports from audit-tests specifically.5
- 21840Verify DiagTalonT-Org/AutoSkillitVerify an architecture diagram against the actual codebase. Checks component existence, connection accuracy, and read/write directionality. Use when user says "verify diagram", "verify diag", "check diagram", or wants to validate diagram accuracy.5