squirrel289
@squirrel289
Public Skills
guarding-branches
by squirrel289
"Enforce protected-branch guardrails for safe PR lifecycle, conflict resolution, and merge safety. Use when working on feature branches against protected main: before merging feature PRs, resolving merge conflicts, syncing with main, or managing work-item updates on protected branches."
auditing-backlog-dependency-graph
by squirrel289
'Perform comprehensive dependency analysis and health checks on work item backlog. Use when asked to "audit backlog", "check work item dependencies", "find missing dependencies", "analyze work items", or before major releases to validate backlog integrity. Includes bidirectional dependency analysis, orphan detection, and consistency checks.'
auditing-backlog
by squirrel289
"Run an end-to-end backlog audit by composing dependency graph validation with evidence-backed checklist validation. Use when asked to audit backlog quality before release, verify closure readiness, clean up stale completion status, or produce one cohesive backlog health report from dependency and checkbox findings."
finalizing-work-item
by squirrel289
"Complete and archive a finished work item, moving it from /backlog/ to /backlog/archive/. Use when work is tested, reviewed, merged, and ready to close. Supports: (1) Verify completion (all acceptance criteria met), (2) Record final metrics (actual_hours, completed_date, test_results), (3) Clean up feature branch, (4) Archive to history, (5) Link successor work items if needed"
updating-work-item
by squirrel289
"Update an existing work item with status changes, effort tracking, test results, and related commits. Use when progressing work, recording test results, or adjusting estimates. Supports: (1) Status transitions (proposed → ready → in-progress → ready-for-review → closed), (2) Feature branch creation and sync, (3) Automatic PR creation on ready-for-review transition, (4) Effort tracking (estimated → actual), (5) Test and commit tracking, (6) Dependency validation (all depends_on items must be closed before closing), (7) Notes with timestamps"
workspace-isolation
by squirrel289
"Use git worktrees to maintain isolated workspaces for multiple parallel work items. Ensures atomic commits, prevents state conflicts, and enables true parallelism with clean git history. Use when executing multiple work items simultaneously with complete workspace separation."
auditing-backlog-checkboxes
by squirrel289
"Audit backlog work items in closed, completed, or ready-for-review status that still contain unchecked checklist items ([ ]). Validate each unchecked item against code and test evidence, mark only fully validated items as [x], and output only a per-work-item summary status report for Tasks and Acceptance Criteria plus recommended workflow next steps. Use when asked to audit completion evidence, clean up stale checklists, or prepare work items for closure/finalization."
creating-skill
by squirrel289
Evaluate a specific use case or skill idea against memory patterns and existing skills, then provide actionable recommendations for enhancing existing skills, creating new PAX skills, project-local skills, aspects, or AGENTS.md updates. Delegates actual skill creation to skill-creator.
resolve-pr-comments
by squirrel289
Workflow skill for addressing and resolving pull request review comments systematically
executing-backlog
by squirrel289
"Orchestrate the full lifecycle of implementing backlog work items from planning through delivery, with integrated validation gating for bulk operations. Use when: (1) Asked to execute backlog, implement work items (WI-ABC), or close out a task, (2) Implementing changes across 3+ similar files, (3) Need end-to-end delivery including PR/merge. Coordinates with prevalidating-bulk-operations for routing and discover-validation-criteria for schema discovery."
creating-work-item
by squirrel289
"Create a new work item (backlog entry) with standardized structure, metadata, and conventions. Use when starting new work, proposing features, or documenting tasks. Supports: (1) Auto-numbering next available ID, (2) Frontmatter with status/priority/effort fields, (3) Goal/Background/Tasks/Deliverables/Acceptance Criteria structure, (4) Dependency tracking via wikilinks"
managing-work-items
by squirrel289
"Orchestrate the full lifecycle of work items from creation through finalization. Use when: (1) Starting new tracked work with proper structure, (2) Progressing work items through status transitions, (3) Completing and archiving finished work. Composes: creating-work-item, updating-work-item, finalizing-work-item."
performing-retro
by squirrel289
"Conduct a post-session review to organize changes into logical commits and document work. Use when: (1) Session has implemented features, fixes, or refactoring and changes are scattered across files, (2) Need to group related changes into atomic commits with conventional messages, (3) Want to create summary documentation of work completed, (4) Final validation before pushing changes. Helps transform a working session into clean git history and clear documentation."
organizing-documents-diataxis
by squirrel289
"Apply Diataxis framework to organize workflow output into documentation directories. Use to guide skill output placement: inline by default unless user requests file; rationale-heavy content to docs/architecture/; lookup tables and reference guides to docs/reference/. Avoid standalone analysis summaries in docs root. Composable into any analysis or decision-making skill."
validating-changes
by squirrel289
"Validate code changes before PR update and merge. Use when preparing to update a PR, pushing changes, or running pre-merge checks: (1) run local CI parity tests, (2) add regression tests for new failures, (3) verify all tests pass before pushing or requesting review."
prevalidating-bulk-operations
by squirrel289
"Route bulk file operations (3+ similar files) to systematic validation pattern or direct implementation. Use when: (1) Planning bulk updates, (2) Need to decide sample-validation approach, (3) Assessing validation risk in bulk operations. Evaluates file count, schema discoverability, and operation type to determine routing: PATTERN_REQUIRED, PATTERN_CONDITIONAL, or DIRECT."
migrating-git-filter-repo
by squirrel289
Move one or more subdirectories or files from one Git repository to another with git filter-repo while preserving commit history, authorship, and timestamps. Use when asked to split monorepos, migrate multiple paths between repositories, import selected files/folders into a new or existing repository, or retire source paths after verified migration.
writing-agents-md
by squirrel289
Create, review, and improve AGENTS.md or agent.md files using proven patterns from GitHub's analysis of 2,500+ repositories. Use when asked to author or refactor repository-level AGENTS.md guidance, .github/agents/*.md personas, command/runbook sections, safety boundaries, or agent templates.
comparative-decision-analysis
by squirrel289
"Comparative decision analysis workflow with mandatory discovery (including external options), criteria derivation and confirmation, explicit evidence discipline, hard-constraint gating, and deterministic scoring. Use for vendor analysis, head-to-head comparisons, competitor analysis, tool/architecture/workflow selection, and build-vs-buy decisions when you need reliable, auditable recommendations."
discovering-alternatives
by squirrel289
"Exhaustive discovery of build, buy, and hybrid options for a stated problem, using pretrained knowledge plus RAG (local memory, repo search, user-provided details, and web search). Use when you need a comprehensive alternatives list and a decision matrix with ranked options. Trigger phrases: discover alternatives, build vs buy, solution landscape, option discovery, vendor shortlist."
capturing-events
by squirrel289
Capture workspace events (file modifications, terminal commands, diagnostics, skill invocations) into local memory for pattern detection and skill evolution. Provider-agnostic design supports GitHub Copilot, Codex, Cursor, and universal workspace-only mode.
comparative-analysis
by squirrel289
Structured, repeatable, objective comparative analysis for choosing between alternatives. Use when selecting skills, tools, architectures, workflows, or build-vs-buy options and when you need explicit criteria definition, metric-based scoring, cross-platform and current-platform success scores, and a deterministic recommendation with a concise decision record.
evaluating-alternative
by squirrel289
"Evaluate one alternative against confirmed criteria in strict isolation and emit a schema-compatible independent evaluator record. Use for delegated per-option subagent scoring in comparative decision workflows."
hybrid-decision-analysis
by squirrel289
'Hybrid comparative decision workflow with mandatory discovery (including external options), criteria derivation and confirmation, explicit evidence discipline, hard-constraint gating, and deterministic scoring. Use when selecting skills, tools, architectures, workflows, vendors, or build-vs-buy options and when you need reliable, auditable recommendations.'
skill-reviewer
by squirrel289
'Evaluate and compare AI agent skills with a structured, repeatable, objective, and data-driven process. Use when asked to review one or more skills, define scoring criteria, compare alternatives, compute platform-specific success scores, or recommend whether to select, improve, extend, compose, or build a new skill.'
comparative-decision-review
by squirrel289
Structured and deterministic comparative decision workflow that combines mandatory rubric confirmation and evidence discipline with deterministic multi-platform scoring, ranking, and action rules. Use when selecting skills, tools, architectures, workflows, vendors, or build-vs-buy options and when you need explicit criteria, consistent scoring, tie-break logic, and an auditable decision record.
hybrid-decision-analysis.v1
by squirrel289
'Hybrid decision workflow that combines expert rubric design, explicit evidence capture, hard-constraint gating, scenario bakeoffs, and deterministic scoring. Use when selecting skills, tools, architectures, workflows, or build-vs-buy options and when you need consistent, reliable, and auditable recommendations.'
auto-evolution
by squirrel289
"Memory-driven self-evolution layer for Agent Skills. Captures usage patterns, learns from errors, and automatically generates reusable knowledge. Use when you want your agent to learn from experience, track skill effectiveness, or generate improvement suggestions."
skill-name
by squirrel289
"[What this skill does]. Use when [trigger scenarios]."
discover-validation-criteria
by squirrel289
'Extract validation requirements from schemas before implementing changes. Prevents trial-and-error by discovering constraints upfront.'
migrating-git-subtree
by squirrel289
Move one folder or a set of folders from one Git repository to another with git subtree while preserving commit history, authorship, and timestamps. Use when asked to migrate directories across repositories, split monorepos, import a subproject, keep syncing with git subtree split/add/merge/pull, or retire the source path after a successful import.
authoring-json-schema
by squirrel289
"Author, refactor, and maintain JSON Schema for reuse, composition, and long-term stability. Use when asked to create schemas, reduce duplication, compose schemas with $ref/allOf/oneOf/if-then-else, review schema quality, or migrate legacy draft-04+ schemas. Prefer draft-2020-12 for new authoring; treat draft-04/draft-06 as migration-only."
write-technical-rfc
by squirrel289
Create, revise, and maintain IETF-style Internet-Drafts and RFC-like technical specifications for protocols, APIs, interoperability contracts, and system behavior. Use when drafting a new spec, updating an existing draft, resolving review feedback, validating RFC 2119/8174 requirement language, or ensuring mandatory sections such as Security Considerations, IANA Considerations, and References are complete and consistent.
create-work-item
by squirrel289
"Create a new work item (backlog entry) with standardized structure, metadata, and conventions. Use when starting new work, proposing features, or documenting tasks. Supports: (1) Auto-numbering next available ID, (2) Frontmatter with status/priority/effort fields, (3) Goal/Background/Tasks/Deliverables/Acceptance Criteria structure, (4) Dependency tracking via wikilinks"
finalize-work-item
by squirrel289
"Complete and archive a finished work item, moving it from /backlog/ to /backlog/archive/. Use when work is tested, reviewed, merged, and ready to close. Supports: (1) Verify completion (all acceptance criteria met), (2) Record final metrics (actual_hours, completed_date, test_results), (3) Clean up feature branch, (4) Archive to history, (5) Link successor work items if needed"
handle-pr-feedback
by squirrel289
"Coordinate PR review loop—detect feedback severity, address minor comments automatically, revert work items if major changes needed. Use when PR has unresolved review feedback. Supports: (1) Comment triage by severity, (2) Auto-resolution of minor comments, (3) Work item reversion on blocker feedback, (4) Feedback summarization"
merge-pr
by squirrel289
Workflow skill for safely merging pull requests after verification
create-pr
by squirrel289
"Create a pull request from a feature branch with work item metadata. Use when implementation is complete, tested, and ready for review. Supports: (1) PR creation from feature branch, (2) Auto-population of PR template with work item details, (3) Linking to work item ID, (4) PR description generation from commit history"
process-pr
by squirrel289
End-to-end workflow for processing pull requests from review to merge
update-work-item
by squirrel289
"Update an existing work item with status changes, effort tracking, test results, and related commits. Use when progressing work, recording test results, or adjusting estimates. Supports: (1) Status transitions (not_started → in_progress → testing → completed), (2) Feature branch creation and sync, (3) Automatic PR creation on testing transition, (4) Effort tracking (estimated_hours → actual_hours), (5) Test and commit tracking, (6) Dependency updates and notes"
feature-branch-management
by squirrel289
"Maintain feature branches for work items. Use to create, sync (rebase), and clean up feature branches. Supports: (1) Creating local feature branches, (2) Rebasing on main, (3) Deleting merged branches locally and remotely, (4) Preparing branches for PR submission"
migrate-pip-to-uv
by squirrel289
Skill to migrate a monorepo Python project from pip/pip-tools to uv, converting requirements files to pyproject.toml and uv.lock, and updating workflows for universal, locked, multi-group dependencies.
copilot-pull-request
by squirrel289
Skill for managing GitHub pull requests and issues using Copilot's built-in PR/issue APIs. Provides structured, agent-native operations for review, comment, resolve, and merge workflows.
sequential-execution
by squirrel289
Execute dependent tasks in order where each task relies on previous results
gh-pr-review
by squirrel289
Interact with GitHub pull requests for review, comment management, and merge operations
pull-request-tool
by squirrel289
Unified skill for managing GitHub pull requests and issues. Uses Copilot's native PR/issue APIs when available, and falls back to gh-pr-review CLI otherwise. Ensures maximum compatibility and agent-native features.
parallel-execution
by squirrel289
CRITICAL skill for executing multiple runSubagent calls in a SINGLE function_calls block for true parallelism. Essential for efficient multi-task workflows, subagent coordination, and maximizing throughput.