← all publishers

Cody-Sims

@cody-sims source repo

Report this profile Claim this profile

• 25 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Code Review · cody-sims bundle

   Reviews a diff, pull request, or set of staged changes for correctness, tests, error and edge cases, security, performance, readability, and architectural fit, then reports severity-ranked, actionable findings with file and line references. Use when reviewing a PR, examining staged or unstaged changes, giving feedback on a patch, or deciding whether a change is safe to merge.
   0
   installs
2. ▌
   Shadow Dream · cody-sims

   Generates evidence-linked future-state architecture options and a reviewable proposal from Shadow observations and accepted constraints, including target states, tradeoffs, migration paths, rollback, risks, and a recommendation. Use when asked to dream, explore architecture options, compare future-state architecture, define a target state, or propose a migration path; excludes product requirements and specifications handled by requirements-and-spec-writing and implementation task planning handled by planning-and-task-breakdown.
   0
   installs
3. ▌
   Shadow Drift · cody-sims bundle

   Checks repository-owned .shadow decision graphs read-only, validates architecture drift, stale decisions, relations, evidence, indexes, and derived output, and reports aligned, drifted, stale, and unknown findings. Use when asked to check Shadow, validate .shadow, investigate architecture drift, or identify stale decisions; not for general completion verification, pull-request review, documentation maintenance, observation capture, speculative architecture, or repairing the graph.
   0
   installs
4. ▌
   Skill Creator · cody-sims bundle

   Creates, audits, and improves Agent Skills in this catalog. Captures intent, triggers, and outputs, checks the catalog for overlap, drafts positive and negative trigger prompts, writes routing descriptions, applies progressive disclosure, decides prose versus script, and validates frontmatter. Use when authoring a new SKILL.md, editing or reviewing an existing skill, fixing a skill that fails validation or fails to trigger, or when someone mentions skill authoring, skill frontmatter, or the skill catalog.
   0
   installs
5. ▌
   Shadow Observe · cody-sims bundle

   Runs bounded, read-only Shadow repository analysis to generate evidence-linked candidate architecture observations, map boundaries and dependencies, and separate verified claims, inference, and unknowns. Use when asked to run Shadow, scan architecture, generate observations, or map boundaries or dependencies for a repository-owned .shadow graph; unlike codebase-exploration, it does not orient an unfamiliar codebase or locate change sites, and it does not create decisions, propose future state, or repair drift.
   0
   installs
6. ▌
   Security Review · cody-sims bundle

   Performs threat-focused security review of a code change or component using STRIDE, checking authentication, authorization and ownership, input validation, injection, deserialization, SSRF, secrets handling, dependency and supply-chain risk, cryptography, and untrusted data including prompt injection. Use when reviewing a diff, feature, endpoint, or integration for vulnerabilities, threat modeling, or hardening before merge or release.
   0
   installs
7. ▌
   Wayfinder Planning · cody-sims bundle

   Navigates Wayfinder decision maps, fog of war, and frontier tickets for long-running ambiguous work through claim-first, one-decision-per-session replanning. Use when charting, resuming, or replanning uncertainty across sessions; not for writing a static specification, decomposing an approved spec, executing agents, Git or pull-request work, or recording durable architecture.
   0
   installs
8. ▌
   Copilot Cloud Agent · cody-sims bundle

   Launches and monitors GitHub Copilot cloud-agent tasks through supported GitHub APIs, selecting explicit models, recording task and pull-request IDs, and distinguishing hosted controls from local CLI flags. Use when starting cloud agents, running hosted loops, assigning issues to Copilot, choosing GPT-5.6 Sol, or checking cloud-agent status; do not use for local subagents or git worktree fleets.
   0
   installs
9. ▌
   Git And Pr Workflow · cody-sims bundle

   Guides Git branching, atomic commits, rebasing, resolving merge conflicts, worktrees, pull request descriptions, and safely finishing a branch. Use when creating branches, staging and committing changes, rebasing or squashing, resolving conflicts, opening or updating a pull request, or cleaning up after merge.
   0
   installs
10. ▌
    Shadow Architecture · cody-sims bundle

    Sets up and maintains a repository-owned .shadow graph, manages approved decision lifecycles and index or schema compatibility, supersedes accepted history, and renders reviewed records. Use when creating or migrating .shadow, recording approved architecture decisions, maintaining its index or schema, superseding accepted decisions, or generating derived views from reviewed records; not for discovering observations, imagining future states, or checking drift.
    0
    installs
11. ▌
    Codebase Exploration · cody-sims bundle

    Builds a focused, evidence-based map of an unfamiliar repository before modifying it, locating entry points, build, test, and lint commands, architecture boundaries, conventions, the dependency graph, and the nearest agent instructions, then reading tests to learn intended behavior and finding the smallest correct change site. Use when onboarding to a new or unfamiliar codebase, orienting before a change, or answering how a project is structured and where to edit, while staying read-only.
    0
    installs
12. ▌
    Systematic Debugging · cody-sims bundle

    Diagnoses bugs, failing tests, build failures, crashes, exceptions, stack traces, and unexpected or intermittent behavior by reproducing the failure, capturing exact error output, isolating the root cause, and fixing the cause rather than the symptom. Use when something is broken, a test or build fails, output is wrong, or a defect must be traced to its origin.
    0
    installs
13. ▌
    External Skill Review · cody-sims bundle

    Reviews third-party agent skills as untrusted code before installing or updating them, assessing provenance, license, the full file tree, scripts, hidden Unicode, network and secret access, destructive commands, tool permissions, and supply-chain risk. Use when installing, updating, vetting, or auditing an external skill, a gh skill install candidate, or any skill from an untrusted repository.
    0
    installs
14. ▌
    Test Driven Development · cody-sims bundle

    Drives implementation with the red-green-refactor cycle by writing a failing behavior test first, confirming it fails for the expected reason, implementing the minimum code to pass, then refactoring while green. Use when adding a feature, fixing a bug with a reproducible case, changing behavior, or whenever tests should precede or guide the implementation.
    0
    installs
15. ▌
    Verification Discipline · cody-sims bundle

    Audits and hardens existing tests and validation so green results are meaningful by detecting vacuous assertions, copied production logic, unbounded checks, unenforced invariants, and build impurity. Use when reviewing suspicious green tests, repairing test credibility, or hardening CI gates; do not use for ordinary test-first feature implementation or routine final gate selection.
    0
    installs
16. ▌
    Documentation Maintenance · cody-sims bundle

    Keeps README, API docs, architecture notes, ADRs, and changelogs accurate when code changes by identifying which documents a change invalidates, documenting rationale, keeping setup instructions and examples runnable, updating the changelog with user-visible changes, and removing stale content. Use when code, configuration, commands, interfaces, or behavior change and documentation must be updated, or when writing an ADR or changelog entry.
    0
    installs
17. ▌
    Parallel Worktree Delivery · cody-sims bundle

    Executes multi-agent, multi-branch git worktree delivery with ownership partitions, dependency waves, branch integration, merge conflict handling, and post-merge gates. Use when running worktree fleets, integration branches, or wave-based migrations where checkout collisions are a risk; do not use merely to identify parallel tasks or for a single small change.
    0
    installs
18. ▌
    Repository Agent Bootstrap · cody-sims bundle

    Audits and bootstraps repository-owned agent customization including AGENTS.md, repository and path-scoped instructions, custom agents, and skills, without overwriting established conventions. Use to set up, review, or maintain a repository's agent guidance, add a skill or agent, or fix overlapping, stale, or overly broad customization.
    0
    installs
19. ▌
    Agent Tool Interface Design · cody-sims bundle

    Designs and evaluates agent-facing CLI tools, code-execution adapters, MCP servers, and hybrid code-over-MCP interfaces using context, composability, state, security, and portability trade-offs. Use when reducing MCP tool sprawl, wrapping APIs for agents, choosing CLI versus MCP, or benchmarking an agent tool interface.
    0
    installs
20. ▌
    Planning And Task Breakdown · cody-sims bundle

    Decomposes an approved specification into small, ordered, dependency-aware tasks, each with explicit acceptance criteria and a verification command, and identifies which tasks are independent and safely parallelizable without overlapping writes. Use when planning multi-step work, breaking a spec or feature into tasks, sequencing dependencies, or coordinating parallel agents, after requirements are agreed and before implementation begins.
    0
    installs
21. ▌
    Runtime Smoke Fixture · cody-sims bundle

    Verifies runtime discovery, explicit invocation, and resource access. Use when exercising cross-runtime smoke infrastructure.
    0
    installs
22. ▌
    Requirements And Spec Writing · cody-sims bundle

    Turns an ambiguous or large request into an agreed written specification before implementation, covering objective, users and use cases, requirements, non-goals, interfaces and data contracts, security and privacy, error and edge cases, acceptance criteria, open questions, alternatives considered, and rollout and rollback. Use when a request is vague, scope or acceptance criteria are unclear, or the user asks for a spec, requirements, or a design before coding begins.
    0
    installs
23. ▌
    Web Research And Verification · cody-sims bundle

    Answers questions that depend on current external information by detecting the exact version in use, preferring primary and authoritative sources, corroborating with a second source, quoting and citing URLs, and separating verified fact from inference. Use when researching APIs, libraries, standards, release notes, CVEs, or any claim where accuracy and up-to-date sourcing matter, or when a source may be deprecated.
    0
    installs
24. ▌
    Verification Before Completion · cody-sims

    Requires fresh evidence before any claim that work is done, fixed, passing, working, complete, or ready. Run the relevant command now, read the actual output and exit status, inspect the produced artifact or diff, reproduce the original symptom and confirm it is gone, and distinguish verified results from assumed ones. Use before reporting completion, closing a task, or telling the user something works, and whenever tests, builds, or lint results are described as passing.
    0
    installs
25. ▌
    Refactoring And Dead Code Removal · cody-sims bundle

    Changes code structure without changing behavior and removes unused code safely by establishing a passing baseline, making one mechanical change at a time, re-running tests between steps, and proving code is dead before deleting it. Use when cleaning up, simplifying, restructuring, extracting, renaming, or deleting suspected unused code, imports, functions, or files.
    0
    installs