Normalizes structured acceptance profiles from seed prompts into deterministic milestone/gate artifacts and traceable task metadata. This skill should be used when a goal prompt includes an ACCEPTANCEPROFILE block or when research stages need reusable objective milestone criteria.
EnglishOpinionated architecture sanity check: identify missing decisions, high-risk failure modes, and the simplest viable architecture with operability/security baked in.
EnglishForces hard pushback on plans/specs by surfacing brittle assumptions, failure modes, and a safer build sequence, with an explicit output contract.
EnglishEvaluate the repo for security risks, correctness hazards, complexity hotspots, and documentation gaps, then produce a prioritized audit report and doc-only improvement plan. Use for repo reviews, security triage, onboarding/documentation passes, and "what should we clean up first" assessments where behavior must not change or violate guardrails.
EnglishBehavior-preserving code cleanup and compaction with strict verification gates. Only runs when the repo has a runnable build/test command set. Refactors safely, removes dead code, reduces duplication, and hardens scripts without introducing breakage or violating guardrails.
EnglishEnforces Millrace research-loop spec quality for GoalSpec and incident fixspec artifacts using verifiable requirements, ambiguity bans, and deterministic traceability. This skill should be used when Clarify, Critic, Designer, Taskmaster, Taskaudit, or Incident Resolve stages create, interrogate, or decompose specs under agents/specs/ and agents/ideas/specs/.
EnglishWrites a single, repo-accurate task card in agents/tasks.md (or queues one in agents/tasksbacklog.md) that is executable by the Builder/QA cycles without interpretation. Includes explicit metadata (Complexity/Assigned skills/Tags/Gates) so the pipeline is deterministic and auditable.
English
AGENT SKILLS ATLASIncludes Acceptance Profile Contract, Advisor Architecture Sanity Check, Advisor Plan Pushback, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Acceptance Profile Contract
Normalizes structured acceptance profiles from seed prompts into deterministic milestone/gate artifacts and traceable task metadata. This skill should be used when a goal prompt includes an ACCEPTANCEPROFILE block or when research stages need reusable objective milestone criteria.
Advisor Architecture Sanity Check
Opinionated architecture sanity check: identify missing decisions, high-risk failure modes, and the simplest viable architecture with operability/security baked in.
Advisor Plan Pushback
Forces hard pushback on plans/specs by surfacing brittle assumptions, failure modes, and a safer build sequence, with an explicit output contract.
Codebase Audit Doc
Evaluate the repo for security risks, correctness hazards, complexity hotspots, and documentation gaps, then produce a prioritized audit report and doc-only improvement plan. Use for repo reviews, security triage, onboarding/documentation passes, and "what should we clean up first" assessments where behavior must not change or violate guardrails.
Codebase Safe Cleanup
Behavior-preserving code cleanup and compaction with strict verification gates. Only runs when the repo has a runnable build/test command set. Refactors safely, removes dead code, reduces duplication, and hardens scripts without introducing breakage or violating guardrails.
Spec Writing Research Core
Enforces Millrace research-loop spec quality for GoalSpec and incident fixspec artifacts using verifiable requirements, ambiguity bans, and deterministic traceability. This skill should be used when Clarify, Critic, Designer, Taskmaster, Taskaudit, or Incident Resolve stages create, interrogate, or decompose specs under agents/specs/ and agents/ideas/specs/.
Task Card Authoring Repo Exact
Writes a single, repo-accurate task card in agents/tasks.md (or queues one in agents/tasksbacklog.md) that is executable by the Builder/QA cycles without interpretation. Includes explicit metadata (Complexity/Assigned skills/Tags/Gates) so the pipeline is deterministic and auditable.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Acceptance Profile Contract skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.