garyld1962
- 231 skills
- 0 followers
- 15 hours ago last updated
- ▌ Spec Review Adversarial · garyld1962Adversarially review PRDs, requirements, user stories, or acceptance criteria using 1–4 lens reviewers (Skeptic, Coherence, Semantic, Devil's Advocate). The Semantic lens checks the deliverable against its sibling ONTOLOGY.md. Returns PASS/CONTESTED/REJECT.
- ▌ Project Context · garyld1962Structured interview and document shape for building a reusable BA project context artifact for Copilot sessions.
- ▌ Aers Readiness · garyld1962Reusable rubric defining the AERS (Agent-Executable Requirements Spec) readiness standard — required sections, closed-decision categories, ambiguity priorities, interaction rules, and the composite readiness score that adds the ontology verdict from _internal/ontology-readiness to the structural score. Consumed by /prd-validate, /kickoff, /execute-prd, and /spec-review-adversarial. Not user-invokable.
- ▌ Code Review Professional · garyld1962Seniority-calibrated craft grade (junior/mid/senior/staff) across 7 axes with line-cited reasoning. Use at the PR boundary after domain-review.
- ▌ Ba Knowledge Ops · garyld1962Templates and quality checks for capturing BA knowledge and evaluating AI-generated BA deliverables.
- ▌ DB Schema Review · garyld1962Database schema and migration review rubric covering ORM conventions, migration safety, indexes, relations, and exported types.
- ▌ Decision Record · garyld1962Canonical schema for decision records written under `docs/decisions/<plan-slug>/`. Every skill that writes or reads decision records cites this contract: file path, frontmatter, body sections, write triggers, read triggers, supersede mechanism, and the proliferation filter. Not user-invokable.
- ▌ Pre Flight Check · garyld1962Reusable pattern for config-dependent skills. Defines how to check for required config, detect placeholders, and halt with actionable messages. Not user-invokable — referenced by other skills.
- ▌ Pre Flight Pattern · garyld1962Reusable pattern for config-dependent prompts. Defines how to detect missing config files, identify unfilled placeholders, and halt with actionable messages before any main workflow logic runs. Auto-loaded by prompts that depend on user-editable config (e.g., configure, autonomous-development-kickoff). Defines hard and soft pre-flight modes, placeholder conventions, and the "configure first" redirect pattern.
- ▌ Review Foundations · garyld1962Legacy compatibility bridge for specialist review prompts. The primary shared review logic now lives in review-engine.
- ▌ Audit Native Overlap · garyld1962Audit this repo's custom Claude Code skills for description-level overlap with native skills (superpowers, plugins, built-ins) using the current session's live skill list as the catalog. Identifies skills whose descriptions compete with natives and recommends per-skill verdicts: tighten, cross-reference, integrate as sub-primitive, hand off, or redundant. Trigger phrases: 'audit native skill overlap', 'check overlap with native skills', 'do my custom skills compete with natives', 'native skill audit', 'evaluate skills against natives'.
- ▌ Ontology Readiness · garyld1962Reusable rubric defining ontology readiness for a requirements artifact — elicitation categories, item states, completeness and extension rules, the ONTOLOGY.md format, and a deterministic ontology score. Composed into _internal/aers-readiness; remedied interactively by /prd-create; consumed by /prd-validate, /ubiquitous-language --from-ontology, /prd-acceptance, /test-plan, and /spec-review-adversarial. Not user-invokable.
- ▌ Modernization Rubric · garyld1962Calibration rubric for the `modernize` prompt. Encodes project-shape detection, sample-read strategy, admissible moves, per-theme finding patterns, and cull criteria.
- ▌ UI Design Compliance · garyld1962UI review rubric for design-system consistency, component states, accessibility, and theme-safe implementation.
- ▌ Professional Rubric · garyld1962Grade definitions and axis descriptions for the Craft grading (seniority-calibrated) used by code-review-professional. Not user-invokable — referenced by code-review-professional.
- ▌ Execution Environment · garyld1962Detect the current shell and OS, then choose safe command routing using the user's env config. Does not hardcode any specific shell — reads routing rules from the user's env.config.md.
- ▌ Security Quick Check · garyld1962Reusable 7-point security review for diffs. Embedded by /hotfix (mandatory), /pr, /ship, /domain-review (conditional, per canonical trigger criteria). Not user-invokable.
- ▌ Code Investigation Search · garyld1962Natural-language and pattern-based code search specialist for one repository. Returns structured matches only.
- ▌ Copilot Platform Playbook · garyld1962Decision framework for designing GitHub Copilot prompts, agents, skills, and instructions in a built-in-first architecture.
- ▌ State Lifecycle · garyld1962State machine analyst — tests every valid transition, rejects every invalid one, verifies side effects of status changes.
- ▌ Professional Review Rubric · garyld1962Seniority-calibrated craft grading rubric used by code-review-professional. Copilot auto-loads this skill whenever a professional-grade code review is requested or when prompts/review/code-review-professional.prompt.md is active. Provides the authoritative 7-axis grade definitions (junior through staff) and citation requirements. Do not use this for defect triage or general code feedback — it grades craft, not correctness.
- ▌ Dependency Classification · garyld1962Reusable taxonomy for classifying code dependencies by their testability and trust boundary. Drives test strategy and audit judgments. Embedded by /test-plan, /audit-existing, and any skill that needs to reason about how a dependency should be tested or treated.
- ▌ Investigation Report Writer · garyld1962Write structured investigation matches to a versioned Markdown report under docs/code-investigations/ and update report pointers.
- ▌ Dependency Change Management · garyld1962Heuristics for auditing dependency health and planning major-version migrations in a repo-specific, evidence-based way.
- ▌ Review Disposition Governance · garyld1962Reconcile plan, code and adversarial review findings with explicit proof, terminal dispositions and human risk acceptance. Use at governed review gates and execution closeout.
- ▌ Boundary Validation · garyld1962Input validation analyst — tests required field enforcement, Zod constraint boundaries, NOT_FOUND handling, error code specificity, soft-delete behavior.
- ▌ Contract Compliance · garyld1962Requirements analyst — decomposes task description into testable requirements. Maps Zod schema fields to assertions. Verifies CRUD completeness and return type coverage.
- ▌ Integration Surface · garyld1962Integration analyst — tests router-to-service wiring, Zod schema binding, query vs mutation assignment, auth requirements, and cross-boundary contracts.
- ▌ Skills · garyld1962 bundleUnified Codex skill-management workflow. List available Savviety skills, show detail for one skill, audit local skill/agent/hook/rule/plugin coverage, check custom skills for overlap with installed native skills, or find installable skills for a requested capability. Trigger phrases: 'what skills are available', 'show skill details', 'audit skills', 'native skill overlap', 'do these skills compete with Codex skills', 'find a skill for X'.
- ▌ Code Investigation Orchestrator · garyld1962Run a cross-repository code investigation from a natural-language request or explicit pattern list and produce a versioned Markdown index.
- ▌ Code Review · garyld1962 bundleDomain-aware code review controller. Triage a diff, select review lenses, and report line-cited findings for correctness, security, tests, architecture, performance, and operability.