Claude Skills by MostAshraf

Register one new repo into an already-bootstrapped workspace, without disturbing repos already registered or re-running the full interview. USER-ENTRY — invoke only when the user explicitly runs /add-repo; never autonomously, never from a subagent (guard-enforced).

Adopt a v2.x ai-sdlc-harness workspace into v3.0 — config carries over, run history stays archived in place. USER-ENTRY and HUMAN-ONLY — invoke only when the user explicitly runs /migrate-workspace; never autonomously, never from a subagent (guard-enforced).

Regenerate the auto-generated repo map the planner grounds its plans in. USER-ENTRY — invoke only when the user explicitly runs /repo-map-refresh; never autonomously, never from a subagent (guard-enforced).

Change one config section (overrides / provider / language / repos) on an already-bootstrapped workspace, without re-running the full /init-workspace interview. USER-ENTRY — invoke only when the user explicitly runs /workspace-config; never autonomously, never from a subagent (guard-enforced).

Run tests with code coverage collection, parse the results, and present a formatted coverage report — any language, discovery-driven. Dispatches by coverage_format from .claude/context/language-config.md. Supports cobertura, jacoco, lcov, json-summary, and go-cover. Highlights pass/fail against the configured threshold (default 90%). Read-only analysis.

Master orchestrator for the AI-driven development workflow. Use when starting a new User Story / Issue implementation. Coordinates the Planner, Developer, Reviewer, and Tester agents through all 7 phases with human approval gates. Supports multiple work item providers (ADO, Jira, GitLab, GitHub, Zoho, local-markdown) and git providers (ADO, GitLab, GitHub, gh-cli, glab-cli) via provider adapters. Supports multi-repo stories with parallel developer agents across repos while maintaining sequent...

One-time workspace setup. Generates local context files (.claude/context/, git-ignored) that all workflows depend on — repo metadata, coding conventions, local repo paths, language configuration (discovered, not hard-coded), and provider configuration. Supports ADO, Jira, GitLab, GitHub, Zoho, and local-markdown as work item providers, plus GitHub CLI (gh-cli) and GitLab CLI (glab-cli) as no-MCP git providers. Run once before using /dev-workflow or /story-workflow.

Pure aggregator for workflow metrics. Reads timestamp stamps from a tracker and produces `metrics-report.md` (per-workflow) plus appends one row to workspace-level `ai/_metrics-log.csv`. No agent reasoning — deterministic data aggregation only.

Decompose an approved requirements summary into an implementation plan with atomic tasks, Mermaid diagrams, and a task tracker. Use during Phase 2 of the development workflow after requirements are fully understood.

Create a Pull Request / Merge Request after all tasks and tests are approved. Assembles PR summary from the task tracker, validates branch naming, and creates the PR/MR via the configured git provider. Links back to the work item via the work item provider. Supports ADO, GitLab, GitHub, and Jira. Used during Phase 6 of the workflow.

Composes the per-repo static security report (SAST + dependency-vuln + secret-scan). Discovery-driven tool selection from `.claude/context/language-config.md`. Severity normalisation via the per-tool map. Returns 0 (no findings ≥ medium) / 1 (findings present) / 2 (precondition unmet — tool missing).

Pull and analyse a User Story / Issue from the configured work item provider. Use when starting Phase 1 of the development workflow — ingesting requirements, parsing acceptance criteria, and surfacing clarifying questions before planning begins. Supports ADO, Jira, GitLab, GitHub, Zoho, and local-markdown via provider adapters.

Refine, analyze, improve, and groom user stories / issues with structured templates and codebase-aware technical analysis. Supports ADO, Jira, GitLab, GitHub, and local markdown files as work item sources via provider adapters. Use this skill whenever the user mentions story refinement, story grooming, story analysis, story improvement, acceptance criteria, user story quality, sprint readiness, or commands like /story-improve, /story-refine, /story-analyze, or /story-groom. Also trigger when ...

Standalone build and test validation — any language, discovery-driven. Reads .claude/context/language-config.md for the target repo and runs the configured restore, build, and test commands, parsing output via the repo's configured regex patterns. Reports results in a structured format with pass/fail status.

Structural validator for Mermaid diagrams embedded in markdown files. Verifies every CC-07.4.1 syntax requirement — HTML entity escaping, quoted subgraph titles, classDef ↔ class-reference closure, node-ID closure, stadium / parallelogram / hexagonal shape closure, comment style, and the 60-node ceiling. Returns 0 (valid) / 1 (invalid + line / column / cause) / 2 (skill precondition unmet).

Display current workflow status dashboard — read-only overview of story progress, task states, branch info, and worktree status