smaqit-extensions

Creates a test playbook for a task — `task.test-create [id]`, `test.create [id]`, or any request to generate an E2E test runbook from a task file. Produces a complete, executable playbook under `.smaqit/user-testing/tests/` with build-gate, deploy-gate, and live-service E2E validation where the task touches live services.

End session by documenting the entire conversation. Use at session completion to create history entries.

Bootstrap or refresh a smaqit project by inferentially synchronizing Codex, Claude Code, and GitHub Copilot project instructions around a canonical root AGENTS.md, then creating the base project directories (docs/, assets/, assets/raw/). Use when the user asks to start, initialize, reinitialize, or refresh a smaqit project.

Execute git operations (commit, tag, push) for local releases

Produces a structured parity assessment comparing any two software systems — frameworks, libraries, platforms, or products. Identifies the current project from session context, studies the target system, checks domain compatibility, then outputs validated Mermaid diagrams and a written ASSESSMENT.md. Trigger phrase: `parity.assess <name>`.

Manages a live Q&A knowledge manifest at `.smaqit/compendium.md`. Invoked when the user says `list compendium`, `fetch from compendium [query]`, `update compendium [question]`, or `remove from compendium [question]`. Lists all Q&A entries grouped by category, semantically searches for relevant entries, upserts a Q&A pair (add or update), or removes an entry after confirmation.

Use this skill when the user asks to run a diagnostic or scan the project for gaps or requests a check on security posture, test coverage, logging setup, monitoring coverage, provisioning, or CI/CD pipelines. Scans six domains (Testing, Security, Logging, Monitoring, Provisioning, CI/CD) using a deterministic filesystem inventory and domain checklists, then produces a prioritised finding report at `.smaqit/reports/diagnose-YYYY-MM-DD.md`. Supports `--tasks` to generate smaqit tasks for new gaps, domain scoping (e.g. `project.diagnose security,logging`), and `--refresh` to overwrite an existing same-day report.

Manages a per-project glossary at `.smaqit/glossary.md`. Invoked when the user says `list glossary`, `fetch from glossary [term]`, `update glossary [term]`, or `remove from glossary [term]`. Lists all terms by category, retrieves a specific term, upserts a term (add or update), or removes a term after confirmation.

Generates a live project dashboard from the current codebase state and writes it to `.smaqit/project-recap.md`. Invoke with `project.recap` to generate the dashboard, or `project.recap --refresh` to force re-scan even if the output file already exists.

Builds and maintains a documentation topology map for the current project, identifying the full tech stack and discovering section-level documentation URLs across multiple platforms (GitHub, official docs, ReadTheDocs, pkg.go.dev, npm, PyPI, and more). Writes a persistent map to `.smaqit/references/project-research.md`; adds task-specific annotation when a task is active. Invoke when the user asks to research project dependencies, build or refresh the documentation map, or find documentation for project tools and libraries.

Collect changes, assess severity, and suggest next version for a release

Obtain approval for suggested version (auto-confirm or interactive)

Execute git operations for PR-based releases (commit, push, and enforce the post-merge automation PR title)

Validate git state and prepare all files (CHANGELOG.md, version files) for release

Critical assessment skill for handling ambiguous requirements, conflicting inputs, and insufficient detail in complex planning scenarios. Provides approval gate with iterative refinement to prevent wasted execution on poor-quality inputs. Invoke when user explicitly requests assessment using words "assess" or "assessment" or when requirements are ambiguous, conflicting, or underspecified.

Summarize session progress as a structured table of accomplished and pending steps. Invoke when the user asks for a "recap of the session", "review of the session", or "progress on the session".

Start a new chat with full project context. Use when beginning a session to load README, recent history, and task planning.

Generate a succinct title for the current session based on work accomplished. Use when finishing sessions to create history file titles.

Mark a task as completed by updating a task's status. Verify its acceptance criteria and record state in PLANNING.md. Use when marking a task as done — whether just implemented, retroactively closing completed work, or responding to a status update request. Follow the steps and mode-specific rules to ensure proper task management.

Create a new task with auto-numbering. Use when creating new tasks to track work.

Show current active tasks. Use to view task overview from planning file.

Plans work before implementation or task creation. Given a task ID or a free-form idea, assesses complexity, resolves design gaps via discovery and Q&A, and produces an approved execution plan. Offers context-appropriate next steps: create a new task, start an existing one, or update the task file with resolved decisions.

Use when a session is ending and you need to identify work committed during the session that has no corresponding smaqit task. Scans session commits and modified files, cross-references against PLANNING.md active tasks, and surfaces candidates for retroactive task creation. Invoke as part of or immediately after smaqit.session-finish to prevent committed fixes, features, or infrastructure changes from going untracked.

Start working on a task. Supports autonomous mode (AI completes) or assisted mode (user approval required). Use when beginning work on tasks to set proper workflow.

Use this skill when finalizing a testing session — verify the playbook's pass/fail criteria against collected execution evidence, generate a standardized test report at `.smaqit/user-testing/YYYY-MM-DD_test-report.md`, and present the result. Use when the user invokes `test.complete`, asks to finalize or wrap up a testing session, or requests a test report. Mirrors `smaqit.task-complete`: the agent executes tests, the user invokes this skill to produce the report.

Start testing session with focused context. Use when beginning test workflows with the user-testing agent.

Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Pre-implementation gate that searches upstream GitHub repositories for open bugs and regressions relevant to a task. Resolves tool names to owner/repo pairs from GitHub URLs in the project research map, falling back to the GitHub REST API via curl. Classifies results as Blocking (halts smaqit.task-start and requires user direction), Advisory (surfaced but non-blocking), Historical (closed issues with workarounds), or Clear. Invoked automatically as step 2a of smaqit.task-start; also invokable standalone as `task.triage [id]`.

Use this skill when the user asks to run a diagnostic or scan the project for gaps or requests a check on security posture, test coverage, logging setup, monitoring coverage, provisioning, or CI/CD pipelines. Scans six domains (Testing, Security, Logging, Monitoring, Provisioning, CI/CD) using a deterministic filesystem inventory and domain checklists, then produces a prioritised finding report at `.smaqit/reports/diagnose-YYYY-MM-DD.md`. Supports `--tasks` to generate smaqit tasks for new gaps, domain scoping (e.g. `project.diagnose security,logging`), and `--refresh` to overwrite an existing same-day report.

Use this skill when the user asks to run a diagnostic or scan the project for gaps or requests a check on security posture, test coverage, logging setup, monitoring coverage, provisioning, or CI/CD pipelines. Scans six domains (Testing, Security, Logging, Monitoring, Provisioning, CI/CD) using a deterministic filesystem inventory and domain checklists, then produces a prioritised finding report at `.smaqit/reports/diagnose-YYYY-MM-DD.md`. Supports `--tasks` to generate smaqit tasks for new gaps, domain scoping (e.g. `project.diagnose security,logging`), and `--refresh` to overwrite an existing same-day report.

Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Extracts text from a PDF file, writes a sidecar .extracted.txt file, reads it, and continues with the caller's original goal. Use when the user references a .pdf file path and requests any content-based action: review, summarize, analyze, benchmark extraction, or similar.

Execute git operations for PR-based releases (commit, push, and enforce the post-merge automation PR title)

Execute git operations for PR-based releases (commit, push, and enforce the post-merge automation PR title)