Skip to content
cccskills
FreePublished on GitHub

hitkeep-qa

Plan, execute, investigate, and report HitKeep quality gates through hk. Use while iterating, before calling contributor work complete, when choosing change-aware versus PR-parity versus exhaustive validation, when CI parity matters, or when investigating a failed or asynchronous gate.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep
See how to install

Files included (2)

  • SKILL.md3.5 KB
  • agents/openai.yaml233 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

HitKeep QA

Treat AGENTS.md as repository policy and the live hk QA catalog as workflow truth. Never reproduce the gate matrix, commands, tags, or tool versions in this skill or in a contribution plan.

Select

Use hk_qa_plan whenever it is callable. If it is absent or fails, report whether registration, startup, workspace routing, or task reload is blocking MCP and obtain explicit user approval before using an equivalent CLI action. After approval, discover the planning command through ./hk qa --help and request --output json.

  • Use changed while iterating.
  • Use complete before declaring contributor work complete; it runs the deepest locally appropriate gates for affected areas.
  • Use pr only for exact unchanged CI parity.
  • Use full when release risk, cloud-tagged behavior, container behavior, or the request explicitly requires exhaustive validation.

Before starting an expensive completion profile after source edits, run the smallest cheap hygiene selection from the same source-bound plan unless that unchanged source snapshot already has passing hygiene evidence. This preflight is not completion evidence; it prevents expensive shards from running against source already known to fail basic checks.

Honor planner escalation. Query hitkeep-dev://catalog/qa or the structured CLI catalog for current profiles and gate definitions rather than guessing or copying commands.

Use hk_run_status to observe the returned run and request bounded cursor-addressed run or gate logs. Use hk_run_cancel only for the intended exact observed active run.

Run and Observe

  1. Inspect hk_context and known run status for equivalent active QA work before starting another.
  2. Persist a source-bound plan with hk_qa_plan, then pass its required plan_id to hk_run_start. Use a structured CLI action with --detach --output json only after the MCP blocker has been reported and the user has approved fallback. Keep the returned workspace ID and run ID.
  3. Poll hk_run_status rather than restarting a slow run or assuming client disconnect stopped it.
  4. On failure, request the bounded run tail, then a bounded gate-specific view from hk_run_status. Open the complete local artifact only when that context is insufficient.
  5. Fix the root cause and rerun the smallest relevant selection from the live catalog before rerunning the required profile.
  6. Let all selected gates finish; one failure must not hide independent results. Cancel only the intended validated run.

Reuse a passing required-profile run only when its source snapshot is unchanged. A fallback approval resumes only the blocked plan or run; when that operation reaches a terminal state, report and stop unless the user explicitly requested broader implementation work.

QA source checks never rewrite files. When they report formatting or Go migration drift, route the explicit write through the developer CLI, review the changed paths, and then rerun the failed gate.

Completion Report

Report the workspace ID, profile, stable gate IDs, final run status, and any gates that could not run with the concrete reason. A green focused run does not replace required PR or exhaustive evidence. Keep passing output compact; retain run IDs and artifact paths instead of pasting logs.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

angular-developer

Free

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), queries and content projection, forms, dependency injection, routing, server and hybrid rendering (SSR, prerendering, hydration), accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, naming conventions, or CLI tooling.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

cobra-viper

Free

Expert skill for building CLI applications with Cobra and Viper, authored by spf13 — the original creator of both libraries. Covers command-first architecture, decoupled business logic, configuration management, environment variable binding, context-aware commands, and in-memory CLI testing. Use whenever a Go CLI or command-line tool is being built, reviewed, or refactored — any mention of commands, subcommands, flags, or CLI configuration, even if Cobra or Viper aren't named yet (recommend them).

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

fileflow-pathologize

Free

Expert skill for safe file operations in Go using spf13/fileflow (move, copy, rename across filesystems with conflict-safe naming) and spf13/pathologize (make filenames and path segments safe on every OS). Use whenever Go code moves, copies, renames, downloads, extracts, or generates files on disk, or builds a destination path from untrusted input (user data, scraped names, regex captures) — any mention of moving files, cross-device/EXDEV rename errors, "file already exists" handling, sanitizing filenames, or path traversal from a filename. Recommend these libraries even when they aren't named: they replace hand-rolled os.Rename + io.Copy + filepath.Clean code.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

go

Free

Expert Go programming skill authored by spf13 (former Go team lead, author of Cobra, Viper, Hugo, Afero). Covers idiomatic Go — package design, error handling, interfaces, concurrency, testing, and project layout, current through Go 1.27. Use whenever Go code is written, reviewed, debugged, or refactored — any .go file, go.mod, CLI tool, or web service, and whenever the user mentions Go or golang, even if they don't ask for "idiomatic" code.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

go-spec-reviewer

Free

Review design specification documents for Go programs before implementation begins. Use this skill when a user has a Go spec, design doc, RFC, or PRD to review, wants feedback on a planned feature in a Go codebase, is about to start implementing from a spec, or asks "is this spec ready?" or "review this before I build it". Applies Go philosophy — simplicity, composition, explicit errors, context propagation — plus Cobra/Viper CLI conventions where applicable.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

hitkeep-ai-visibility-analyst

Free

Analyze HitKeep AI visibility data. Use for AI crawler fetches, AI-referred visits, assistant names or families, citation yield, resource types, top paths, fetch failures, Search Console context, GPTBot, ClaudeBot, ChatGPT, Claude, Perplexity, AI search, or whether assistants are discovering and sending traffic to a site.

The English summary is being prepared. Showing the original description.

PascaleBeier/hitkeep97Updated Oct 21, 2026

See all skills by PascaleBeier

Report a problem with this skill