kryptamine/herdr-auto-title / .claude/skills/validate-agent-work
validate-agent-work
VerifiedUse when finishing any change to this repository, or when the user says "validate", "check my work", "run checks", or "verify changes". Also use automatically after adding a feature, fixing a bug, or editing Go, Python or documentation here.
Validate Agent Work
The rules live in AGENTS.md and CONTRIBUTING.md; this is the order to check them in before handing work back.
Steps
-
See what changed — the branch against
main, and whatever is not committed yet:git diff --name-only main...HEAD git status --shortStage nothing: every check below runs over the whole module, and the index is the user's to decide.
-
Run the gate:
make checkfmtruns first and rewrites files, so re-read one before editing it again. A change underscripts/also runsmake lint-scripts, whichmake checkleaves out because it needs uv and shellcheck. -
Comment pass — the
## Comment passin.claude/rules/comments.md, over the comments this change added or touched. -
Read the diff against the mandatory rules in AGENTS.md — the language, commit, type, script and comment rules, and the "Working here" list. The linter checks none of them. Two need a search rather than a read: a field, method or constant added without a reader in the same change, and a probe whose finding has not reached
docs/architecture/herdr-socket-api.md, which is the record —AGENTS.mdtakes it only if it misleads the code in silence. -
Check nothing was left running:
make ps -
Before opening a pull request, write its body with the
prskill and check it against .github/pull_request_template.md: every section filled, no HTML comment left, no attribution line. -
Fix and re-run — fix what a step found, then run that step again to confirm it. If a failure is not yours to fix, say so rather than working around it.
-
Report — always say what happened:
-
Clean: a brief confirmation.
-
Found and fixed, one line each:
Validation found and fixed 3 issues: - golangci-lint: unused parameter in resolver.qualify - Comments: dropped a caller note in app/reads.go - Type rule: removed PaneInfo.Cols, which nothing read -
Still broken: what is wrong and why you could not fix it.
-
make check is the whole gate on this machine, but CI also builds and tests on
the Go floor go.mod names and on macOS — see CONTRIBUTING's "Pull requests".
The user should never be surprised by a failure that could have been caught
here.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 465k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |