Skip to content

JetBrains/thinkrail / packages/pi-thinkrail-workflow/skills/brainstorming

brainstorming

Verified

Use before implementing a feature, a change in behavior, or a bug fix — however small. Not for questions, checks, or edits that change no behavior (typos, documentation or configuration only, mechanical refactors).

FileKindSize
SKILL.mdskill md4.6 KB
amending-specs.mdmarkdown2.2 KB
fixing-a-bug.mdmarkdown2.2 KB

amending-specs.md

View on GitHub
# Amending specs — brainstorming's shared tail

Entry: the accepted change is built and verified (spine step 8). Saves: the durable spec graph.
Ends: the workflow.

The specs stay the ground truth only if every change lands in them. This is your job, not a round
of approvals: do it yourself, and let the user see the result in the Changes review. Read the
**writing-specs** concept skill first — its bar holds for every edit here.

1. **Find what changed in the specs' terms** — from the task-spec and the actual diff, not the plan:
   - the goal doc, when a capability was added or removed or a principle overturned;
   - `architecture.md`, when topology, a cross-module decision, or a repo-wide invariant moved;
   - the owning module or submodule `SPEC.md`, for a responsibility, boundary, contract, decision,
     or known limitation — and a new spec for a genuinely new module;
   - for a bug classified silent or wrong, the spec that should have stated the intended behavior.
2. **Amend top-down** — goal → architecture → modules — without asking the user to approve the list
   or the edits. `spec_create` for a new spec, `spec_update` for frontmatter, `edit` for prose. Write
   the decisions and the *why* the code cannot show, once, in the spec that owns them; link the rest
   by `id`. Unconfirmed assumptions are marked unconfirmed where they stand.
3. **Check against reality.** Each amended spec matches what was built, not what was planned; the
   specs you touched don't contradict each other or use a term two ways. Run `spec_validate` and fix
   what it reports.
4. **Nothing durable changed?** (A bug classified right, a change the specs already describe.) Then
   make no edits — never invent content to show activity.
5. **Report in a line or two:** which specs changed, by name, and any unconfirmed assumption left in
   them. No per-file narration.
6. **Retire the task-spec** — once its durable content is in the tree, set its `status: done` with
   `spec_update`. Never delete it: it stays in the user's Artifacts tab, and spec search skips a
   finished task-spec.

## Ending

This workflow ends here. PR lifecycle work, if requested, then enters **shipping-a-pr** separately.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexUnverifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall