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

fixing-a-bug.md

View on GitHub
# Fixing a bug — brainstorming's bug branch

Entry: a bug report, with the task-spec open (spine step 3). Saves: the task-spec's **Bug**
section. Next: spine step 8 (Build) — or spine step 5 when the "bug" turns out to be a feature.

A bug is a gap between what the product is meant to do and what it does. Settle the intended
behavior before touching the code: it is confirmed and recorded in the task-spec here, which leads
the fix the way a design leads a feature. The durable specs are amended at spine step 9, as for
every change, so they describe what was actually built.

1. **Pin the report.** Symptom (what happens), expected behavior (what should happen instead), and
   how to trigger it. Infer them from the request; ask only what is missing, in one round per the
   **asking-user-questions** concept skill.
2. **Reproduce** when a safe command can show it — a failing test is best. Never run a destructive
   command to reproduce. If it can't be reproduced, record that and carry on.
3. **Locate** the code that produces the behavior and the specs that govern that area (spec-graph).
4. **Classify** by what those specs say about the expected behavior:
   - **Silent** — no spec covers it. The intended behavior is a product decision: confirm it with
     the user as an inference; spine step 9 adds it to the spec that should have stated it.
   - **Wrong** — a spec states the buggy or an outdated behavior. Confirm the correction with the
     user; spine step 9 corrects that spec.
   - **Right** — the spec already states the expected behavior; only the code is wrong. No question
     needed.
   - **Feature** — the code does what the specs intend, and the expected behavior was never
     intended. Tell the user it is a new capability and continue at spine step 5.
   Ask about the classification itself only when the evidence genuinely supports two of them.
5. **Record** symptom, expected behavior, reproduction (or "unreproduced"), classification, and the
   confirmed intended behavior in the task-spec's **Bug** section. The intended behavior is the
   accepted design — there is no separate design review for a bug.
6. **Fix it test-first** when practical: a regression test that fails before the fix and passes
   after. Continue at spine step 8.
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: 471kUpdated 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