Why
by backnotprop3a604672c46cNo license1.3K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
Only the file list is public. File contents are available once the skill is installed in a workspace.
| Path | Size | Type |
|---|---|---|
| references/epistemics.md | 7.6 KB | text/markdown |
| references/investigator-prompt.md | 6.8 KB | text/markdown |
| references/source-playbook.md | 1.3 KB | text/markdown |
| references/sources/code-archaeology.md | 3.4 KB | text/markdown |
| references/sources/databricks.md | 6.8 KB | text/markdown |
| references/sources/datadog.md | 5.2 KB | text/markdown |
| references/sources/incident-postmortem.md | 1.9 KB | text/markdown |
| references/sources/linear.md | 2.9 KB | text/markdown |
| references/sources/notion.md | 2.8 KB | text/markdown |
| references/sources/sentry.md | 4.8 KB | text/markdown |
| references/sources/slack.md | 3 KB | text/markdown |
| references/synthesizer-prompt.md | 7.8 KB | text/markdown |
| SKILL.md | 10.8 KB | text/markdown |
Source and attribution
Source:backnotprop/pstackinskills/whyat commit3a60467
License: No license
Content belongs to its original authors. SourceWeft indexes it from a public repository.
More from backnotprop/pstack
Swarm
backnotprop
Fans out N parallel workers on slices or races, aggregates their results, and returns one report.
Setup Pstack
backnotprop
Configures pstack's per-role model choices and reasoning budget by writing a settings rule file.
Recall
backnotprop
Rebuilds recent working context from chat history, shared records and live state, then returns a tight current-state brief.
No Comments
backnotprop
Removes unjustified code comments by spawning a review subagent, fixing accepted findings, and offering encodings for constraints.
Interrogate
backnotprop
Runs multiple LLM reviewers on code changes and synthesizes an adversarial verdict.
Maintain Verification Skill
backnotprop
Periodic upkeep loop that audits a project's verification skill and feature map, then ships at most one PR of proven corrections.
More in Research & Analysis
Equity Research
anthropics
Builds structured equity research snapshots from consensus estimates, fundamentals, prices and macro data.
Sector Overview
anthropics
Produces industry and sector landscape reports covering market size, competitive positioning, valuation and investment implications.
Idea Generation
anthropics
Systematic stock screening and investment idea sourcing using quantitative screens, thematic research and pattern recognition.
Competitive Analysis
anthropics
Builds competitive landscape decks: market positioning, competitor deep-dives, comparative tables and strategic synthesis.
Notion Research Documentation
openai
Researches Notion pages and synthesizes findings into cited briefs, comparisons, or reports published back to Notion.
Notion Meeting Intelligence
openai
Prepares meeting agendas and pre-reads using Notion context and research, tailored to attendees and meeting type.