Skip to content
mcp/skillhub

Agent Skill

Why skill

whymichael-denyer/pstack-claudeplugins/pstack/skills/why/SKILL.md

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.

3.3kMIT

always on

89 tokname + description

once used

2,290 tokSKILL.md body

bundled files

1245 KB

repo stars

3.3kGitHub

Install the Why skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/michael-denyer/pstack-claude --skill why

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/michael-denyer/pstack-claude.git /tmp/pstack-claude
mkdir -p ~/.claude/skills
cp -R /tmp/pstack-claude/plugins/pstack/skills/why ~/.claude/skills/why

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description89 tok
When the agent uses itThe SKILL.md instructions2,290 tok
Only if opened12 bundled files (45 KB)varies

Until it is used, why costs about 15× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 65 skills from michael-denyer/pstack-claude would load 3,163 tokens of descriptions. Skills vs MCP study

Checks

  • Contains text that matches a prompt-injection pattern. In the skills we checked by hand this was security teaching material or a test fixture; read the file before you install it.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Why
  • Operating Posture
  • Step 1. Understand the Target and the Question
  • Step 2. Establish the Code Anchor
  • Step 3. Spawn Parallel Investigators
  • Discovery
  • Investigator roster, one per available evidence category
  • When to skip an investigator
  • Step 4. Synthesize
  • Step 5. Present
  • Output Format
  • Common Failure Modes to Avoid
  • Models
  • Reasoning effort

More skills from michael-denyer/pstack-claude

All skills in this repo
  1. architectmichael-denyer/pstack-claude

    Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

    3.3k52 tok idle · 1,615 in use
  2. arenamichael-denyer/pstack-claude

    Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

    3.3k58 tok idle · 1,321 in use
  3. automate-memichael-denyer/pstack-claude

    Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.

    3.3k72 tok idle · 1,755 in use
  4. babysitmichael-denyer/pstack-claude

    Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.

    3.3k61 tok idle · 1,057 in use
  5. benchmark-checklistmichael-denyer/pstack-claude

    Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.

    3.3k53 tok idle · 1,107 in use
  6. blast-radiusmichael-denyer/pstack-claude

    Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code ('make X public', 'X already handles Y') before you design against that assertion.

    3.3k87 tok idle · 867 in use
  7. bromichael-denyer/pstack-claude

    Restate the last message in plain human language, with no jargon. Use for /bro or when asked to say it plainly.

    3.3k28 tok idle · 30 in use
  8. correctmichael-denyer/pstack-claude

    Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.

    3.3k68 tok idle · 461 in use