Skip to content
mcp/skillhub

Agent Skill

Diagnosing Bugs skill

diagnosing-bugsMatt Pocock Skillsskills/engineering/diagnosing-bugs/SKILL.md

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

300kMIT

always on

40 tokname + description

once used

1,988 tokSKILL.md body

bundled files

21 scripts

installs

824kskills.sh

Install the Diagnosing Bugs skill

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

npx skills add https://github.com/mattpocock/skills --skill diagnosing-bugs

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/mattpocock/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -R /tmp/skills/skills/engineering/diagnosing-bugs ~/.claude/skills/diagnosing-bugs

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 description40 tok
When the agent uses itThe SKILL.md instructions1,988 tok
Only if opened2 bundled files (1 KB)varies

Until it is used, diagnosing-bugs costs about 34× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 38 skills from mattpocock/skills would load 1,290 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

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

  • Diagnosing Bugs
  • Redact
  • Phase 1: Build a feedback loop
  • Ways to construct one, in roughly this order
  • Tighten the loop
  • Non-deterministic bugs
  • When you genuinely cannot build a loop
  • Completion criterion: a tight loop that goes red
  • Phase 2: Reproduce + minimise
  • Minimise
  • Phase 3: Hypothesise
  • Phase 4: Instrument
  • Phase 5: Fix + regression test
  • Phase 6: Cleanup

More skills from mattpocock/skills

All skills in this repo
  1. grill-memattpocock/skills

    A relentless interview to sharpen a plan or design.

    1.4M14 tok idle · 9 in use
  2. grill-with-docsmattpocock/skills

    A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

    1.2M30 tok idle · 17 in use
  3. improve-codebase-architecturemattpocock/skills

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

    1.2M32 tok idle · 1,304 in use
  4. tddmattpocock/skills

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    1.1M33 tok idle · 735 in use
  5. setup-matt-pocock-skillsmattpocock/skills

    Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

    1.0M44 tok idle · 1,673 in use
  6. handoffmattpocock/skills

    Compact the current conversation into a handoff document for another agent to pick up.

    1.0M19 tok idle · 151 in use
  7. triagemattpocock/skills

    Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

    979k33 tok idle · 1,510 in use
  8. prototypemattpocock/skills

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    976k39 tok idle · 597 in use