Debugging · Matt Pocock
Diagnosing Bugs by Matt Pocock
Runs a gated diagnosis loop from reproduction and minimization through instrumentation and regression testing.
Setup and compatibility
Part of Matt Pocock Skills. The 25 promoted skills remain strongest as a Claude Code-centered personal workflow, although editable copies work across agents. The most ambitious orchestration and self-improvement ideas are still under in-progress, rely on background agents, worktrees, issue graphs, and project conventions, and should not yet be treated as stable lifecycle coverage.
Editorial compatibility guidance: Claude Code · Codex · Cursor. This is not an executed compatibility test; see the review for source and run evidence.
Read Diagnosing Bugs instructions and prerequisites · Read Matt Pocock Skills setup documentation
Independent review
This skill makes debugging a sequence of evidence-producing gates: reproduce, minimize, hypothesize, instrument, fix, and regression-test. It is a strong antidote to agents editing the first suspicious line and declaring victory.
Read the Diagnosing Bugs review and usage guideTry this skill
Install · Selected skill + setup skill
Run in a terminal from your target project. Requires Node.js 22.20+, npm/npx, Git and network access.
Also installs setup-matt-pocock-skills; run that setup skill once per repository.
npx skills@latest add mattpocock/skills --skill diagnosing-bugs --skill setup-matt-pocock-skills -a claude-code
Command / route checked 30 October 2026. Upstream installationCLI optionsAgent support
Setup requirements and caveats
Run in a terminal from the target project. Requires Node.js 22.20+ (current skills CLI), npm/npx, Git and network access. Review the installer summary before confirming. Keeps this skill’s supporting files. Also installs setup-matt-pocock-skills; run that setup skill once per repository. Avoid installing both plugin and file copies. Grill Me may load its grilling dependency from upstream.
Node.js with node:test; standard patch utility and a fresh scratch directory
No dispatched skill dependencies; optional HITL script unused
These are documented requirements; installation has not been tested here.
Your agent needs its own account, runtime and model access. Usage charges depend on your plan; unrecorded costs are unknown.
- Existing Codex account; incremental charges were not measured
Run the example
Start a fresh session in the target project. Provide the relevant files or diff. This is the review’s example request, not a record of your execution.
Use the diagnosing-bugs skill. Diagnose why checkout latency doubled after the last release without changing production code until the responsible path is isolated.
Check your result · Successful first run
A reproduction, narrowed cause and evidence supporting a fix before production changes.
Confirm the agent loaded the named skill, inspect the output and run the relevant checks. Installation alone does not prove a successful run.
Something not working?
The skill is missing from my agent
Check that the skill is installed for the selected agent and project/global scope. Open a fresh session in that project and check the agent’s skill list. Plugin installs may also need to be enabled.
The wrong skill runs, or nothing happens
Start a fresh conversation, explicitly name the skill using the request above, and provide the requested inputs. Ask the agent to confirm which skill it loaded. Check for duplicate installed copies or overlapping instructions.
The skill runs but the result is poor
Compare the result with the successful-first-run check above. Supply the missing files, reproduction steps or constraints, then ask for one focused correction. If the skill addresses a different problem, return to the task guide and compare alternatives.
Installation troubleshooting · missing dependencies
If npx fails, check the Node/npm versions in setup requirements, Git and network access. For skills CLI installs, run npx skills list (add -g for global). If a route changed, follow upstream instructions.
Collection background and tradeoffs
The 25 promoted skills remain strongest as a Claude Code-centered personal workflow, although editable copies work across agents. The most ambitious orchestration and self-improvement ideas are still under in-progress, rely on background agents, worktrees, issue graphs, and project conventions, and should not yet be treated as stable lifecycle coverage.
Source maintained by Matt Pocock. Read original skill. Compatibility guidance and published showcase runs remain separate from your first run.
Inspect the recorded Diagnosing Bugs example and its limitations