debugging

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'tsx debug', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'playwright', 'flaky test', 'fails intermittently', 'passes in isolation', 'only fails in CI'.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected index skill with excellent progressive disclosure and a clearly sequenced, validated phase workflow. The body's weaknesses are rhetorical redundancy (repeated mandatory-reading admonitions) and that most executable commands live in references rather than in SKILL.md itself, which is appropriate by design but leaves the body's standalone actionability incomplete.

Suggestions

Collapse the repeated 'READ THE REFERENCES / NOT OPTIONAL' admonitions into a single gate-rule statement; the message currently recurs in the header callout, the Runtime Setup intro, the Specialist Tools intro, the Phase Loop intro, and the closing line.

Consider inlining one or two of the most common executable commands (e.g., the core attach/breakpoint invocation for the top runtimes) so the body is actionable without requiring a reference open for trivial cases.

Trim the predictive-failure prose in the header callout ('you will reattach a debugger the wrong way, miss a silent-failure pattern...') to a tighter justification; it reads as motivational padding.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept explanation, but the hortatory 'READ THE REFERENCES / THIS IS NOT OPTIONAL' message is repeated across the header callout, each section intro, and the closing line, which is redundant padding that could be tightened.	2 / 3
Actionability	Provides some concrete guidance (the bundled-vs-native discriminator command 'du -h' + 'strings -n 12 ... \| rg -iE ...', exact reference paths, and a numbered entry procedure), but the bulk of executable debugging commands are delegated to references rather than present in the body.	2 / 3
Workflow Clarity	A clearly sequenced Phase 0–10 loop with explicit validation checkpoints — Phase 6 'confirmed only when toggling the suspected cause toggles the bug', Phase 10 'four evidence gates', Phase 9 'verify git diff shows only fix + test' — plus the safety invariants as feedback gates.	3 / 3
Progressive Disclosure	Exemplary index structure: SKILL.md is an overview pointing to one-level-deep references organized in tables (runtimes, tools, methodology phases), all referenced paths verified as real files, with easy navigation and no nested reference chains.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, highly specific description that names concrete debugging actions, supplies a large set of natural trigger terms, and explicitly separates 'what' from 'when'. It avoids first/second-person pronouns and uses imperative 'Use when'-style triggers consistent with the rubric's good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles... confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Runs a hypothesis-driven loop: form ≥3 hypotheses... scrub artifacts') and when ('MUST USE for any real runtime debugging...', plus an explicit 'Triggers:' clause), so it is not capped at 2.	3 / 3
Trigger Term Quality	Extensive coverage of natural phrases users would say — 'debug this', 'why is X not working', 'hanging', 'flaky test', 'fails intermittently', 'passes in isolation' — plus relevant tool keywords (gdb, pdb, pwndbg) for the domain.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (runtime debugging across any language/binary) with distinct, specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 24 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 49 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/debugging/SKILL.md
Commit: 895b70c

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.