systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/software-development/systematic-debugging/SKILL.md

Quality

Content

73%Weight 40%Scale 1-5

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

The body is a strong, well-sequenced debugging process with excellent workflow clarity, concrete commands, and validation checkpoints; its main weakness is redundant anti-guessing rhetoric that inflates length without adding capability.

Suggestions

Consolidate the redundant anti-guessing rhetoric from the Iron Law, Feedback Loop Rule, Red Flags, and Common Rationalizations into one section to reduce padding and lift conciseness.

Rewrite the search_files examples as actual executable calls (or clearly mark them as tool invocations) so all code blocks are copy-paste ready.

Consider moving the 10-item loop-construction list or the delegate_task template into a reference file to shorten the core SKILL.md and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The core process content is actionable and does not over-explain basic concepts, but the same anti-guessing message is repeated across the Iron Law, Feedback Loop Rule, Red Flags, and Common Rationalizations sections with heavy ALL-CAPS emphasis, which is noticeable padding that could be tightened.	3 / 5
Actionability	Provides many concrete, executable commands (pytest, git log/diff, repro loops) and a specific 10-item loop-construction list, but the search_files examples are written as non-executable comment-style pseudo-calls, leaving minor gaps.	4 / 5
Workflow Clarity	Four phases are explicitly sequenced with sub-steps, a Phase 1 completion checklist, STOP gates between phases, and clear feedback loops (verify → new hypothesis; Rule of Three), matching the anchor for explicit validation steps and checklists.	5 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections with no nested-reference anti-pattern, and no bundle files exist to split; the main gap is that a ~400-line monolith with no detail-file references could offload some material, keeping it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

61%Weight 40%Scale 1-5

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

The description is terse and uses natural trigger terms, but it lacks an explicit "when to use" clause and only minimally enumerates concrete actions, which caps completeness and limits specificity.

Suggestions

Add an explicit "Use when..." clause naming trigger situations (e.g., "Use when facing test failures, production bugs, or unexplained behavior — especially under time pressure.") to lift completeness above 3.

List 2-3 concrete actions (e.g., "reproduce, trace data flow, form and test hypotheses") so capabilities read as specific rather than a single high-level framing.

Include synonyms like "troubleshooting" or "errors" to broaden natural-term coverage toward a 5.

Dimension	Reasoning	Score
Specificity	Names the domain ("root cause debugging") and a concrete two-part framing ("understand bugs before fixing") plus a structural claim ("4-phase"), but lists no granular actions like reproduce, trace, or hypothesize, so it sits between anchors 2 and 3.	3 / 5
Completeness	The "what" is reasonably clear (4-phase root cause debugging), but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural user terms — "debugging", "root cause", "bugs", "fixing" — that a user would plausibly say, with only common synonyms like "troubleshooting" or "errors" missing, matching the anchor for good but not comprehensive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	"Root cause debugging" carves a clear niche with mostly distinct triggers, with only minor overlap risk against generic debugging/troubleshooting skills, fitting the "mostly distinct" anchor.	4 / 5
	Total	14 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/systematic-debugging/SKILL.md
Commit: 6327930

Reviewed: 3 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.