CtrlK
BlogDocsLog inGet started
Tessl Logo

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

55

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/systematic-debugging/SKILL.md

The canonical home for this skill is systematic-debugging in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 skill delivers a strong, well-sequenced debugging workflow with explicit validation and feedback loops, plus a useful instrumentation example. Its weaknesses are motivational/redundant padding around the core process and references to supporting files that are not present in the bundle.

Suggestions

Consolidate the overlapping Red Flags, Common Rationalizations, and Signals sections into one trim "When to stop and return to Phase 1" list to cut redundancy.

Either provide the referenced root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md files or inline their essential technique and drop the dangling references.

Remove or qualify the unsubstantiated "Real-World Impact" statistics (95% vs 40% first-time fix rate) since they read as filler and aren't verifiable.

DimensionReasoningScore

Conciseness

The four-phase core is efficient and instructional, but surrounding sections (Red Flags, Common Rationalizations, "your human partner's Signals") cover overlapping ground and the "Real-World Impact" stats ("95% vs 40%") are unsubstantiated padding that could be trimmed.

3 / 5

Actionability

Each phase lists concrete steps and Phase 1 includes a real, runnable bash instrumentation example (env grep, security find-identity, codesign); the main gap is that "Trace Data Flow" defers its core technique to a referenced file that does not exist.

4 / 5

Workflow Clarity

A clearly sequenced four-phase process ("You MUST complete each phase before proceeding") with explicit validation checkpoints (Verify Before Continuing, Verify Fix) and feedback loops (failed fix → new hypothesis; 3+ failures → question architecture), plus a Quick Reference checklist.

5 / 5

Progressive Disclosure

In-body structure is well organized with clear section headers, but "Supporting Techniques" lists root-cause-tracing.md, defense-in-depth.md, and condition-based-waiting.md as "available in this directory" when no such bundle files exist, leaving navigation dangling.

3 / 5

Total

15

/

20

Passed

Description

56%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 an excellent, explicit trigger clause but functions almost entirely as a "when" with no explicit "what" — the skill's actual purpose (systematic root-cause investigation) is left implied. Trigger terms are natural and well-chosen.

Suggestions

State the "what" explicitly, e.g. "Systematically investigate root cause before fixing" so the capability is named, not just the trigger.

Add common trigger synonyms (crash, error, exception, regression) to broaden natural-term coverage.

Lead with the action (e.g. "Find root cause before proposing fixes") and follow with the "Use when..." clause to satisfy both what and when.

DimensionReasoningScore

Specificity

The description names the debugging domain via triggers ("any bug, test failure, or unexpected behavior") but states no concrete actions the skill performs; "before proposing fixes" is a timing cue, not a capability.

2 / 5

Completeness

The "when" is explicit and strong ("Use when encountering any bug, test failure, or unexpected behavior"), but the "what" (systematic root-cause investigation) is only weakly implied by "before proposing fixes" rather than explicitly stated.

3 / 5

Trigger Term Quality

"bug, test failure, unexpected behavior" are natural phrases a user would say, with good coverage; common synonyms like crash, error, exception, or regression are missing.

4 / 5

Distinctiveness Conflict Risk

The debugging niche is mostly distinct and the "before proposing fixes" framing narrows it; minor overlap risk remains because "unexpected behavior" is broad enough to collide with other dev skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.