CtrlK
BlogDocsLog inGet started
Tessl Logo

he-fix-bugs

Restore broken behavior by reproducing failures, identifying root cause, and delivering verified fixes. Use when the user needs regression debugging, incident triage, or bug repair from tracker or direct reports.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Failed to scan

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 content is a well-structured, actionable debugging workflow with strong validation checkpoints, but progressive disclosure is weakened by broken/messy reference navigation and referenced files absent from the bundle.

Suggestions

Reattach each detached "Read when:" line to its corresponding reference link so the Full Context section reads as paired link-plus-condition entries instead of orphaned lines.

Resolve bundle-path mismatches: the body points to ./Infrastructure/references/contract.yaml, evals.yaml, task-profile.json, and ./assets/, none of which exist in the bundle — either add the files or correct the paths to the real ./references mirror.

Avoid deeply nested external relative paths (e.g. ../../../../../Skills/agent-ops/codex-agent-creator/SKILL.md) and duplicate content between the Procedure and references/context-preservation.md; keep SKILL.md the concise overview and let the reference hold the detail.

DimensionReasoningScore

Conciseness

The body is mostly lean procedural lists that assume Claude's competence, but Procedure steps 5-9 are duplicated verbatim in references/context-preservation.md and a few constraints could be trimmed, so minor tightening remains.

4 / 5

Actionability

Concrete instruction-only guidance ("ask at most 2-3 focused questions", "read only tails or targeted matches", "capture [ERROR]/[WARN] markers", "apply the minimal fix") is specific and executable with only minor gaps, though no copy-paste code/commands are given.

4 / 5

Workflow Clarity

A clear 9-step Procedure is paired with a dedicated Validation section containing explicit fail-fast gates ("stop at first failed gate and do not proceed") and regression-verification checkpoints, matching the anchor for explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

Sections are well-organized, but the Full Context section has detached "Read when:" lines that lost their associated links (lines 103, 108-111), references nonexistent bundle paths (./Infrastructure/references/*, ./assets/), and uses deeply nested external paths, so references are not clearly signaled.

3 / 5

Total

16

/

20

Passed

Description

87%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 third-person, concise, and explicitly covers both what the skill does and when to use it with concrete trigger phrases. It is specific and clearly distinct from neighboring skills.

DimensionReasoningScore

Specificity

"reproducing failures, identifying root cause, and delivering verified fixes" lists several specific concrete actions with only minor coverage gaps, matching the anchor that names multiple specific actions.

4 / 5

Completeness

It explicitly answers both what ("Restore broken behavior by reproducing failures, identifying root cause, and delivering verified fixes") and when ("Use when the user needs regression debugging, incident triage, or bug repair...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"regression debugging, incident triage, or bug repair from tracker or direct reports" gives good natural keyword coverage a user would actually say, with a few common synonyms missing.

4 / 5

Distinctiveness Conflict Risk

The regression debugging / incident triage / bug-repair niche has distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 5 missing, 4 deeper-than-1-level, 6 suspicious

Warning

Total

14

/

16

Passed

Repository
jscraik/Agent-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.