python-debugpy

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote or headless attach.

Quality

84%

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

93%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.

A tight, highly actionable debugging reference that assumes competence and provides copy-paste commands with cleanup validation. Its only soft spot is workflow clarity, which is reference-style rather than an explicit step sequence.

Suggestions

Optional: frame the Rules section as a short ordered checklist (reproduce smallest case → choose debugger → attach → cleanup/verify) to make the workflow sequence explicit and lift workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	Lean reference with no padding about what Python or debuggers are; every command, snippet, and rule earns its place and assumes Claude's competence.	5 / 5
Actionability	Fully executable copy-paste bash and python blocks cover launching pdb, post-mortem, debugpy listen/wait/PID/source-edit attach, plus a concrete pdb command reference for the common cases.	5 / 5
Workflow Clarity	A clear decision framework and an explicit cleanup validation checkpoint ('rg' to remove breakpoints, rerun the test gate) plus a ptrace troubleshooting hint, but the body reads as a reference rather than an explicitly sequenced workflow.	4 / 5
Progressive Disclosure	Self-contained and well-organized under clear headers (Commands, pdb commands, Rules) with no need for external bundle files, making navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

75%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.

A concise, specific description with strong distinctiveness and concrete actions, but it omits an explicit 'Use when...' trigger clause, which caps completeness. Adding a trigger sentence would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when Python code needs interactive debugging, a failing test, or a hung subprocess you need to attach to.'

Add a few natural synonyms such as 'step through', 'set a breakpoint', or 'trace' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'pdb', 'breakpoint()', 'post-mortem inspection', 'debugpy remote or headless attach' — covering the main Python debugging approaches comprehensively.	5 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' trigger clause; per the rubric guideline, a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms (Python, debug, pdb, debugpy, breakpoint) but a few common synonyms like 'step through', 'trace', or 'set_trace' are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear Python-debugging niche with distinct triggers (pdb, debugpy) and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: EKKOLearnAI/hermes-studio
Path: packages/ekko-agent/skills/python-debugpy/SKILL.md
Commit: 07ccb17

Reviewed: 5 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.