python-debugpy

Debug Python: pdb REPL + debugpy remote (DAP).

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/software-development/python-debugpy/SKILL.md

Quality

Content

77%

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

The content is highly actionable and well-sequenced with strong verification steps, but it is a monolithic single-file skill with no progressive disclosure into referenced files. Some repetition of setup blocks and inline long scripts slightly reduce conciseness.

Suggestions

Move the long dap_client.py script and the Hermes-specific process guidance into separate reference files, signaling them with one-level-deep links from SKILL.md to improve progressive disclosure.

De-duplicate the repeated debugpy.listen/wait_for_client setup by referencing a single canonical snippet instead of restating it in the gateway and _SlashWorker sections.

Consider extracting the full pdb command table into a reference file so SKILL.md stays a concise overview pointing to detail.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (no 'what is pdb' filler, efficient tables), but the debugpy.listen setup is repeated across the gateway and Hermes-specific sections and could be tightened.	2 / 3
Actionability	Every recipe provides fully executable, copy-paste-ready code and commands with concrete file paths and flags (e.g. 'python -m debugpy --listen 127.0.0.1:5678 --pid <pid>').	3 / 3
Workflow Clarity	A 'pick by situation' table sequences tool choice, recipes are ordered, and an explicit Verification Checklist plus the xdist warning in Pitfall #1 provide validation checkpoints and error-recovery feedback.	3 / 3
Progressive Disclosure	No bundle files exist and all content is inline in one ~360-line document; large separable chunks (the dap_client.py script, the Hermes-specific section) live inline rather than being split into one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concise and names real tools, but it is terse: it lacks explicit use-when triggers and broader natural-language keyword coverage. It conveys what the skill does but not clearly when Claude should reach for it.

Suggestions

Add an explicit 'Use when ...' clause naming natural triggers, e.g. 'Use when a test fails without revealing why, when you need to step through Python code, or when debugging a long-running process.'

Broaden trigger terms to common user phrasings such as 'breakpoints', 'step through', 'post-mortem', and 'attach to a running process' rather than only tool names.

Expand the capability list beyond two tools to surface concrete actions (set breakpoints, inspect locals, post-mortem, attach to running processes).

Dimension	Reasoning	Score
Specificity	Names concrete tools and modes ("pdb REPL", "debugpy remote (DAP)") but lists only two actions rather than a comprehensive set of capabilities like breakpoints, post-mortem, or stepping.	2 / 3
Completeness	It states what the skill does but provides no explicit "Use when..." trigger guidance, so the when is only implied; per the guideline a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	"Debug Python" is a natural user phrase, but the rest (pdb, debugpy, DAP) is technical jargon and common variations like "breakpoints", "step through", or "post-mortem" are absent.	2 / 3
Distinctiveness Conflict Risk	The pdb/debugpy niche is fairly specific but could still overlap with general debugging skills such as systematic-debugging, so it is not a fully distinct trigger set.	2 / 3
	Total	8 / 12 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: 7 missing	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/python-debugpy/SKILL.md
Commit: 74a56b7

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.