python-debugpy

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

Quality

75%

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

85%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 highly actionable and well-sequenced with strong validation guidance — its main strength. The weakness is structure: a large single file with no one-level-deep references to split out the lengthy DAP-client recipe and the Hermes-specific process guidance.

Suggestions

Split the long DAP client script and Hermes-specific process sections into reference files (e.g. references/dap-client.py, references/hermes-processes.md) and link to them from the body to improve progressive disclosure.

Trim a few padded phrases ('Easiest.', 'Useful for quick poking.') and consider condensing the three debugpy client options to a short comparison table.

Move the bulk of the pdb quick-reference table into a reference file if it pushes the main body over a comfortable scanning length, keeping the most-used commands inline.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no padding about what Python or pdb is; code blocks are tight. Minor throwaway phrases ('Easiest.', 'Useful for quick poking.') and the long inline DAP client script keep it just below fully lean. Not a 5 because a few sections could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready code and commands throughout — breakpoint() recipes, `python -m pdb`, `pytest --pdb`, debugpy listen/wait-for-client, remote-pdb set_trace + nc. Specific examples cover the common cases including a worked DAP client script. Fits the anchor 5 example.	5 / 5
Workflow Clarity	Multi-step recipes are clearly sequenced (setup -> pattern -> connect), and the Verification Checklist plus Common Pitfalls supply explicit validation checkpoints and error-recovery feedback (e.g. breakpoint not hitting -> check PYTHONBREAKPOINT/runner/attach timing). Matches anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist and the ~370-line body is essentially monolithic, though it is broken into well-labeled sections (Overview, Recipes, Pitfalls, Checklist). Per the rubric, a large monolithic document without external references lands at anchor 3 rather than higher. The under-50-line simple-skill exception does not apply.	3 / 5
	Total	17 / 20 Passed

Description

66%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 concise and names the right tools and capabilities, but it omits any 'Use when...' trigger guidance, which is the dominant weakness. Adding a trigger clause would lift completeness and distinctiveness significantly.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when a Python test or long-running process needs interactive stepping, post-mortem inspection, or attaching to an already-running process.'

Include a few natural synonyms/trigger terms such as 'breakpoints', 'step through', and 'post-mortem' so users' phrasings match.

Explicitly state the distinguishing scope (local pdb vs. remote attach) to reduce overlap with a generic Python debugging skill.

Dimension	Reasoning	Score
Specificity	Names concrete capabilities — 'pdb REPL', 'debugpy remote (DAP)' — as distinct debugging mechanisms rather than generic actions, though coverage of actions is thin. Sits between anchors 3 and 4, closer to 4 because two concrete tool/capability pairs are specified.	4 / 5
Completeness	Has a clear 'what' (debug Python via pdb REPL + debugpy remote DAP) but no 'Use when...' or equivalent trigger guidance. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural trigger terms users actually say — 'Debug Python', 'pdb', 'debugpy', 'remote', 'DAP' — giving good keyword coverage. Falls short of 5 due to missing synonyms/file extensions (e.g. 'breakpoints', 'step through').	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Python debugging via pdb + debugpy) with minimal overlap risk, but lacks the fully explicit trigger phrasing that would make it unambiguously distinct. Mostly distinct, minor overlap with a generic Python debugging skill.	4 / 5
	Total	15 / 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: 7 missing	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/software-development/python-debugpy/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.