CtrlK
BlogDocsLog inGet started
Tessl Logo

pdf-debug-unbuffered

Debug Python PDF generation errors by using unbuffered output and stderr inspection to reveal actual tracebacks

58

Quality

73%

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 ./benchmarks/gdpval/skills/pdf-debug-unbuffered/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 delivers highly actionable, executable debugging guidance with a clear step sequence and good organization. Its main weakness is moderate verbosity from explaining basic shell/Python concepts Claude already knows.

Suggestions

Trim the 'Why This Works' section — Claude already knows what the `-u` flag, `2>&1`, and `head` do; keep only the non-obvious insight about output buffering hiding tracebacks on crash.

Condense or remove the 'Notes' section, which restates applicability already implied by the technique.

Make the error-recovery loop explicit in the step-by-step (e.g. 'If the traceback is still truncated, increase the head limit or capture full stderr to a file').

DimensionReasoningScore

Conciseness

The core technique is code-focused and efficient, but the 'Why This Works' section over-explains basic shell concepts (what `-u`, `2>&1`, and `head` do) that Claude already knows, and the 'Notes' section adds general padding.

3 / 5

Actionability

Provides copy-paste-ready commands (`python -u your_script.py 2>&1 | head -100`), concrete alternatives (`2> error.log`, `-v -u`), and a worked reportlab example with the actual FileNotFoundError output — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

A clear 5-step sequence (identify → run unbuffered → analyze traceback → fix → re-run normally to confirm) with a verification checkpoint in step 5, though the error-recovery loop is implicit rather than an explicit 'if still failing, repeat' feedback loop.

4 / 5

Progressive Disclosure

Single-purpose skill with no external references needed; content is well-organized under clear section headers (Core Technique, Step-by-Step, Common Issues, Alternative Approaches, Example), which is appropriate for a self-contained technique.

5 / 5

Total

17

/

20

Passed

Description

53%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 clearly states what the skill does using concrete technical terms but omits any 'when to use' trigger guidance, which limits completeness. Trigger term coverage is adequate but lacks synonyms and library names that would improve discoverability.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when a Python PDF library (reportlab, fpdf) fails with a generic or opaque error message and the real traceback is hidden.'

Include common trigger synonyms and library names like 'reportlab', 'fpdf', '.pdf', or 'PDF library' to improve keyword coverage.

Tighten the description to third-person imperative form and ensure it signals the trigger condition (opaque/generic PDF errors) clearly.

DimensionReasoningScore

Specificity

Names the domain ('Python PDF generation errors') and concrete actions ('unbuffered output', 'stderr inspection', 'reveal actual tracebacks'), but coverage is narrow — a single debugging technique rather than a comprehensive set of actions.

3 / 5

Completeness

Has a clear 'what' (debug PDF errors via unbuffered output and stderr inspection to reveal tracebacks) but no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes relevant natural terms like 'PDF generation errors' and 'tracebacks' that a user might say, but misses common synonyms and library names (reportlab, fpdf, .pdf) that would broaden trigger coverage.

3 / 5

Distinctiveness Conflict Risk

Targets a specific niche (debugging PDF generation errors via unbuffered/stderr inspection) with minimal overlap risk, though it could conceivably overlap with general Python debugging skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
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.