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

66%

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

72%

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 with concrete executable commands and a strong real example, and is well-organized for a simple technique. Its main weaknesses are mild redundancy and an implicit rather than explicit validation/feedback loop in the workflow.

Suggestions

Remove the redundant command variants (the 'more specifically' head -50 block and the repeated command in Step 2) and consolidate into one canonical invocation.

Tighten the 'Why This Works' section to drop explanation of basic shell mechanics (2>&1, head) that Claude already knows.

Make the workflow's validation explicit by adding a feedback loop: if the re-run still fails, return to Step 3 to analyze the new traceback rather than ending at Step 5.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but repeats near-identical commands (head -100 vs head -50, and the same command in Step 2) and explains basics Claude already knows (what 2>&1 and head do), so it could be tightened.

2 / 3

Actionability

Provides multiple fully executable bash commands and a copy-paste before/after reportlab example with a concrete FileNotFoundError output, matching the score-3 anchor for executable, copy-paste-ready guidance.

3 / 3

Workflow Clarity

A clear 5-step sequence exists with a confirm-on-re-run step, but the validation checkpoint is implicit and there is no explicit error-recovery feedback loop (e.g., if the re-run still fails, return to traceback analysis), matching the score-2 anchor.

2 / 3

Progressive Disclosure

A single, well-organized self-contained file with clear sections and no nested references; for a simple single-purpose technique with no bundle files, this satisfies the score-3 'well-organized' condition.

3 / 3

Total

10

/

12

Passed

Description

60%

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 specific and concrete about the technique and outcome, but omits explicit trigger ('Use when...') guidance and leans on technical jargon, limiting completeness and trigger coverage. Adding a usage trigger and broader natural keywords would raise it.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g., 'Use when a Python PDF library fails with a generic or unknown error message and the real traceback is hidden').

Broaden trigger terms with natural user phrasings and library names, e.g., 'PDF generation error', 'reportlab', 'fpdf', 'PDF build failing', 'silent crash'.

Sharpen distinctiveness by anchoring the niche to the specific failure mode (opaque/generic error messages hiding tracebacks) rather than generic 'debug Python errors'.

DimensionReasoningScore

Specificity

Names the domain (Python PDF generation) and multiple concrete actions ('using unbuffered output and stderr inspection to reveal actual tracebacks'), matching the score-3 anchor for listing specific concrete actions.

3 / 3

Completeness

Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Includes relevant natural terms like 'PDF generation errors' and 'tracebacks', but relies on technical jargon ('unbuffered output', 'stderr inspection') and misses common variations such as library names (reportlab, fpdf) or phrasings like 'PDF won't build'.

2 / 3

Distinctiveness Conflict Risk

Carves a reasonable niche (debugging PDF generation via unbuffered/stderr inspection) but 'debug Python errors' is general enough to overlap with broader Python debugging skills, matching the score-2 'somewhat specific but could still overlap' anchor.

2 / 3

Total

9

/

12

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.

Validation16 / 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.