pptx — SkillCheck Report

Issues

Warnings (11)

5.1-no-style-section No writing style section found line 1
Fix: Add a '## Writing Style' or '## Anti-Slop' section
16.1-no-stop-condition Complex skill lacks explicit stop conditions line 7
Fix: Add stop/termination criteria (e.g., 'Stop after N iterations', 'Abort if error rate exceeds threshold')
15.1-no-budget-cap Multi-agent skill has no budget or turn cap; runaway costs are possible line 7
Fix: Add max_turns, cost_limit, or similar budget constraint for subagents
19.3-generator-no-output-spec Generator pattern detected but no output format specified line 7
Fix: Document the output format (template, schema, or example output)
19.5-pipeline-no-stages Pipeline pattern detected but no stage documentation found line 7
Fix: Document the pipeline stages, checkpoints, and data flow between stages
19.2-reviewer-no-criteria Reviewer pattern detected but no evaluation criteria documented line 7
Fix: Add a criteria section (checklist, rubric, or pass/fail conditions)
4.5-desc-no-triggers Description lacks triggering conditions line 2
Fix: Add phrases like 'Use when...', 'Triggers on...', or 'Applies to...' to help Claude select this skill
1.2-desc-what Description missing WHAT clause (action verb) - recommended by agentskills spec line 3
Fix: Consider starting with what the skill does, e.g., 'Creates...', 'Generates...', 'Validates...'
1.2-desc-when Description missing WHEN clause - recommended by agentskills spec line 3
Fix: Consider adding 'Use when...' or 'Activate when...' to description
6.2-no-alt-text No alt text guidance found line 1
Fix: Add instructions for alternative text on images
12.3-workflow-vague-step Step is too brief to be actionable: "Fix issues" line 199
Fix: Add specific details: what, where, and how

Suggestions (12)

5.2-no-do-dont Missing DO/DON'T lists for style guidance line 1
Fix: Add explicit DO and DON'T lists for writing patterns
16.4-no-idempotency Skill does not document whether it is safe to re-run line 7
Fix: Add idempotency guidance: state whether running the skill twice produces the same result or causes side effects
17.1-no-input-contract No input contract found; unclear what data the skill expects line 7
Fix: Document what the skill expects as input (format, required fields, constraints)
17.2-no-output-contract No output contract found; unclear what the skill produces line 7
Fix: Document what the skill produces (format, structure, side effects)
17.3-no-mode-awareness Skill does not clarify standalone vs composed behavior line 7
Fix: Clarify whether the skill works standalone, in pipelines, or both
3.3-name-single-word Single-word names are less discoverable line 2
Fix: Consider a two-word name like 'task-tracker' or 'code-reviewer'
18.1-no-confidence-signal No confidence signal found for orchestrator decision-making line 1
Fix: Add confidence indicators (e.g., confidence: high/medium/low) so orchestrators can route or retry
18.2-no-progress-signal Complex skill lacks progress reporting checkpoints line 1
Fix: Add progress signals (e.g., 'Step 2 of 5: validating input') for long-running workflows
18.3-no-structured-output No structured output format defined for machine consumption line 1
Fix: Define a structured output format (JSON, YAML, or table) so downstream tools can parse results
15.3-no-human-checkpoint Multi-agent skill has no human-in-the-loop checkpoint line 7
Fix: Add pause points for human review before high-stakes operations
9.5-desc-tokens Description is 141 tokens; aim for under 100 line 3
Fix: Make description more concise
6.4-generic-font Generic font specified line 100
Fix: Consider brand-specific or more distinctive typography