talk-stage1-extract
Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk.
75
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/talk-pipeline/stage-1-extract/SKILL.mdQuality
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that clearly communicates both what the skill does and when to use it, with specific concrete actions and a distinct niche. Its main weakness is that some terminology is domain-specific (e.g., 'REX vs Concept type') which may not match natural user language, and it could benefit from broader trigger terms like 'presentation' or 'speech' to improve discoverability.
Suggestions
Add common synonyms for 'talk' such as 'presentation', 'speech', or 'conference talk' to improve trigger term coverage for users who may use different vocabulary.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'extracts and structures source material', 'narrative arc, themes, metrics, and gaps', 'auto-detects REX vs Concept type', and 'auditing existing material'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('extracts and structures source material into a talk summary with narrative arc, themes, metrics, and gaps') and when ('Use when starting a new talk from any source material or auditing existing material before committing to a talk'). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'articles', 'transcripts', 'notes', 'talk', 'source material', but the domain is niche and terms like 'REX vs Concept type' are specialized jargon that users may not naturally use. Missing common variations like 'presentation', 'speech', 'conference talk'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around talk preparation and summarization from source material. The specific mention of 'talk summary', 'narrative arc', 'REX vs Concept type', and 'auditing existing material' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid instructional skill that clearly defines a structured extraction process with a well-specified output format and useful rules. Its main weaknesses are moderate verbosity (some sections repeat information) and a lack of integrated validation checkpoints within the workflow itself. The output template is the strongest element, providing very concrete guidance on what the result should look like.
Suggestions
Integrate validation checkpoints into the workflow steps rather than having a separate post-hoc checklist — e.g., 'After detecting source type, confirm with user if confidence is low' or 'After metric extraction, verify count against source before proceeding.'
Remove or consolidate the 'When to Use This Skill' and 'What This Skill Does' sections — the numbered steps already convey the workflow, and the usage context is covered by the opening sentence.
Add a concrete example of running the skill: show a sample invocation (e.g., with a file path and flags) and a brief excerpt of what the output summary looks like with real-ish data filled in, rather than only the template.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The 'What This Skill Does' section largely duplicates the workflow that follows. The 'Tips' section restates things already implied. The anti-patterns section, while useful, could be tighter. Some sections like 'When to Use This Skill' repeat the description. | 2 / 3 |
Actionability | The skill provides a detailed output template and clear rules for metric extraction, which is good. However, there are no executable code examples or concrete commands — it's entirely instruction-based with no tool invocations, file I/O commands, or scripts shown. The guidance is specific enough to follow but lacks the copy-paste readiness of a score-3 skill. | 2 / 3 |
Workflow Clarity | The numbered steps in 'What This Skill Does' provide a clear sequence, and there's a validation checklist at the end. However, the validation checklist is a post-hoc review rather than integrated checkpoints within the workflow. There's no explicit feedback loop (e.g., 'if source type detection is ambiguous, ask user before proceeding'). The AskUserQuestion for missing metadata is a good checkpoint but is mentioned only briefly. | 2 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections, a logical flow from input to output to rules to validation, and clean references to related stages at the bottom. The content is appropriately scoped for a single file — it doesn't need to be split further — and the cross-references to other pipeline stages are one level deep and clearly signaled. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
746adc8
- 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.