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.
64
77%
Does it follow best practices?
Impact
—
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 strong description that clearly communicates both what the skill does and when to use it, with a well-defined niche around talk preparation from source material. The main weakness is that trigger terms could be broader to capture more natural user language variations (e.g., 'presentation', 'speech', 'conference'). The domain-specific jargon 'REX vs Concept type' may not be recognized by users unfamiliar with the framework.
Suggestions
Add common synonyms for 'talk' such as 'presentation', 'speech', or 'conference talk' to improve trigger term coverage for users who may use different terminology.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'extracts and structures source material', 'talk summary with narrative arc, themes, metrics, and gaps', 'auto-detects REX vs Concept type', and 'auditing existing material'. These are concrete, well-defined 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'). The explicit 'Use when...' clause is present with clear trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'articles', 'transcripts', 'notes', 'talk', 'source material', but the domain is fairly niche (talk preparation) and some terms like 'REX vs Concept type' are 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: structuring source material specifically into talk summaries with narrative arcs and type detection (REX vs Concept). This is unlikely to conflict with general document processing or presentation creation skills due to its specific domain focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that clearly defines a content extraction workflow with good validation checkpoints and a comprehensive output template. Its main weakness is that the extraction process itself is described at a specification level rather than with concrete, executable steps — Claude is told *what* to produce but the *how* relies on implicit understanding. Some sections are mildly redundant, repeating the skill's purpose across 'When to Use', 'What This Skill Does', and the opening line.
Suggestions
Make the source type detection more actionable by providing a concrete algorithm or decision tree (e.g., 'Count REX signals vs Concept signals; if REX > 60%, classify as REX') rather than just a signal table.
Remove or consolidate the 'When to Use This Skill' section — it repeats information already in the opening line and the 'Tips' section.
| 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 formatting rules for metrics, which is concrete. However, there are no executable code examples, no specific commands to run, and the actual extraction process is described abstractly ('Reads the source', 'Detects source type') rather than with concrete implementation steps. The guidance is more of a specification than executable instructions. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: collect metadata → read source → detect type → extract arc → extract metrics → identify themes → flag gaps → write file. The validation checklist at the end serves as an explicit checkpoint. The 'AskUserQuestion' step for missing metadata is a clear feedback loop. The metric extraction rules provide guardrails for a potentially error-prone step. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with clear sections that progress logically from overview to details. References to related stages (Stage 2, Stage 3, Orchestrator) are one level deep and clearly signaled. The content is appropriately self-contained for a single skill file with no bundle, and the length is justified by the output template specification. | 3 / 3 |
Total | 10 / 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
60a4372
- 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.