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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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.

A well-structured, actionable instruction skill: a concrete output template, explicit extraction rules, a clear step sequence, and a validation checklist. The main improvements are de-duplicating the Tips section and adding an explicit feedback loop tying the validation checklist to a retry step.

Suggestions

De-duplicate the 'Tips' section against 'When to Use This Skill' (e.g. 'Run this before the orchestrator' restates 'First step of the talk pipeline') to tighten conciseness.

Tie the final 'Validation Checklist' to an explicit feedback loop (e.g. 'If any unchecked item fails, return to the relevant step and re-run before saving') to lift workflow_clarity toward 5.

Consider splitting the long output-format template into a referenced file (e.g. references/summary-template.md) only if the skill grows; for now the inline template is appropriate, so this is low priority.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding over concepts Claude already knows (no explanation of what transcripts or metrics are); the only minor trim is the 'Tips' section overlapping 'When to Use This Skill', placing it at anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Provides a copy-paste-ready output template with concrete metric examples ('1,200 commits over 7 months (Source: "acceleration" section)'), precise extraction rules ('If two sources contradict, flag both without picking one'), and a detection-signal table — specific examples cover the common cases, matching anchor 5 for this instruction-only skill.	5 / 5
Workflow Clarity	Clear 8-step sequence in 'What This Skill Does', an explicit conditional checkpoint ('If metadata is missing -> AskUserQuestion'), and a final validation checklist; missing only an explicit validate→fix→retry feedback loop, so anchor 4 rather than 5. The operation is non-destructive, so the batch/destructive cap-at-3 does not apply.	4 / 5
Progressive Disclosure	Single self-contained file with clear section headers and well-signaled one-level-deep 'Related' links to sibling pipeline skills; no bundle files exist to mis-organize. The inline output template is appropriately core rather than reference material, fitting anchor 4; it is over 50 lines and lacks an overview→details split, so not anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong description that concretely states capabilities, explicitly pairs a 'what' with a 'when' trigger clause, and carves out a distinct niche in a talk-preparation pipeline. Minor room to broaden trigger synonyms, but it is well above the midpoint on every dimension.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Extracts and structures source material', 'into a talk summary with narrative arc, themes, metrics, and gaps', 'Auto-detects REX vs Concept type') with only minor coverage gaps, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Extracts and structures… into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type') and when ('Use when starting a new talk… or auditing existing material before committing to a talk') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('starting a new talk from any source material', 'auditing existing material', 'before committing to a talk') with good coverage, but lacks synonym/file-extension breadth that would warrant anchor 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (talk-creation pipeline stage 1) with distinct triggers ('talk summary', 'narrative arc', 'REX vs Concept type') and minimal overlap risk with other skills, matching anchor 5.	5 / 5
	Total	18 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Path: examples/skills/talk-pipeline/stage-1-extract/SKILL.md
Commit: 752edfe

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.