talk-pipeline

Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints for REX or Concept mode talks. Use when starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow.

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

83%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 orchestrator skill body with clear sequencing, explicit checkpoints, a dependency graph, and concrete commands and naming conventions. Minor redundancy in the output-naming listing and delegation to sibling skills (rather than inline detail) keep it just below perfect on conciseness and actionability.

Suggestions

Consolidate the output naming convention so filenames appear once and the Final Summary Format references it, reducing duplicated token usage.

Add a short inline note on what each stage produces at a high level so the orchestrator is actionable without requiring the reader to open every stage skill.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient—sections are tight, use tables and code blocks for structure, and avoid explaining concepts Claude already knows—though the duplicated output-naming convention (listed once then re-listed in the Final Summary Format) adds some redundant tokens.	4 / 5
Actionability	Provides concrete, executable guidance: exact slash-command invocations, a stage routing table mapping each stage to a skill, and a precise output naming convention with real filenames. It stops short of 5 because the per-stage behavior is delegated to other skills rather than shown inline.	4 / 5
Workflow Clarity	The 8-step workflow is clearly sequenced with an explicit CHECKPOINT after Stage 4 (angle + title choice) and again at the kimi-prompt verification step, plus a dependency graph, an anti-patterns section, and a validation checklist with verification items—exemplifying explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	Structure is well organized with clearly labeled sections (Modes, Usage, Workflow, Dependency Graph, Stage Routing, Output Naming, Anti-patterns, Validation) and a one-level-deep Related section linking each stage skill. No bundle files exist locally, so it scores on structure rather than bundle navigation; the body is self-contained rather than pointing into a deeper reference tree.	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, specific description that clearly answers both what the skill does and when to use it, with concrete capabilities and explicit triggers. The main weakness is somewhat narrow trigger vocabulary and overlap with sibling stage skills.

Suggestions

Add a few synonym trigger phrases (e.g., 'preparing a conference talk', 'building a presentation from source material') to broaden natural keyword coverage.

Distinguish the orchestrator from the individual stage skills by noting it is the top-level entry point that coordinates the per-stage skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—orchestrating a 6-stage pipeline, running stages in sequence with human-in-the-loop checkpoints, supporting REX/Concept modes—and names specific output types (revision sheets, changelog), giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (orchestrates the complete talk preparation pipeline from raw material to revision sheets, 6 stages, REX/Concept modes) and 'when' ('Use when starting a new talk pipeline, resuming... or running the full end-to-end preparation workflow') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('Use when starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow'), but relies on the term 'talk' repeatedly without synonyms or alternate phrasings a user might say.	4 / 5
Distinctiveness Conflict Risk	The 'talk preparation pipeline' niche is distinct and unlikely to trigger for unrelated skills, but the orchestrator overlaps with the individual stage skills it invokes, creating minor conflict risk between this and the stage skills.	4 / 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: 7 suspicious	Warning

	Total	14 / 16 Passed

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

Reviewed: about 10 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.