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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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 body with concrete commands, a clear sequenced workflow, checkpoints, and clean one-level-deep delegation to per-stage skills. The main weakness is redundancy: the generated-file list appears twice, which inflates token cost without adding information.

Suggestions

Remove the duplicate file listing: keep the 'Output Naming Convention' block and have 'Final Summary Format' reference it (or vice versa) instead of repeating all paths verbatim.

Consider collapsing the 'Usage' code block, the 'Workflow' steps, and the 'Stage Routing' table, which restate the same stage-to-skill mapping three times in slightly different forms.

Move the long static file manifest into a references file (e.g. references/outputs.md) so the SKILL.md overview stays lean while retaining the exact naming convention.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and sectioned, but the same output file list is stated twice - once in 'Output Naming Convention' (lines 89-104) and again verbatim in 'Final Summary Format' (lines 110-139) - which is removable duplication. Not a 1 because no concepts Claude already knows are explained; not a 3 because the duplicated listing could be tightened.	2 / 3
Actionability	Gives concrete, copy-paste-ready guidance: exact slash commands per stage ('/talk-stage1-extract', '/talk-stage5-script'), exact flags ('--rex', '--concept', '--stage=extract'), a stage-routing table, and a precise output naming convention 'talks/{YYYY}-{slug}-{stage}.md'. For an instruction-only orchestrator this is fully actionable.	3 / 3
Workflow Clarity	The 6-stage process is sequenced in a numbered workflow, visualized in a dependency graph, gated by an explicit 'CHECKPOINT: wait for angle + title choice', and backed by a validation checklist and anti-patterns ('Do not proceed... if an upstream stage failed'). Checkpoints and validation are present, so it is not capped at 2.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent); the SKILL.md is a clear overview that delegates each stage's detail to its own one-level-deep skill link in 'Related' (../stage-1-extract/SKILL.md ... ../stage-6-revision/SKILL.md), with no nested/deep references. Content is appropriately split across the per-stage skills.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 well-crafted description that states concrete capabilities, includes an explicit 'Use when' trigger clause, and occupies a clear niche. It avoids verbosity and over-claims while covering both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names several concrete actions - 'Orchestrates the complete talk preparation pipeline from raw material to revision sheets, running 6 stages in sequence with human-in-the-loop checkpoints' - specifying the input/output, the 6-stage structure, and the checkpoint mechanism rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Orchestrates the complete talk preparation pipeline... running 6 stages... with human-in-the-loop checkpoints') and when ('Use when starting a new talk pipeline, resuming...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	The 'Use when' clause lists natural trigger phrases a user of this system would say - 'starting a new talk pipeline, resuming a pipeline from a specific stage, or running the full end-to-end preparation workflow' - covering the main invocation scenarios.	3 / 3
Distinctiveness Conflict Risk	The 'talk preparation pipeline' niche with 'REX or Concept mode' qualifiers is a clear, distinct trigger surface unlikely to collide with unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: eb4fbbd

Reviewed: 2 days 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.