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.
82
80%
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/orchestrator/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is well-structured with clear 'what' and 'when' clauses, and is highly distinctive due to domain-specific terminology. However, it could benefit from listing the specific stages or actions within the pipeline rather than abstracting them as '6 stages', and could include more natural user-facing trigger terms beyond the specialized jargon.
Suggestions
List the specific stages or key actions in the pipeline (e.g., 'outline drafting, content structuring, slide generation...') to improve specificity.
Add more natural trigger terms a user might say, such as 'prepare a talk', 'presentation prep', 'conference talk', or 'speech preparation' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It mentions 'talk preparation pipeline', '6 stages', 'human-in-the-loop checkpoints', 'REX or Concept mode talks', and 'revision sheets', which names the domain and some actions but doesn't list the specific concrete actions/stages performed (e.g., outline generation, slide creation, etc.). | 2 / 3 |
Completeness | Clearly answers both 'what' (orchestrates complete talk preparation pipeline from raw material to revision sheets, 6 stages with human-in-the-loop checkpoints) and 'when' (starting a new talk pipeline, resuming from a specific stage, or running the full end-to-end workflow) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'talk pipeline', 'talk preparation', 'REX', 'Concept mode', 'revision sheets', and 'stage', but these are fairly specialized. Common user phrases like 'prepare a talk', 'presentation prep', or 'speech preparation' are missing, and 'REX' and 'Concept mode' are domain-specific jargon that only insiders would use. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific domain terms like 'talk preparation pipeline', 'REX or Concept mode', '6 stages', and 'revision sheets' that clearly carve out a unique niche unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%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 orchestrator skill that clearly defines a multi-stage pipeline with proper checkpoints, validation, and mode routing. Its main weakness is some redundancy between the workflow description, dependency graph, and stage routing table, plus the verbose final summary template. Overall it's a strong skill that effectively guides Claude through a complex multi-stage process with appropriate human-in-the-loop controls.
Suggestions
Consolidate the workflow section and dependency graph into a single representation to reduce redundancy — the ASCII graph could replace the numbered workflow list.
Remove the Tips section as it adds minimal actionable value and explains things Claude can infer from the rest of the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy — the dependency graph, stage routing table, and workflow section overlap significantly. The final summary format template and output naming convention are both lengthy but arguably necessary for an orchestrator. The tips section adds little value. | 2 / 3 |
Actionability | Provides concrete CLI commands, a clear stage routing table mapping stages to specific skill invocations, explicit context collection fields, and precise output file naming conventions. The checkpoint and anti-patterns sections give specific, actionable constraints. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with an explicit CHECKPOINT before Stage 5, a dependency graph visualization, parallel execution paths clearly defined, anti-patterns listing failure modes, and a validation checklist ensuring upstream files exist before downstream stages run. The feedback loop (don't proceed if upstream failed) is explicit. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear orchestrator overview with well-signaled one-level-deep references to each of the 6 stage skills and a full workflow guide. Content is appropriately split — the orchestrator describes routing and sequencing while delegating stage-specific details to linked files. | 3 / 3 |
Total | 11 / 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
4ef3dec
- 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.