kickoff-doc
Turn a shaped project kickoff transcript into a reference document for the builder. Use when the user has a transcript (VTT, etc.) from a kickoff call and wants to produce a document that captures what was shaped and agreed.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 well-crafted description with a clear 'Use when' clause and a distinct niche. Its main weakness is that it could be more specific about the concrete actions performed on the transcript (e.g., extracting decisions, scope boundaries, open questions, appetite). The trigger terms and completeness are strong.
Suggestions
Add 2-3 more specific concrete actions to boost specificity, e.g., 'Extracts scope, decisions, open questions, and appetite from a shaped project kickoff transcript to produce a builder reference document.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (shaped project kickoff transcript) and the core action (turn into a reference document), but doesn't list multiple specific concrete actions like extracting decisions, capturing scope, listing open questions, etc. | 2 / 3 |
Completeness | Clearly answers both what ('Turn a shaped project kickoff transcript into a reference document for the builder') and when ('Use when the user has a transcript (VTT, etc.) from a kickoff call and wants to produce a document that captures what was shaped and agreed'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords a user would say: 'transcript', 'VTT', 'kickoff call', 'shaped', 'reference document', 'builder'. These are terms someone with a kickoff recording would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining shaped project methodology, kickoff transcripts, and builder reference documents. Unlikely to conflict with generic transcription or document generation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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-crafted skill that provides clear, actionable guidance for a specific document-generation task. Its greatest strengths are the concrete structural template (Frame/Shape), the inline design decisions principle with real examples, and the clear 6-step process with a verification step. The main weakness is moderate verbosity in explanatory sections that could be tightened without losing clarity.
Suggestions
Tighten the 'Organizing Principle' section — the description of what transcripts look like ('circle back, go on tangents, get sidetracked by browser issues') is unnecessary context Claude can infer.
Consider condensing the Voice Do/Don't lists into a more compact format, as the distinction between synthesis and editorializing could be stated more concisely.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining things Claude already knows, but some sections are slightly verbose — e.g., the 'Voice' section's Do/Don't lists and the 'Organizing Principle' section could be tightened. The explanation of what a kickoff transcript looks like ('people talk through things in order, circle back, go on tangents, get sidetracked by browser issues') is somewhat unnecessary padding. | 2 / 3 |
Actionability | The skill provides highly concrete, specific guidance: exact document structure (## Frame, ## Shape, ### Problem, ### Outcome), clear rules for where to place design decisions with specific examples ('Matches stored in DB not Redis → goes in the section about matching'), and a concrete test for every sentence written. No code is needed here — the guidance is fully actionable for document generation. | 3 / 3 |
Workflow Clarity | The 6-step process at the end is clearly sequenced and logical, with an explicit validation step (step 6: review against transcript). The 'Before You Start' section establishes prerequisites. The workflow naturally builds from reading → identifying structure → drafting frame → writing sections → placing decisions → reviewing, which is a well-ordered sequence with a verification checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's all inline in a single file at ~100 lines. The Voice section and Design Decisions section could potentially be separated or condensed. For a skill of this complexity, the structure is adequate but the inline examples and extended explanations make it slightly monolithic. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- rjs/shaping-skills
- Commit
d8b65d7
- 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.