Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly communicates a distinctive workflow (interactive fragment mining for pre-structural writing), provides explicit trigger guidance via a 'Use when' clause, and uses natural language terms users would actually say. The parenthetical elaboration of what 'fragments' means adds helpful specificity without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'mines the user for fragments', 'heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts)', and 'appends them to a single document as raw material for a future article'. These are specific, tangible actions describing what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (grilling session that mines fragments and appends them to a document) and 'when' (explicit 'Use when' clause specifying the user wants to develop ideas before imposing structure, or mentions specific trigger terms). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'fragments', 'ideate', 'raw material', 'writing', 'develop ideas', 'article'. The parenthetical examples (claims, vignettes, sharp sentences, half-thoughts) also serve as natural keywords a user might mention. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche: pre-structural ideation through fragment collection appended to a single document. The specific workflow (interactive mining → appending raw material) and distinct trigger terms ('fragments', 'ideate', 'raw material') make it unlikely to conflict with general writing or editing skills. | 3 / 3 |
Total | 12 / 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 running a fragment-mining session. Its strengths are the concrete file format example, explicit behavioral rules (re-read before write, append-only), and well-defined scope boundaries. The main weakness is moderate verbosity in explaining what fragments are and how the session should feel — content that could be tightened by about 30% without losing clarity.
Suggestions
Tighten the 'What is a fragment' section — the bullet list of examples is useful but the introductory paragraph and the novelist's diary metaphor could be condensed into one sentence.
Trim the 'How the session feels' section by removing some of the example prompts (keep 2-3 strongest) and condensing the behavioral guidance into fewer, punchier bullet points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and the content is genuinely useful, but it over-explains what a fragment is with an extensive list of examples and metaphors ('The novelist's diary is the model') that Claude could infer from a shorter description. The 'How the session feels' section, while valuable, could be tightened — some of the example prompts are illustrative but slightly verbose. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific file format with a complete markdown example, explicit behavioral instructions (re-read before writing, append only, use horizontal rules), clear interaction patterns with example prompts ('say it three different ways'), and precise handling of edge cases (no path given, user edits between turns, 'cut the last one' commands). | 3 / 3 |
Workflow Clarity | The workflow is clear and well-sequenced: ask for path → create file with H1 → re-read before every write → append fragments separated by --- → handle user edit commands. The re-read-before-write step serves as a validation checkpoint that prevents data loss. The 'never overwrite, only append' constraint and explicit handling of user edits ('cut the last one', 'merge those two') provide appropriate safeguards for a file-writing operation. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (what-to-do, supporting-info with subsections), but everything is inline in a single file. For a skill of this length (~100 lines of substantive content), the fragment examples and session feel guidance could potentially be split out, though it's borderline. The structure is good but not exemplary — no external references are needed but the inline content is on the heavy side. | 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.
494e4b2
Table of Contents
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.