CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-like-me

Use this skill when the user asks to "draft this email in my voice", "rewrite this message like me", "sound like me", "learn my writing style", "update my voice profile", or "inspect my writing voice". Covers personal writing style emulation, tone calibration, and profile maintenance. Do NOT use this skill for filing notes or organizing vaults (use `para-vault`) or raw file operations (use `manage-file-operations`).

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/write-like-me/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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.

The body is well-structured and concise with sensible invariants and a verification checklist, but its progressive disclosure is substantially broken against the real bundle: the two workflow runbooks it routes to don't exist, and four of the five reference files are orphaned with no links from the entry point. The result is an orchestrator whose concrete procedures are unreachable.

Suggestions

Fix the broken references: either add the missing `workflows/draft.md` and `workflows/maintain.md` files or repoint the triage matrix at the actual bundle files (e.g., `references/drafting-and-review.md` and `references/calibration.md`).

Link the four orphaned reference files (`calibration.md`, `drafting-and-review.md`, `learning-from-edits.md`, `storage.md`) from the body so the detailed material is discoverable from the entry point, per one-level-deep progressive disclosure.

Trim the duplicated scope-exclusion text in the IMPORTANT callout, which restates the frontmatter description's boundaries nearly verbatim.

DimensionReasoningScore

Conciseness

The body is efficient — no concept over-explanation, compact triage table, terse invariants, and a checklist — but the scope directive callout ("It does NOT own filing drafted notes into a PARA vault... or raw filesystem mechanics...") duplicates the frontmatter's exclusions, which could be trimmed. Anchor 4 fits: efficient with minor instances that could be tightened; anchor 3 would require noticeably unnecessary explanation, which is not present.

4 / 5

Actionability

Concrete, specific guidance exists (specific paths like `.nyssa-ai/agent-skills/writing-voice/`, specific files `VOICE.md`/`STYLE.md`, a triage table, and a verification checklist), but the primary executable runbooks it routes to — [`workflows/draft.md`](workflows/draft.md) and [`workflows/maintain.md`](workflows/maintain.md) — do not exist anywhere in the bundle, so the actual steps are unreachable. This is a major gap, not the minor gaps of anchor 4, while the concrete path/file/precedence detail exceeds the high-level-hints-only level of anchor 2.

3 / 5

Workflow Clarity

Routing sequencing is clear (intent → runbook table) and an explicit verification checklist provides checkpoints, so it is above anchor 2's poorly-defined-steps level. But the multi-step processes the routing points to live in the missing `workflows/draft.md` and `workflows/maintain.md` files, so the actual sequenced workflows with feedback loops cannot be followed from the skill as shipped — below anchor 4's 'clear sequence with most checkpoints present'.

3 / 5

Progressive Disclosure

Scored against the actual bundle: 2 of the 3 links in the body (`workflows/draft.md`, `workflows/maintain.md`) are broken — no `workflows/` directory exists — and 4 of the 5 real reference files (`calibration.md`, `drafting-and-review.md`, `learning-from-edits.md`, `storage.md`) are never referenced from SKILL.md, leaving them undiscoverable. The body's own section structure is decent, but the overview fails its core navigation role, fitting anchor 2's 'references are buried'/broken-navigation level better than anchor 3's 'references present but not clearly signaled'.

2 / 5

Total

12

/

20

Passed

Description

95%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.

The description is a strong example: natural trigger phrases with synonym coverage, explicit what/when, and named-skill exclusion boundaries that sharply reduce mis-routing. The only mild weakness is that the capability summary sentence is more abstract than the concrete trigger phrasing.

DimensionReasoningScore

Specificity

Quotes concrete user actions ("draft this email in my voice", "rewrite this message like me", "learn my writing style", "update my voice profile", "inspect my writing voice") covering drafting, learning, updating, and inspecting. Not 5 because the capability sentence "Covers personal writing style emulation, tone calibration, and profile maintenance" is abstract summary language rather than a fully concrete action list, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both questions: "Use this skill when the user asks to..." gives concrete when-triggers, and "Covers personal writing style emulation, tone calibration, and profile maintenance" gives the what, with explicit negative boundaries. Matches the top anchor exactly.

5 / 5

Trigger Term Quality

Six natural phrases users would actually say, with synonym variations ("draft this email in my voice", "rewrite this message like me", "sound like me", "learn my writing style", "update my voice profile", "inspect my writing voice") — matches the comprehensive-coverage-with-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (personal writing voice) with distinct triggers and explicit exclusions routing lookalike requests to named siblings ("use `para-vault`", "use `manage-file-operations`"). Minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

NyssaAI/agent-skills

Path

skills/write-like-me/SKILL.md

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.