CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

technical-writer

Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A well-structured instruction-only skill with a coherent working process, concrete editorial rules, and exemplary progressive disclosure — every reference file is real, substantive, and signposted with read-conditions. The main improvement opportunities are trimming cross-section redundancy and adding one or two worked before/after examples to make the editorial rules immediately imitable.

Suggestions

Consolidate the verification-and-handoff guidance that recurs across "Ground the content", "Make procedures and examples usable", and "Prepare the handoff" into a single place, pointing to technical-verification.md for detail, to cut roughly 15-20% of body length.

Add one compact worked example in "Edit with a reason" — a short original passage, the identified problem, and the revised passage — so the five-step procedure is demonstrated rather than only described.

Include a small sample handoff note under "Prepare the handoff" (e.g., a filled-in list of checks performed and unresolved gaps) to make the reporting requirements copy-paste concrete.

DimensionReasoningScore

Conciseness

The body is rule-dense with essentially no filler explaining concepts Claude already knows — nearly every sentence is a directive such as "Do not change code identifiers, quoted errors, UI labels, or official names to satisfy a prose rule" or "Match UI labels exactly and format them in bold." There is minor redundancy (verification and handoff guidance recurs across "Ground the content", "Make procedures and examples usable", and "Prepare the handoff") and the body could be tightened by roughly 20%, which fits the efficient-with-minor-trimmable-instances anchor rather than the mostly-efficient-but-noticeably-padded one.

4 / 5

Actionability

Guidance is concrete and executable throughout for an instruction-only skill: a numbered five-step editing procedure, specific formatting rules ("Use inline code for file paths, commands, identifiers, environment variables", "Label fenced code blocks with their language"), and operational specifics like "mktemp -d" and lint-tool usage. It stops short of the top anchor because the body contains no worked examples (e.g., a before/after revision or sample handoff), which would make the editorial rules directly copyable; there are no missing key details that would drop it to 3.

4 / 5

Workflow Clarity

The workflow is clearly sequenced — establish the reader's task, working notes, delegation, site conventions, grounding, drafting, procedures, editing, whole-document review, handoff — with verification checkpoints ("Compare the revision directly with the original", the pre-handoff checklist "verify that the reader's task is answered, claims retain their scope...") and a feedback loop for regressions ("When feedback identifies a regression, reassess the passage's purpose..."). Minor gaps keep it below 5: validation steps are described prose-wise rather than as an explicit validate-fix-retry loop, and the overall sequence must be inferred from section order.

4 / 5

Progressive Disclosure

The body is an overview of process guidance that delegates detail to three real, substantive, one-level-deep bundle files, each clearly signaled with when-to-read conditions: "Read [editorial standards](references/editorial-standards.md) for every writing or editing task. Read [technical verification](references/technical-verification.md) when the work contains product claims, procedures, configuration, or code. Read [content patterns](references/content-patterns.md) when planning or restructuring a documentation page." All referenced paths exist and none of the references nest further; the core-vs-detail split is appropriate and easy to navigate, matching the top anchor.

5 / 5

Total

17

/

20

Passed

Description

88%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.

A strong description that clearly states what the skill does and when to use it, with third-person voice, concrete actions, and comprehensive document-type triggers. The main gaps are missing common synonyms ("docs", "how-to") and some residual overlap risk with generic writing skills.

DimensionReasoningScore

Specificity

"Write, review, and edit developer documentation for SDKs, libraries, and frameworks" names three concrete actions, and the coverage of document types is comprehensive: "getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples." This matches the anchor for multiple specific concrete actions with comprehensive coverage; score 4 would require noticeable coverage gaps, and none are apparent.

5 / 5

Completeness

Both questions are explicitly answered: the what ("Write, review, and edit developer documentation for SDKs, libraries, and frameworks") and the when ("Use for getting-started guides, tutorials, API references...") with concrete trigger phrases. The explicit "Use for..." clause is equivalent trigger guidance, matching the anchor where both what and when are answered clearly; the anchor for 4 requires the when to be weaker or less specific, which is not the case here.

5 / 5

Trigger Term Quality

Natural trigger phrases users would actually say are well covered ("tutorials", "API references", "migration guides", "troubleshooting", "getting-started guides"), plus site names like ai-sdk.dev. It falls short of the comprehensive-synonym anchor because common variations such as "docs", "documentation site", or "how-to" are absent, but it is clearly above the "some relevant keywords" level.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — developer documentation for SDKs with named destination sites (ai-sdk.dev, chat-sdk.dev) and document-type-specific triggers — but "write, review, and edit documentation" broadly overlaps with general writing and editing skills, creating minor conflict risk with closely related skills. It is more distinct than the "somewhat specific but could still overlap" anchor, but not the minimal-conflict clear-niche anchor.

4 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

vercel-labs/deepsec

Path

.agents/skills/technical-writer/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.