CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

to-spec

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

Quality

73%

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 ./eval/archives/grill-test-20261013/application/skills/to-spec/SKILL.md
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.

The body is a tight, actionable instruction skill: a numbered process with a genuine user checkpoint, a complete spec template, a worked user-story example, and a concrete publishing label. Its only deductions are minor opening-paragraph redundancy and a publish step whose mechanism lives outside this file.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows, but has minor trimmable redundancy: the opening paragraph restates the frontmatter description ("This skill takes the current conversation context and codebase understanding and produces a spec. Do NOT interview the user — just synthesize what you already know"), and "A LONG, numbered list" plus "should be extremely extensive and cover all aspects of the feature" says the same thing twice.

4 / 5

Actionability

For an instruction-only skill the guidance is highly concrete — a 3-step process, a full spec template with named sections, an explicit user-story format with a worked example ("As a mobile bank customer, I want to see balance on my accounts..."), the concrete triage label `ready-for-agent`, and a sharp seam rule ("The fewer seams across the codebase, the better - the ideal number is one"). The one gap is that "publish it to the project issue tracker" is delegated to an external setup skill ("should have been provided to you"), so the final step is not executable from this file alone.

4 / 5

Workflow Clarity

The process is a clearly sequenced 3 steps with a real mid-flow checkpoint ("Check with the user that these seams match their expectations") before writing and publishing. It falls short of anchor 5 because there is no post-publish verification or error-recovery loop (e.g. confirming the ticket was created with the label applied).

4 / 5

Progressive Disclosure

The skill is a single self-contained file with no bundle directories; content is well-organized (intro, numbered process, clearly delimited spec template) and everything belongs inline since the template is the working artifact used on every invocation. Per the simple-skill scoring note, a single-task skill with no need for external references scores 5 on well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

53%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 states a clear, concrete dual action (synthesize a spec from the conversation, publish it to the issue tracker) and is refreshingly lean, with a distinctive "no interview" framing. Its main weakness is the complete absence of explicit trigger guidance — no "Use when..." clause — and no synonym coverage, leaving a user to guess when to invoke it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to turn the discussion into a spec, write up requirements, or file agreed work as a ticket."

Include natural synonyms for discoverability, such as "specification", "requirements doc", or "user stories", so users phrasing the request differently still match.

Mention one or two concrete spec artifacts (problem statement, user stories) to raise specificity beyond the current two-action summary.

DimensionReasoningScore

Specificity

"Turn the current conversation into a spec and publish it to the project issue tracker" names exactly two concrete actions (synthesize a spec from the conversation, publish it to the tracker), matching the anchor for 1-2 concrete actions that are not comprehensive; score 4 requires several specific actions, which this lacks.

3 / 5

Completeness

The "what" is clear ("Turn the current conversation into a spec and publish it to the project issue tracker"), but there is no "Use when..." clause or equivalent explicit trigger guidance — "just synthesis of what you've already discussed" only weakly implies timing — so completeness is capped at 3 per the judging guideline.

3 / 5

Trigger Term Quality

"spec", "conversation", and "issue tracker" are natural terms a user would say, but common variations and synonyms ("specification", "requirements doc", "user stories", "PRD") are missing, matching the anchor for some relevant keywords without variation coverage.

3 / 5

Distinctiveness Conflict Risk

The combination of conversation-to-spec synthesis, issue-tracker publishing, and the distinguishing anti-feature "no interview, just synthesis of what you've already discussed" carves a mostly distinct niche with only minor overlap risk against other spec- or documentation-writing skills.

4 / 5

Total

13

/

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

rpamis/comet

Path

eval/archives/grill-test-20261013/application/skills/to-spec/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.